The Mamba architecture has been widely applied to various low-level vision tasks due to its exceptional adaptability and strong performance. Although the Mamba architecture has been adopted for spectral reconstruction, it still faces the following two challenges: (1) Single spatial perception limits the ability to fully understand and analyze hyperspectral images; (2) Single-scale feature extraction struggles to capture the complex structures and fine details present in hyperspectral images. To address these issues, we propose a multi-scale, multi-perceptual Mamba architecture for the spectral reconstruction task, called M3SR. Specifically, we design a multi-perceptual fusion block to enhance the ability of the model to comprehensively understand and analyze the input features. By integrating the multi-perceptual fusion block into a U-Net structure, M3SR can effectively extract and fuse global, intermediate, and local features, thereby enabling accurate reconstruction of hyperspectral images at multiple scales. Extensive quantitative and qualitative experiments demonstrate that the proposed M3SR outperforms existing state-of-the-art methods while incurring a lower computational cost.

In extended reality (XR) virtual interaction environments, both flexible user interaction and reliable authentication are essential. However, current wearable systems relying on single-sensor data suffer from insufficient data dimensionality, often failing to simultaneously achieve fine-grained gesture recognition and continuous authentication. Multi-sensor systems, while more capable, tend to be bulky, comfort-compromising, and computationally demanding for edge deployment. Furthermore, inefficient parallel processing and the decoupled pipeline for gesture and authentication tasks degrade computational efficiency, ultimately hindering practical adoption. To overcome these limitations, we propose M-Ring, a lightweight ring-based system equipped with a compact, optimized sensor layout that synchronously captures impedance and IMU signals. By fusing complementary physiological and behavioral cues, M-Ring enables accurate hand-state perception. We design an adaptive-scale convolutional network with a parameter-separated and progressively routed architecture (PLE), which effectively captures intrinsic correlations within multimodal data and enhances synergy between gesture recognition and user authentication, all while minimizing computational overhead. For fine-grained authentication, we propose a dual-factor framework that integrates Siamese networks with contrastive learning to enhance inter-user discriminability. By jointly modeling physiological activations and kinematic patterns, our approach enables both seamless gesture-based interaction and non-intrusive continuous authentication. Experiments demonstrate that M-Ring achieves 97.8% gesture recognition accuracy and 97.5% identity authentication accuracy under complex conditions, while maintaining low enrollment cost, power efficiency, low latency, and strong edge deployment capability.

Underground fires pose a significant threat to production safety in coal mines, and existing detection methods suffer from drawbacks such as poor adaptability to complex subterranean environments and excessive model parameters. To address the need for deploying object detection models on resource-constrained devices, this paper proposes a novel and efficient algorithm forUndergroundFireYOLOdetection, named UF-YOLO. The core innovation of this method is threefold: first, the StarNet module is introduced into the backbone to significantly reduce model parameters and computational complexity without sacrificing accuracy; second, the Cross-scale Context Fusion Module (CCFM) is integrated into the neck to enhance the model’s detection capability for fires of various scales, particularly small targets; and finally, Partial Convolution (PConv) is integrated to extract spatial features more efficiently, further reducing redundant computations and memory access. On our self-built Mine Fire Image Dataset (MFID), compared to the baseline model YOLOv11m, UF-YOLO reduces parameters by 77.1%, increases inference speed by 60.6%. Experimental results on the public COCO val 2017 dataset demonstrate that the proposed method outperforms state-of-the-art (SOTA) models such as YOLOv12. The results confirm that UF-YOLO can be efficiently deployed on the edge-side of coal mine IoVT monitoring systems to performe accurate and real-time fire detection. This work provides a new intelligent paradigm for the real-time monitoring of underground fires.

The security of voice control in the Voice Internet of Things (Voice IoT) heavily relies on the fast and accurate authentication of the command issuer. In this work, we focus on the critical application scenario of Voice IoT in underground coal mines, where voice commands typically last 4–10 seconds. Speech in this scenario typically consists of short, imperative utterances and faces challenges from environmental noise and device heterogeneity. The limitations of traditional speaker verification models in temporal modeling restrict their performance in such scenarios. To address this, this paper proposes a three-dimensional attention module (Branch-MFA) designed for Voice IoT. This module employs a dual-parallel branch architecture: the MFA branch is responsible for extracting attention in the frequency and channel dimensions, and its multi-scale nature enables it to effectively focus on speaker-discriminative frequency bands that remain stable under noise and different collection devices, thereby enhancing the model’s environmental robustness; the GLTA branch, through its innovative grouped variable-length attention mechanism, specifically models the temporal structure of these short voice commands, addressing the challenge of sparse temporal information in short utterances. By integrating the dual-branch outputs through a fusion module, we construct the Branch-MFA-TDNN model. Experiments on the Cn-Celeb dataset show that this model significantly outperforms baseline models in short-utterance verification tasks, particularly for the challenging 4–10 second duration relevant to mine communications, providing an identity authentication solution for Voice IoT that combines high security and real-time performance. We have also released the code1for future comparison.

Vehicular edge computing is rapidly amplifying the need to process computation-intensive tasks generated in vehicular environments. Conventional centralized processing frameworks struggle to meet these low-latency demands due to network latency and bandwidth constraints. Federated learning (FL) addresses these challenges by retaining raw data on vehicle nodes (VNs). However, sustainable FL training in vehicular edge computing faces persistent obstacles: the instability of VNs (high entry/exit rates), resource heterogeneity, and the lack of effective incentives. Notably, while existing incentive mechanisms are extensively studied, they inadequately address two critical sustainability barriers: extreme data heterogeneity and the volatile energy costs of mobile VNs. To overcome these challenges, we propose an auction-based sustainable federated learning (ASFL) framework. In this framework, the edge server acts as both the FL task publisher and the auctioneer, while VNs serve as bidders. Each bid encapsulates critical attributes including data quality, computing capacity, and projected energy cost. The core objective of ASFL is to maximize long-term social welfare. Formulating this objective reveals an inherently nonconvex optimization problem. Through rigorous analysis, we derive an equivalent convex formulation. The systematic bidder selection process inherent in ASFL simultaneously mitigates data heterogeneity and promotes rational energy utilization across FL. We theoretically prove that the framework achieves incentive compatibility and individual rationality. Experimental results on MNIST and CIFAR-10 datasets demonstrate the effectiveness of the method in mitigating the impact of non-i.i.d. data and reducing energy consumption.

The Internet of Nano Things (IoNT) refers to an interconnected network of nanoscale components engineered to perform tasks such as data processing, storage, and actuation. IoNT has broad applications, including environmental monitoring and pollution source localization. In order to achieve monitoring and localization for multiple releasing sources (RSs), the deployment of nanosensor networks is indispensable. However, constrained by spatial limitations and high costs, sensors can only be sparsely deployed, resulting in severe degradation in localization performance. In this paper, we consider a turbulent diffusion molecular communication scenario and the objective is to enable multi-source localization and obstacle perception with sparse nanosensors. For sparse signal recovery, we first propose a real-symmetric based on Truncated Nuclear Norm Regularization with Alternating Direction Method of Multipliers (RS-TNNR) matrix completion algorithm, which utilizes the spatial symmetry of molecular diffusion to achieve precise data recovery under high missing ratios. Furthermore, for multi-source localization and obstacle perception, we also propose an Adaptive Iterative Grid based on Sparse Bayesian Learning (AIG-SBL) algorithm, which enhances the localization accuracy with SBL, mitigates off-grid errors via the proposed adaptive iterative grid, and simultaneously estimates obstacle position and radii. Simulation results demonstrate the effectiveness of the proposed algorithms for RS-TNNR and AIG-SBL.

The transmission of semantic information related to users’ interests can significantly reduce the network transmission burden. However, if a base station transmits semantic information to a group of users simultaneously, partially similar interests among them inevitably produce repetitive transmission and higher energy consumption. Additionally, the worst channel condition among users impedes enhancements to network capacity. To achieve green communication and enhance network capacity, this paper exploits shared and individualized channels of cooperative rate splitting multiple access (RSMA) for semantic information assignment. Meanwhile, the appropriate relay is selected for network capacity enhancement based on semantic information assignment, energy consumption, and channel status. Then, semantic information assignment, relay selection, time resource allocation, and rate splitting are jointly optimized to minimize energy consumption. The formulated problem is an intractable mixed-integer non-linear programming problem, which can be resolved with the Dinkelbach method and successive convex approximation technique. A customized algorithm, namely SRTR, is proposed for green cooperative RSMA networks. Simulation results reveal that the SRTR algorithm can increase network capacity and flexibly allocate semantic data, resulting in a 21% reduction in energy consumption compared with traditional cooperative RSMA.

Spatial-temporal beam spoofing (STBS) poses a severe security threat to integrated sensing and communication (ISAC) systems by deliberately manipulating signal properties to fabricate deceptive target echoes, thereby undermining the sensing accuracy and evading the current security measures through the spatial masking and asynchronous injection. To combat this intelligent attack in ISAC, we proposes a beam consistency anomaly detection (BCAD) method, which establishes a physics-constrained verification procedure based on inherent propagation properties of legitimate signals. The proposed BCAD method systematically incorporates essential signal consistency requirements, such as array steering vector coherence, Doppler shift linearity, and phase progression consistency, into multivariate polynomial formulations. It then utilizes sum-of-squares relaxation to rigorously verify the global non-negativity of these polynomials across the entire parameter space encompassing angle-of-arrival, delay, and Doppler shift. This verification process confirms the physical legitimacy of the signal, and a negative result reveals violations of the transmission continuity constraint caused by STBS. Numeric results are presented to show the detection performance of the proposed BCAD method.

This paper addresses the challenges of automatic monitoring and restoration in ancient mural conservation, aiming to enhance the efficiency and quality of heritage preservation. Traditional manual inspection is time-consuming and often misses early damage, while existing digital restoration models struggle with consistent restoration, especially for large-scale damage. To address these issues, we propose an Internet of things (IoT)-based solution combining event-driven edge intelligence and artificial intelligence generated content (AIGC) techniques. A fine-tuned EdgeSAM model, using a Conv-adapter, enables efficient damage segmentation at the edge; an event-driven mechanism reduces resource consumption; and a LoRA-tuned PowerPaint model, aided by Blip2 and Qwen, provides effective restoration of large damaged areas. Cloud-side processing utilizes AIGC techniques to restore damaged mural areas, ensuring high-quality restoration while minimizing communication demands. Experimental results demonstrate that the proposed method achieves accurate damage monitoring on resource-constrained edge devices and generates diverse, contextually appropriate restoration results on cloud servers, providing a deployment-oriented feasibility validation under simulated temporal degradation and real hardware constraints.

Perceiving scene depth and 3D structure is fundamental for environmental comprehension and interaction in Internet of Video Things (IoVT) devices. Self-supervised monocular depth estimation, which leverages photometric consistency across sequential video frames without requiring ground-truth labels from active sensors, has emerged as a compelling paradigm. Nevertheless, this paradigm suffers from inherent limitations in low-texture or occluded regions, where photometric supervision becomes ambiguous or invalid, typically leading to structural degradation and indistinct object boundaries when inferring depth. To mitigate this limitation, we propose a dual-branch local distillation framework that harnesses priors from depth foundation models (DFMs) to alleviate depth ambiguity and improve fine-grained estimation accuracy. Specifically, guided by a frozen DFM, the framework synergistically employs local-context and cross-context supervision to optimize a student network, facilitating robust perception of depth discontinuities and precise boundary modeling. Furthermore, to enhance the spatial representation within a lightweight architecture, we design DE-LiteMono as the student model, which recovers geometric details through a detail enhancement block and fusion modules. Moreover, a spatial distance consistency loss is introduced to explicitly model the relative geometric topology in the image plane, providing robust structural guidance. Extensive experiments on standard benchmarks, including KITTI, Cityscapes, and Make3D, demonstrate that the proposed method outperforms state-of-the-art self-supervised methods, achieving sharper depth boundaries, reduced ambiguity, and superior quantitative performance.

Industrial IoVT (Internet of Video Things) still faces the dual bottleneck of insufficient accuracy and poor real-time performance in circuit board tiny defect detection. To this end, we propose RGM-YOLO (RefConv–GhostNet–CBAM-enhanced YOLOv8 ), which introduces deformable convolution and channel attention via RefConv and GhostNet modules, and experimentally validates it on the BDL-PCB (Bare Die on Laminate–Printed Circuit Board) large-scale dataset. Experimental results show that RGM-YOLO achieves 94.2% in mAP50 and 67.3% in mAP90–95, representing improvements of 2.4% and 11.2% over the baseline model, YOLOv8. The number of parameters and GFLOPs is reduced by 4.2M and 2.5G, respectively, while the FPS increases from 78 to 102. This approach offers a high-precision, low-latency defect detection paradigm for edge IoVT devices targeting small defects and can be generalized to other industrial quality-inspection scenarios.

Federated Learning (FL) has emerged as a promising paradigm for decentralized machine learning, where a central server coordinates distributed clients to collaboratively train a global model without direct access to raw data. Despite its advantages, heterogeneous and long-tail data distributions across clients remain a major bottleneck, particularly in IoT scenarios with diverse devices and sensing modalities. To address these challenges, we propose FedSM, a novel framework that integrates multimodal semantic knowledge with balanced pseudo features to enhance global model optimization. Unlike conventional approaches that rely on single-modal information, FedSM leverages CLIP’s cross-modal representations and open-vocabulary priors to guide semantic-aware data augmentation. A probabilistic selection mechanism further refines local features by mixing them with global prototypes, ensuring pseudo features are semantically reliable and reducing bias caused by skewed client distributions. Almost all computations are performed locally at the client side, thereby alleviating server overhead and improving scalability in resource-constrained IoT environments. Extensive experiments on long-tail benchmarks including CIFAR-10-LT, CIFAR-100-LT, and ImageNet-LT demonstrate the superiority of FedSM over state-of-the-art baselines, highlighting its potential for robust communication-efficient FL in IoT networks.

To cope with the challenges of the rapid growth of Industrial Internet of Things devices, deploying cache servers (CS) at the edge of the network becomes a promising solution. The cache node (CN) can reduce request latency and the traffic load on backhaul link by pre-caching relevant data generated by sensors. However, the storage resources of CSs are limited, and select the appropriate data item to cache is a critical issue for improving efficiency. In addition, we introduce the Age of Information (AoI) to describe the freshness of cached data. However, increasing the freshness of data through frequent caching updates could result in increased energy consumption of sensor. In this paper, we study the caching problem of multiple CNs, and further model the problem as a multi-agent Markov Decision Process to minimize long-term request latency, AoI, and energy consumption. Furthermore, to solve this problem, we propose a variant of the Soft Actor-Critic-based multi-agent caching algorithm. Finally, experiments show that the proposed algorithm can converge to a better caching strategy and has better performance in multiple objectives than existing algorithms.

Zero-shot temporal action localization (ZSTAL) aims to localize and recognize action categories unseen during training. However, it assumes that test videos contain only unseen classes, which is unrealistic in practice where seen and unseen actions naturally co-exist. To bridge this gap, we introduce generalized ZSTAL (GZS-TAL), where models trained only on seen classes must handle both seen and unseen ones during testing. This setting highlights a critical challenge: a static, frozen model cannot adapt to the mixed distributions encountered at test time. To address this issue, we propose a Temporal-Sensitive Adaptation (TSA) module that equips TAL models with the ability to update themselves during testing. The key intuition is to use temporal dependency prediction as a self-supervised signal: TSA introduces an online-updatable memory optimized to reconstruct features of preceding segments from the current one, thereby embedding temporal dependencies into parameters and reusing them for adaptation at test time. To further enhance temporal modeling, we extend TSA into a Bi-directional TSA (Bi-TSA) mechanism that performs prediction in both forward and backward directions. By simultaneously exploiting historical and future contexts, Bi-TSA improves long-range temporal representation and yields more accurate boundary localization. Extensive experiments on THUMOS14 and ActivityNet-1.3 demonstrate that our approach achieves significant improvements over state-of-the-art methods under the GZS-TAL setting, validating its effectiveness and generalization ability.

competitive swarm optimizer (CSO) is considered as a prominent paradigm for solving large-scale multiobjective optimization problems (LMOPs). However, the pairwise random competition (PRC) mechanism used in most existing CSOs may limit their performance in solving LMOPs due to the following reasons. First, when the winner particle obtained by PRC is of poor quality, it may limit the learning effect of its corresponding loser particle. Second, due to the stochastic nature of PRC, the evolutionary direction of the loser particles may be drastically perturbed over the iterations, thus slowing down their convergence speed. To alleviate the above issues, this article proposes a constrained learning (CL)-based CSO for tackling LMOPs, called CL-CSO. First, CL-CSO adopts a set of reference vectors to divide the original objective space into several subregions. Second, CL-CSO designs a CL-based strategy, including the intra-subregion learning and cross-subregion learning strategy, which let the loser particles only learn from the winner particles in their intra-subregions or neighboring subregions, respectively. Moreover, CL-CSO designs a Gaussian model assisted evolutionary strategy to help the evolution of winner particles, aiming to further improve the diversity and quality of winner particles. This way, the learning effect of particles and the overall convergence speed can be significantly enhanced. Compared to several competitive algorithms for tackling LMOPs, experimental results show that CL-CSO performs well in solving two well-known benchmark LMOPs (containing 2-3 objectives and 500-5000 decision variables), as well as real-world instance selection problems.

The widespread adoption of machine learning (ML) in privacy-sensitive domains such as healthcare and finance has amplified concerns surrounding data privacy, regulatory compliance, and generalization across data domains. Federated learning (FL) offers partial mitigation by enabling collaborative training without sharing raw data. However, current FL frameworks often fail to address key challenges, including vulnerabilities to semi-honest and colluding participants, inefficiencies in computation and communication for edge devices, and limited support for uncertainty-aware models like Gaussian Processes (GPs). This paper presentsF2GP, a secure federated framework for sparse GP approximation that addresses these gaps through two core innovations. First, a privacy-preserving support set selection algorithm based on one-shot federated$k$-means clustering improves model accuracy with minimal communication overhead. Second, a multi-party homomorphic encryption (HE) scheme secures the aggregation and inference process, ensuring robustness even when up to$M-1$participants collude with the server. We implement F2GP on a testbed of 15 NVIDIA Jetson Nano devices, emulating low-resource edge environments. The framework demonstrates practical scalability and achieves 15–20% better accuracy compared to non-secure distributed and centralized GP baselines, while maintaining sub-linear communication overhead. Evaluations across diverse datasets confirm F2GP's performance, resilient privacy, and suitability for uncertainty-aware inference. The code will be made available onhttps://gitee.com/SZU-AI4H/securedgp

Band selection (BS) is a key method in Hyperspectral image (HSI) classification that helps to reduce the computational burden and improve the class separability. However, with the emerging of unmanned aerial vehicle (UAV)-borne HSI datasets, their attributes such as high spatial and spectral resolution as well as large-scale samples pose serious challenges to the existing BS methods, making them inefficient. In addition, the efficient utilization of the prior knowledge from the data collected by fixed UAV-borne sensors in different regions is often easily overlooked. In view of these issues, this paper proposes a neural network-assisted particle swarm optimization (PSO) algorithm for cross-domain BS of UAV-borne HSIs. First, a knowledge learning strategy is designed for the source domain, which applies a neural network model to learn the useful prior knowledge in labeled source domain data. Then, a network-assisted PSO algorithm is introduced to search for the optimal subset of bands in the target domain under the guidance of the valid prior knowledge captured from the source domain by the network model. Moreover, a similarity-based grouping strategy is designed to group similar bands and then select bands from each group with the aims of reducing the redundant information in the subset of bands. Finally, experimental results on three common UAV-borne HSI datasets show that our proposed method can efficiently handle UAV-borne HSI data with large samples, as it is able to find a subset of bands with higher quality compared to several state-of-the-art BS methods.

In this paper, we explore the vulnerability of the physical uplink shared channel (PUSCH) to a new smart jamming attack in fifth generation (5G) new radio (NR), where an intelligent adversary first executes its attack by sniffing the downlink control information (DCI)-indicated resource scheduling information and then disrupts the PUSCH data transmission effectively and covertly by the precise jamming. To combat such kind of DCI sniffing based smart jamming (DCIS-SJ), we propose a novel method for effective DCIS-SJ suppression leveraging the DCI-scheduled subset identification and the PUSCH resource reconstruction. Our method fundamentally relies on the differences in the spatial domain feature under available control channel elements and resource block group granularities between legitimate users and the DCIS-SJ attacker, to selectively exclude unwanted elements while safeguarding the authenticity of the targeted transmissions. Numerical results evaluate and confirm the effectiveness of our method.

Large language models (LLMs) are increasingly deployed in edge computing environments to reduce latency and preserve privacy. However, their inference process presents fundamental challenges for resource-constrained IoT devices. LLM inference involves computationally asymmetric stages: parallelizable prompt processing and sequential token decoding. This asymmetry creates deployment bottlenecks where IoT devices lack capacity for prompt processing while edge nodes suffer from inefficient sequential decoding. This paper presentsE$^{2}$LLM, an efficient distributed inference framework for large language models in heterogeneous edge-IoT environments.E$^{2}$LLMleverages high-capacity edge devices for structural planning and introduces auxiliary lightweight models to generate segment-specific key-value (KV) caches. These minimal inference artifacts enable collaborative parallel decoding across IoT devices without requiring full model instantiation. The framework employs static-dynamic KV cache separation to minimize communication overhead while maintaining semantic coherence through structure-guided coordination. Extensive evaluation on realistic edge testbeds demonstrates significant performance improvements. Under diverse deployment settings,E$^{2}$LLMachieves 74%–87.7% end-to-end latency reduction compared with several state-of-the-art baselines, while maintaining comparable generation quality; meanwhile, it also delivers a 34.6%–72.2% reduction in communication overhead, improves 9-12 × in energy efficiency. The framework exhibits strong scalability under bandwidth-limited conditions, enabling efficient LLM deployment across heterogeneous edge-IoT environments.

Low Earth orbit (LEO) satellites can be used to assist maritime wireless communications for wide-area data transmission. However, the extensive coverage of LEO satellites, combined with the openness of channels, can cause the communication process to suffer from security risks. This paper presents a LEO satellite-maritime communication system assisted by low-altitude unmanned aerial vehicle (UAV) friendly-jamming to ensure data security at the physical layer. Since such a system requires balancing the conflicting performance metrics of secrecy rate and energy consumption of the UAV to meet evolving scenario demands, we formulate a secure satellite-maritime communication multi-objective optimization problem (SSMCMOP). In order to solve the dynamic and long-term optimization problem, we reformulate it into a Markov decision process. We then propose a transformer-enhanced soft actor-critic (TransSAC) algorithm, which is a generative artificial intelligence-enabled deep reinforcement learning approach to solve the reformulated problem, thus capturing strong temporal correlations and diversely exploring weights. Simulation results demonstrate that the TransSAC algorithm outperforms comparative approaches and algorithms, maximizing the secrecy rate while effectively minimizing the energy consumption of the UAV. Moreover, the results identify more suitable constraints for the system.

With the emergence of fluid antenna (FA) in wireless communications, the capability to dynamically adjust port positions offers substantial benefits in spatial diversity and spectrum efficiency, which are particularly valuable for mobile edge computing (MEC) systems. Therefore, we propose an FA-assisted MEC offloading framework to minimize system delay. This framework faces two severe challenges, which are the complexity of channel estimation due to dynamic port configuration and the inherent non-convexity of the joint optimization problem. Firstly, we propose Information Bottleneck Metric-enhanced Channel Compressed Sensing (IBM-CCS), which advances FA channel estimation by integrating information relevance into the sensing process and capturing key features of FA channels effectively. Secondly, to address the non-convex and high-dimensional optimization problem in FA-assisted MEC systems, which includes FA port selection, beamforming, power control, and resource allocation, we propose a game theory-assisted Hierarchical Twin-Dueling Multi-agent Algorithm (HiTDMA) based offloading scheme, where the hierarchical structure effectively decouples and coordinates the optimization tasks between the user side and the base station side. Crucially, the game theory effectively reduces the dimensionality of power control variables, allowing deep reinforcement learning (DRL) agents to achieve improved optimization efficiency. Numerical results confirm that the proposed scheme significantly reduces system delay and enhances offloading performance, outperforming benchmarks. Additionally, the IBM-CCS channel estimation demonstrates superior accuracy and robustness under varying port densities, contributing to efficient communication under imperfect CSI.

Deep neural network (DNN) model partitioning and pruning have proven to be effective methods for enhancing resource efficiency and reducing inference delay by strategically allocating DNN workloads across heterogeneous edge and cloud infrastructures. Nevertheless, the heterogeneous nature of resources complicates the deployment of DNN in mobile edge-cloud computing (MEC) networks. In this paper, we present an innovative framework for collaborative DNN inference in MEC networks by integrating fine-grained model partitioning and magnitude-based pruning. However, the joint model partitioning and pruning policy presents significant challenges due to the inherently coupled and mutually influential nature. To address it, we adopt Long Short-Term Memory (LSTM) networks as action generation controllers to generate discrete actions for model partitioning and pruning alternately. After that, we adopt the policy gradient algorithms to optimize the LSTM-generated actions with a moving average according to the Monte Carlo estimate. By directly optimizing the policy function, the proposed framework enhances the efficiency and stability of action space exploration, yielding faster convergence and improved inference performance. Experimental results on standard datasets indicate that the proposed framework outperforms state-of-the-art approaches, achieving an 8.247% increase in system reward and an average reduction of 27.313% in total delay within the considered MEC networks.

Edge Intelligence (EI) combines edge computing and artificial intelligence to deliver low-latency and resource-efficient services. Integrated Sensing and Communication (ISAC) further empowers EI by enhancing edge perception and accelerating intelligent model training. However, integrating ISAC into EI complicates the coordination of dynamically varying sensing, communication, and computation resources, especially under device mobility and unpredictable network conditions, leading to degraded service performance. To address these coordination challenges and sustain high-quality service under mobility and dynamics, we aim to design an adaptive service provision framework that tightly couples real-time perception with intelligent decision-making at the edge. Specifically, we propose an adaptive service provision architecture for ISAC-assisted EI, where Digital Twins (DTs) hosted on edge servers represent edge devices and their contexts to enable accurate perception and intelligent decision-making, thereby enhancing the efficiency of ISAC-enabled services. By dynamically migrating DTs across edge servers based on device mobility and resource availability, the system supports continuous decision-making and seamless service delivery. We further integrate convex optimization for efficient multi-resource coordination and a Time-Varying Contextual Bandit (TVCB) algorithm to enable adaptive, context-aware DT migration in dynamic environments. Extensive simulations demonstrate that our approach significantly improves service quality, reliability, and adaptability in ISAC-assisted EI systems, reducing migration oscillations and overhead while achieving lower latency and higher utility compared with representative baselines.

With the rapid development of 6G and Internet of Vehicles (IoV) technologies, the volume of computation-intensive tasks generated by intelligent vehicles is growing exponentially. Given limited onboard processing capabilities, vehicles increasingly rely on edge servers deployed by service providers (SPs) at roadside units to offload tasks. Vehicle clients can offload the tasks to SPs to mitigate their onboard computation load, while SPs derive economic benefits through the provision of computation resources. However, this interaction introduces a conflict of interest, as vehicles aim to minimize their offloading costs, while SPs seek to maximize revenue. To address this problem, we propose SPOR, a Stackelberg game-based service priority-aware computation offloading and resource pricing scheme in IoV. SPOR is a hierarchical game-theoretic framework in which SPs act as leaders setting prices, while vehicles act as followers determining their offloading strategies. A novel service prioritization function is introduced, incorporating booking price, system load, and reputation to ensure fair and balanced resource allocation. We provide a theoretical proof of the existence and uniqueness of a Nash equilibrium. Extensive experiments on a real-world vehicle edge computing dataset show that SPOR outperforms baseline methods in delay, energy consumption, average load, and task completion rate. Notably, SPOR maintains task completion rates above 97% even under heavy workloads, demonstrating its effectiveness in enhancing system reliability and overall performance.

Federated learning (FL) that preserves privacy has appeared as a prospective paradigm in mobile edge computing networks. However, due to the system and data heterogeneity of mobile clients (MCs), group-based FL with a sampling mechanism is crucial for minimizing model training costs. To address these challenges, we investigate and formulate the problem of group-based FL with a sampling mechanism for reducing model training cost (i.e., latency and energy consumption), and propose a group-based FL with a cost-efficient sampling mechanism (GFLCSM) framework to address it. More precisely, before training, each MC locally pre-trains a model, estimates its data distribution from the classifier's gradient norms, and uploads it to the central server (CS) instead of raw data to preserve privacy. Using this information, the CS transforms vanilla FL into a group-based FL. During training, GFLCSM replaces the random sampling mechanism with a cost-efficient one. Moreover, to enhance robustness against network dynamics, we extend GFLCSM with a backup resampling mechanism, termed GFLCSM-E. Experimental results indicate that GFLCSM surpasses the baseline frameworks, reducing latency by 24.63% and energy consumption by 11.47% on average across two datasets, while GFLCSM-E maintains high performance even under client dropout. The source code address ishttps://github.com/kt4ngw/GFLCSM.

Recently, edge computing has emerged as a prevailing paradigm in applying deep learning-based object detection models, offering a promising solution for time-sensitive tasks. However, existing edge object detection faces several challenges: 1) These methods struggle to balance detection precision and model lightweightness. 2) Existing generalized edge-deployment designs offer limited adaptability for object detection. 3) Current works lack real-world evaluation and validation. To address these challenges, we propose theEdgeDetectionToolbox(ED-TOOLBOX), which leverages generalizable plug-and-play components to enable edge-site adaptation of object detection models. Specifically, we propose a lightweightReparameterized Dynamic Convolutional Network(Rep-DConvNet) that employs a weighted multi-shape convolutional branch structure to enhance detection performance. Furthermore, ED-TOOLBOX includes aSparse Cross-Attention(SC-A) network that adopts a localized-mapping-assisted self-attention mechanism to facilitate a well-craftedJoint Modulein adaptively transferring features for further performance improvement. Moreover, we propose anEfficient Headfor the classification and location modules to achieve more efficient prediction. Additionally, in practical industrial scenarios, we identify that helmet detection-one of the most representative edge object detection tasks-overlooks band fastening, which introduces potential safety hazards. To address this, we build aHelmet Band Detection Dataset(HBDD) and apply an edge object detection model optimized by the ED-TOOLBOX to tackle this real-world task. Extensive experiments validate the effectiveness of components in ED-TOOLBOX. In visual surveillance simulations, ED-TOOLBOX-assisted edge detection models outperform sixstate-of-the-artmethods, enabling real-time and accurate detection. These results demonstrate that our approach offers a superior solution for edge object detection.

Deploying federated learning (FL) in mobile edge computing (MEC) networks has become a prevalent approach to distributed learning. However, the inherent heterogeneity in computing, transmission and data on edge devices (EDs) brings challenges in improving training efficiency and speed. Existing approaches primarily focus on increasing batch sizes or employing adaptive batching to expedite convergence, but often overlook the generalization ability of the model. In this paper, we propose an energy-efficient adaptive batching approach for FL in MEC networks, aiming at minimizing the energy consumption by balancing training efficiency and speed. Initially, we exploit the relationship between batch size and loss improvement while determining the optimal learning rate corresponding to the batch size and understanding the correlation among loss improvement, learning rate, and gradient noise scale (GNS). Then we dynamically adjust the batch size based on the GNS and propose a low-complexity approach for measuring GNS. Finally, we fine-tune the batch size by assessing gradient similarity on each ED to ensure an optimal level of gradient noise during training, thereby enhancing the model's generalization. Experiment results demonstrate the effectiveness of our approach with an approximate 50% and 20% reduction in energy consumption and time consumption compared with existing approaches.

Depression significantly impacts mental health, severely disrupting patients' daily lives. During depressive episodes, individuals may experience symptoms such as excessive guilt, self-harm, and suicidal ideation. Compared to proprietary devices like brain electrode caps, wearable technologies for depression detection have gained attention due to their affordability and portability—enabling real-time monitoring of depressive states. However, challenges such as low-quality data from ubiquitous devices, individual variability, and the complexity of multimodal physiological signal analysis limit model generalizability. To address these issues, we present DepGuard, a novel ubiquitous wearable system for depression assessment based on multimodal physiological signals. DepGuard performs a two-stage detection process: depression recognition and real-time episode monitoring. For depression recognition, we propose an unsupervised domain adaptation method to reduce the domain gap between source and target subjects. For episode monitoring, we employ a few-shot learning strategy to enable personalized modeling. Both approaches enhance cross-subject generalization. Our system achieves 90.75% accuracy in cross-subject depression recognition using 30 unlabeled samples per target subject, and 93.52% accuracy in episode monitoring using 15 labeled samples per class.

The rapid development of the low-altitude economy (LAE) has significantly enhanced the service diversity of the Internet of Things (IoT) networks, necessitating efficient coordination among the unmanned aerial vehicles (UAVs). In this work, we utilize multiple UAVs to provide both wireless data collection (WDC) service and wireless energy transfer (WET) service, and divide the IoT devices into the I-devices that only need the WDC service and the E-devices that only need the WET service, respectively, from the multiple UAVs. Due to their conflicting service demands on the UAVs with limited resources, we formulate the bi-objective optimization problem (BOOP) to minimize the age of information (AoI) for the I-devices and the hungry-level of energy (HoE) for the E-devices at the same time, by jointly optimizing all the UAVs' trajectories and WET decisions over time slots and their WDC decisions over sub-slots. To efficiently solve the complex BOOP, we innovatively transform it into a single-objective optimization problem (SOOP), in which the two conflicting objectives are scalarized via a self-adaptive objective weight. Unlike the conventional approach reliant on fixed and pre-defined objective weights, we optimize the objective weight jointly with other decision variables, enabling automatic adaptation to various network environments without human intervention. However, the proposed SOOP is NP-hard with a large number of decision variables. Accordingly, we propose a new Multi-Agent Adaptive and Hierarchical Deep Reinforcement Learning (MA$^{2}$HDRL) framework, which leverages a central controller (CC) to guide the local training of multiple individual UAV agents. In this framework, each UAV agent employs a two-tier hierarchical DRL model: tier-1 optimizes the trajectory and WET policies over the time slots, while tier-2 optimizes the WDC policy across the sub-slots. Meanwhile, the CC trains the global reward preference for all the UAV agents over the training episodes, to adaptively balance the WDC and WET service demands. Finally, extensive simulation results are conducted to demonstrate the outstanding performance of the proposed MA$^{2}$HDRL approach as compared to state-of-the-art benchmarks.

Heart rate (HR) and respiratory rate (RR) are essential physiological indicators of people's physical function and exercise performance. Advancement in sensor technology has rendered earable devices with in-ear microphones feasible for vital sign monitoring. However, it is rather challenging to monitor heart rate and respiration simultaneously with a single earable device especially when a person is doing exercises. This is because intense physical activities can lead to significant noise interference which can easily obscure physiological signals. To address this challenge, this paper presents VitalEar, an exercise physiological monitoring system based on in-ear microphones, designed to estimate HR and RR while addressing complex motion interference and variability in users and activities. VitalEar employs Empirical Wavelet Transform (EWT) to decompose heartbeats into periodic and harmonic coefficients, enhancing noise reduction in the ECG spectrogram reconstruction model. Additionally, VitalEar incorporates a DCN-LSTM-based breathing curve reconstruction model to mitigate background noise and variability in user and activity. The experiments show that VitalEar achieves an average MAE of 5.61 BPM and 2.31 RPM, MAPE of 4.16% and 10.58% for HR and RR estimation, respectively. Compared to related work, our approach offers significant advantages in robustness against intense physical activities

Stereo image Super-Resolution (SR) aims to enhance image resolution by leveraging complementary information in stereo pairs. Convolutional Neural Networks (CNNs), widely used in stereo image SR for their strong local pattern extraction capabilities, often fail to capture long-range dependencies critical for stereo correspondence. On the other hand, Swin Transformers have demonstrated superior performance in modeling long-range dependencies for stereo image SR tasks. However, their computational complexity scales quadratically with the window size, leading to a trade-off between global receptive fields and computational efficiency. To tackle these challenges, we propose StereoMamba+, a novel stereo image SR method designed to adaptively capture both local and global dependencies in stereo pairs. Leveraging the Mamba architecture as its backbone, StereoMamba+ integrates an Adaptive State Space Module (ASSM) that efficiently extracts and fuses global and local features, maintaining linear computational complexity. Additionally, a Gated Enhanced Feed-Forward Network (GEFN) selectively amplifies essential features and depth cues, and a Residual Frequency Block (RFB) is employed to capture global features in the frequency domain. To further enhance stereo correspondence, we introduce a Stereo Bi-Directional Cross Attention Module (SBCAM), aligning unique features along both horizontal and vertical epipolar lines to improve stereo consistency. Extensive experiments demonstrate that our proposed StereoMamba+ method achieves state-of-the-art performance on 2× and 4× stereo image SR tasks, delivering PSNR improvements of up to 0.45dB, while maintaining competitive parameter efficiency compared to existing methods.

Edge Networks (ENs) are emerging networks that enable deploying multiple virtual network functions (VNFs) on resource-limited edge servers to provide users with tailored virtual network services. Decomposing a single VNF into multiple thinner replicas can enhance service reliability while inevitably incurring additional computing capacity consumption (e.g., operating system overhead caused by instantiating more replicas), which increases with the number of decomposed replicas. Moreover, redundant backup replicas can be deployed near the replicas to enhance the reliability further. However, the stateful nature of VNFs requires state synchronization among replicas and between replicas and backup replicas, resulting in additional communication traffic. In this paper, we consider a joint strategy for the decomposition and deployment of stateful VNFs with the goal of minimizing total cost while meeting users’ reliability requirements. The total cost includes the computing cost for instantiating replicas and backup replicas, the additional consumption of computing capacity due to VNF decomposition, and the communication cost for routing traffic among users, replicas, and backup replicas. We first formulate the cost minimization problem as an integer nonlinear program and prove that it is NP-hard. Then, we propose an online two-stage scheme to solve this problem, where the first stage is a VNF decomposition algorithm, and the second stage is a deployment algorithm based on deep reinforcement learning (DRL). The former effectively reduces computing cost by iteratively adjusting the number of replicas and backup replicas, while aiding the latter to adaptively minimize communication cost. Extensive experiments demonstrate that our scheme is promising compared to existing state-of-the-art methods.

Emotion recognition is a crucial part of cognitive computing. Traditional emotion recognition systems include audio-visual modality. However, a recent trend in recognizing emotions is to use physiological signals such as the Electroencephalogram (EEG). EEG signals, together with audio-visual and other physiological signals, improve the performance of emotion recognition systems. This article presents a systematic literature review on EEG-based multimodal (multimedia) emotion recognition systems for the last 5 years. Three major research questions are addressed: (1) What kind of learning models are used in EEG-based multimedia emotion recognition? (2) What are the publicly available related datasets? (3) What are the challenges and future directions of this topic? The answers to the research questions are provided in different subsections.

Intelligent adaptive bitrate (ABR) schemes have been widely recognized for their excellent learning strategies. However, existing intelligent ABR methods have limitations, i.e., the lack of logical reasoning capability for video-aware symbolic representations leads to low sampling efficiency and fails to achieve the optimal performance of Bitrate Adaptation. We introduce NeuroBA, a learning-based approach to realize ABR using neuro-symbolic deep reinforcement learning. NeuroBA trains a neuro-symbolic deep network model without making any assumptions about the edge video scene and without relying on a predefined model. Instead, it enables bitrate decision-making under uncertainty and partial observability by knowledge-driven video quality perception in symbolic first-order logic. To enhance wireless signals, we have introduced Intelligent Reflecting Surface (IRS) technology to address this issue. By dynamically adjusting the phase shift of IRS, the throughput performance of wireless networks is significantly improved. Based on trace-driven and real-world experiments covering a variety of edge video scenarios, and network performance metrics, NeuroBA is compared with state-of-the-art ABR schemes, and NeuroBA exhibits superior performance, with an average QoE improvement of 16.58% (BOLA)-25.34% (Fugu). In particular, it outperforms existing baseline approaches even without pre-programmed models and network scenarios assumed for the edge network.

The Mobile Edge Computing (MEC)-Empowered Internet of Vehicles (IoVs), a transformative paradigm characterized by real-time decision-making and distributed processing via data offloading to the network edge, has garnered substantial research interest. Nonetheless, emerging applications such as autonomous driving pose dual challenges of computational bottle necks and inadequate wide-area coverage in resource scheduling. To this end, we propose a Digital Twin (DT)-enhanced, satellite assisted resource allocation framework that synergistically coordinates MEC and satellite networks while leveraging DTs for network virtualization and collaborative training, thereby fully exploiting the low-latency capabilities of edge computing, the high-capacity processing of satellite computing, and the cost efficient simulation advantages of DT technology. During the training phase, we develop DR4SV, a Deep Reinforcement Learning (DRL)-based online optimization method that constructs specialized intelligent agents tailored for satellite-collaborative IoV scenarios. By incorporating depthwise over-parameterized convolutional layers, DR4SV enables multi-channel synergistic processing across heterogeneous communication channels while establishing robust policy alignment between physical agents and their DT counterparts. This architecture facilitates real-time state mapping and multi-dimensional parallel simulation within the digital space, enhancing resource allocation efficiency while dynamically balancing latency and energy consumption with accelerated convergence. Extensive experiments are conducted based on real-world datasets, encompassing hyperparameter con figurations and rigorous performance evaluations. The numerical results demonstrate that DR4SV achieves reductions in both time and energy consumption, with optimization rates reaching up to 6.8% and 19.1%, respectively. Meanwhile, the correlation between DTs and physical entities reaches up to 97%, thereby validating the effectiveness and feasibility of DT technology in satellite-terrestrial integrated vehicular networks.

With the rapid deployment of large language model (LLM) technology across various fields, numerous LLMs have been deployed on edge servers (ESs) to provide low-latency generative services for edge devices. However, as factual knowledge evolves, the massive number of parameters in LLMs poses significant challenges for updating LLMs on ESs. Existing studies employ federated fine-tuning to update LLMs, but these unconstrained updating approaches can lead to overfitting and knowledge forgetting, while also resulting in substantial overhead. Knowledge editing (KE), as a promising technology, ensures the injection of new knowledge while preserving existing knowledge by editing specific parameters. In this paper, we propose multi-ES collaborative KE for the first time and design the CoKE and pCoKE frameworks in edge-cloud scenarios. These frameworks enhance editing efficiency by extracting identical expressions of the same knowledge across different LLM parameters for collaborative editing across multiple ESs. Additionally, we incorporate a personalized selection module in pCoKE to provide domain-specific generative services on ESs. To further reduce editing latency, we design a binary search-based resource allocation algorithm to balance editing latency across ESs. Extensive experiments demonstrate that CoKE and pCoKE reduce editing latency by 73% while maintaining high editing quality. Moreover, pCoKE achieves an approximately 6% improvement in editing quality.

Cell-free (CF) massive multiple-input multiple-output (MIMO) has emerged as a promising technique to deliver uniform signal coverage and high data rates. However, employing low-precision hardware in user equipment introduces susceptibility to hardware impairments (HI), resulting in significantly degraded channel state information (CSI) accuracy. Fortunately, rate-splitting multiple access (RSMA) has been proposed as a robust solution to mitigate the adverse effects of imperfect CSI by performing message splitting at the transmitter and successive interference cancellation (SIC) at the receiver. In this paper, we incorporate RSMA into CF massive MIMO systems to tackle the problem posed by imperfect CSI. Taking into account inevitable pilot contamination, we first derive a novel and closed-form expression for the spectral efficiency (SE) to analytically characterize the performance of RSMA-enabled CF massive MIMO systems under spatially correlated Rician fading channels. Subsequently, we focus on optimizing the decoding order, power allocation, and fronthaul weights to maximize the system’s sum SE. To address this mixed-integer nonlinear programming (MINLP) problem, we initially propose an alternating optimization (AO)-based optimization method that decomposes the original intractable problem into three manageable subproblems, which are iteratively handled until convergence. Considering the significant computational complexity associated with the AO-based approach, we further propose a proximal policy optimization (PPO)-based method to establish an effective and low-complexity optimization framework. Simulation results unveil the detrimental impact of HI on both CSI accuracy and the overall sum SE performance. In particular, the presence of HI introduces residual interference that limits the performance gains achievable through additional RSMA layers, especially in strong line-of-sight scenarios, highlighting the trade-off between these gains and the SIC-related costs in terms of computational complexity and decoding latency.

To address the challenges of information leakage, low energy efficiency, and the Doppler effect in mobile Internet of Vehicles (IoV), this paper proposes an enhanced IoV cooperation framework, where privacy information is forwarded by the untrusted relay assisted by unmanned aerial vehicle (UAV) and reconfigurable intelligent surface (RIS), which can improve security and energy efficiency. To meet the requirements of green communication, we formulate a secrecy energy efficiency maximization problem by jointly optimizing the transmit power allocation, the relay’s amplification factor, the two-hop RIS phase shift matrices, and the UAV trajectory. Given the non-convex nature of this problem, we introduce an iterative algorithm based on the convex-concave procedure and Dinkelbach’s method to optimize the transmit power and amplification factor. Additionally, we conceive the majorization-minimization (MM) algorithm to optimize the two-hop RIS phase shift matrices, and a designed firefly algorithm-deep deterministic policy gradient (FA-DDPG) algorithm is proposed to obtain the UAV trajectory. Simulation results demonstrate the effectiveness of the proposed scheme in enhancing secrecy energy efficiency. Specifically, compared to the DDPG-only and FA-based schemes, the proposed scheme achieves an improvement of 33.3% and 64.2%, respectively, in secrecy energy efficiency.

Reconfigurable intelligent surface (RIS)-enabled integrated sensing and communication (ISAC) is emerging as a key 6G technology for improving spectral efficiency and enabling high-resolution sensing. However,sensing targets within the communication coverage may act as potential eavesdroppers and intercept confidential data. To address this challenge, this paper proposes a sensing-assisted secure beamforming framework to enhance physical-layer security (PLS). First, we design a closed-loop architecture that sequentially performs RIS cascaded CSI estimation, target direction-of-arrival (DoA) estimation, and a Cramér–Rao bound (CRB)-based sensing accuracy evaluation. We then introduce an angular-domain information leakage (ADIL) metric to characterize leakage within the target’s angular uncertainty region. Building on this metric, we formulate a weighted-sum utility to jointly optimize the communication rate and sensing CRB under an ADIL-suppression constraint. To solve the resulting non-convex problem, we develop a penalty dual decomposition (PDD)-augmented alternating optimization (AO) algorithm that iteratively updates the BS beamforming, RIS phase shifts, and sensing time allocation. Convergence and complexity analyses further demonstrate that PDD accelerates AO convergence and mitigates zig-zag updates caused by coupled variables. Simulation results verify that the proposed sensing-assisted secure beamforming scheme effectively suppresses ADIL at eavesdropper angles and enhances PLS. Moreover, the PDD-augmented AO achieves up to a 21.3% improvement in communication rate and a 5.2% reduction in CRB compared with conventional schemes.

Traditional centralized model training assumes that data samples are readily available and can be processed without constraints. In contrast, decentralized machine learning (DML) addresses the limitation by collaborative model training and inference directly on distributed data sources. The transformation from data centralization to decentralization helps comply with data regulations and improves system scalability with reduced reliance on cloud servers. However, a tradeoff between model personalization and generalization exists: the fine-tuning of local training data distribution sacrifices model generalization on the testing data distribution that differs from the training data distribution. To improve the tradeoff, we propose a DML framework that can inherently make model personalization and generalization easier by selecting a model among multiple ones judiciously. We develop a scalable selector for model selection and use blockchain to achieve model consensus. The personalized model selector is then proposed for test-time adaptation. Using computer simulations, we show that our method not only outperforms competitive personalization benchmarks but also generalizes well for new data distributions with various shifts.

Accurate and timely 90-day survival prediction for critically ill COVID-19 patients is vital to optimize scarce ICU resources, yet single-source models often miss important pathophysiological cues. Emerging studies show that combining complementary modalities can reveal richer prognostic signatures than any modality in isolation. Motivated by this, we present DQU-CLIP, an advanced multimodal deep learning framework designed to overcome this limitation. Utilizing the CoCross dataset (comprising 171 ICU patients), our model integrates chest Xrays (CXRs) via a pre-trained Contrastive Language-Image Pretraining (CLIP) encoder with key clinical features, including Age, Charlson Comorbidity Index (CCI), APACHE II, and SOFA scores, processed by a neural network. DQU-CLIP achieves a robust ROC-AUC of 0.85, significantly outperforming unimodal baselines (CXR-only: 0.78, Clinical-only: 0.72) and competing multimodal approaches. Extensive validation and ablation studies confirm the synergistic benefit of this fusion. Furthermore, interpretability analysis using Grad-CAM identified relevant lung regions in CXRs, while feature importance pinpointed SOFA and APACHE II scores as critical indicators of disease severity. By effectively unifying radiological and clinical evidence, DQU-CLIP provides a more reliable prognostic assessment.

Federated learning (FL) enables model training on mobile clients (M Cs) while protecting data privacy by keeping the data local. However, the data and system heterogeneity among MCs can significantly undermine model performance, slow convergence, and increase energy consumption. To achieve green and efficient edge intelligence, we propose an energy consumption optimization problem under the FL framework for mobile edge computing networks in this paper. Our goal is to reduce the energy consumption of MCs and improve the FL model performance. Then we design a heterogeneity-aware client selection and gradient optimization (HCSGO) algorithm. Specifically, HCSGO selects MCs based on data, computation, and communication quality to mitigate the impact of heterogene-ity on model performance, while leveraging a residual gradient mechanism to optimize gradient aggregation and accelerate convergence. Experiment results demonstrate that the proposed algorithm achieves the lowest energy consumption and improves the model performance compared to the baselines.

Mobile edge computing (MEC) has gained significant attention for enhancing computational capacity and resource efficiency in wireless networks, particularly in Internet of Things (IoT) ecosystem where massive device connectivity is critical. However, the limited computational and energy resources of mobile users, such as IoT sensors and actuators, remain key barriers to further improving system performance. To address this, we propose an energy harvesting MEC system integrated with reconfigurable intelligent surfaces (RIS), which optimizes phase shifts and enhances channel state information to improve channel quality and enable efficient task offloading to edge servers for real-time IoT data processing. This study introduces an integrated deep reinforcement learning-based optimization (IDBO) framework to maximize the system computation rate. By decomposing the joint optimization problem into two modules — RIS phase shift configuration and task offloading strategy, and incorporating a unified reward mechanism, the framework achieves collaborative optimization between signal control and task allocation. Simulation results present that the proposed IDBO algorithm improves the system computation rate by 8% compared to baseline methods, demonstrating superior global optimization capabilities and strong generalization performance across diverse IoT network scenarios.

As factories in the Industrial Internet of Things (IIoT) scale up and complexity increases, distributed Large Language Models (LLMs) enabled Digital Twin Network (DTN) is required to enhance real-time mapping capabilities. However, current wired communication processes in distributed LLMs fine-tuning cannot meet the demands of mobile IIoT scenarios. Confronting this thorny problem, we propose a wireless communication strategy for gradient synchronization to enhance the efficiency of distributed LLM-enabled DTN fine-tuning. Specifically, leveraging mobile edge intelligence, we jointly optimize central node closeness centrality and computational capacity, thereby enhancing the efficiency of distributed LLM fine-tuning. Subsequently, we design the Dueling Double Deep Q-Network (D3QN) enabled parameter fine-tuning gradient synchronization (D3QN-REFRESH) algorithm and analyze its complexity. Extensive simulations using real factory data demonstrate the superior performance and generalization capabilities of D3QN-REFRESH.

Stereo image super-resolution (SR) aims to enhance image resolution by leveraging the complementary information from stereo image pairs. While convolutional neural network (CNN)-based methods have traditionally dominated this field, they struggle with capturing long-range dependencies. Transformer-based approaches have shown improvements by better modeling long-range dependencies, but their computational complexity scales quadratically with respect to the window length. To address these challenges, in this paper we propose StereoMamba, a new stereo image super-resolution method built on Structured State Space Models (SSMs). StereoMamba leverages the Mamba architecture to effectively capture long-range dependencies and inter-view correlations in stereo image pairs. Additionally, we introduce a Stereo Bi-directional Cross-Attention Module (SBCAM) to further improve stereo view correlation. Extensive experiments show that StereoMamba consistently surpasses state-of-the-art methods across several public datasets.

With the extraordinary success of generative artificial intelligence, large pretrained models (LPMs) have been widely used to achieve human-level performance. Despite the one-shot capability, it is always preferred to fine-tune the LPMs for domain-specific downstream tasks. Therefore, the federated learning system is leveraged to fine-tune the large pretrained models enabling concurrrently use multiple distributed clients as well as their local datasets. While the first-order fine-tuning methods suffer from high computational and memory costs due to the backward propagation, we are motivated to propose a federated zeroth-order fine-tuning method with only forward propagation. Moreover, we also leverage differential privacy to further preserve the data privacy of local clients. Experimental results illustrate that our proposed federated zeroth-order method can reduce the memory and retain a similar testing accuracy over the state-of-the-art benchmarks.

End-edge collaborative inference refers to the fact that edge servers (ESs) and end devices (EDs) jointly participate in inference tasks, which can not only reduce communication latency and bandwidth consumption with the cloud but also protect user data privacy. However, existing collaborative inference methods do not fully consider the limited resources of EDs and ignore the latency and accuracy requirements of different inference tasks. In this paper, we design a DNN inference acceleration framework to balance inference latency and accuracy. Specifically, we first use a compression method based on deep reinforcement learning to determine the compression ratio and deeply compress the original model to reduce the complexity of the model. To reduce the cumulative error caused by compression, a knowledge distillation-based scheme is used to fine-tune the compressed model. Finally, the DNN model is partitioned and deployed on the ED and ES, respectively. Extensive experiments demonstrate the effectiveness of the framework in achieving lowlatency DNN inference on demand.

This paper proposes a UAV-assisted forwarding system based on distributed beamforming to enhance age of information (AoI) in Internet of Things (IoT). Specifically, UAVs collect and relay data between sensor nodes (SNs) and the remote base station (BS). However, flight delays increase the AoI and degrade the network performance. To mitigate this, we adopt distributed beamforming to extend the communication range, reduce the flight frequency and ensure the continuous data relay and efficient energy utilization. Then, we formulate an optimization problem to minimize AoI and UAV energy consumption, by jointly optimizing the UAV trajectories and communication schedules. The problem is non-convex and with high dynamic, and thus we propose a deep reinforcement learning (DRL)-based algorithm to solve the problem, thereby enhancing the stability and accelerate convergence speed. Simulation results show that the proposed algorithm effectively addresses the problem and outperforms other benchmark algorithms.

In mobile edge computing (MEC) networks, federated learning (FL) has emerged as the leading distributed framework for training a shared machine learning model, primarily benefiting from its ability to exchange the information of edge devices (EDs) while safeguarding their privacy. However, in MEC networks, the heterogeneity of communication, computation, and data can result in challenges such as stragglers and data imbalances, thereby impeding the training process of FL. To address these challenges, we propose a Semi-Asynchronous Federated Learning (Semi-AFL) framework with cluster-based scheduling. In Semi-AFL, the EDs can perform local training at their own pace using different stale global models to tackle the straggler effect. Considering the asynchronousity of Semi-AFL and data heterogeneity, we propose a cluster-based scheduling strategy that includes device clustering and device selection. Specifically, it performs clustering based on the label distribution and obtains device-to-cluster information. We further select devices based on clustering information as well as model staleness and contribution, aiming to reduce variance and bias and accelerate model convergence. Experiment results demonstrate the effectiveness of the proposed method in reducing the latency of FL.

Web 4.0 is characterized by decentralized intelligence and blockchain integration, which introduces significant challenges in congestion management for software-defined networking (SDN). Traditional reinforcement learning (RL)-based approaches encounter inefficiencies due to limited adaptability to decentralized and delayed online learning capabilities. To address these issues, we propose an Active Inference-based Reinforcement Learning (AIRL) framework that integrates generative modelling with RL for enhanced decision-making in congestion control. By leveraging blockchain-enabled secure model trading and predictive intelligence, AIRL ensures adaptive policy optimization while maintaining transparency and trust in decentralized network environments. The proposed method demonstrates substantial improvements in delay reduction, packet loss, and efficient utilization of network resources under various dynamic scenarios.

In the paper, we consider the general semantic transmission in wireless networks based on probability distribution. Firstly, we extract a multidimensional semantic probability distribution function, independent of any a specific wireless channel model, by using the variational inference technique. Secondly, we propose a new semantic similarity metric for measuring the difference between the received semantics and the expected semantics based on Kullback-Leibler divergence. Then, we formulate the semantic transmission problem as an optimization problem of transmission symbol adjustment with the aim to maximize the semantic similarity. Finally, we develop an optimal semantic transformation and transmission (STT) algorithm to obtain the optimal transmission symbol adjustment decision. This decision makes the closed-form expression of semantic transmission symbol available, which can realize lossless semantic transmission with energy constraint. Simulation results verify the effectiveness and robustness of the proposed STT algorithm.

In Internet of things (IoT) systems enabled by 6G, unmanned aerial vehicles (UAVs), acting as communication nodes, have the advantages of flexible deployment and wide-area coverage. The channel prediction capability of UAVs for ground communication is of great significance for improving the reliability of IoT communication systems. We propose an innovative and interpretable paradigm for channel prediction based on “physical feature extraction + machine learning”. Specificallywe proposes a real-time UAV-to-ground channel prediction method that leverages propagation environment sensing data, aiming to enhance prediction accuracy and generalization by deeply integrating environmental and communication information. Firstly, we construct the first UAV sensing-communication integrated dataset featuring multi-band, multi-dimensional channel parameters, including UAV-to-ground RGB images, depth maps, and channel data. We then extract multimodal features with clear physical significance relevant to wireless propagation, such as relative position, relative altitude, relative volume, and transmitter-receiver distance. Finally, this paper designs a fusion architecture based on convolutional neural network (CNN) and multilayer perceptron (MLP). This architecture takes multimodal feature data as input, utilizes CNN to extract local features of multi-modal features, and models the fusion of multi-modal features through MLP. Experimental results demonstrate that our model consistently outperforms comparative model. Importantly, our feature analysis quantitatively reveals—for the first time—that building volume is the most influential factor in channel behavior, and that prediction accuracy degrades with increasing flight altitude. Furthermore, system-level simulations confirm that channel prediction leads to substantial improvements in network performance. This work presents a robust and interpretable framework for environment-aware channel characterization, laying a foundation for future 6G intelligent communication systems.

In the rapidly evolving field of autonomous driving, accurately detecting and understanding dynamic environments remains a challenge. Federated learning (FL) offers a promising approach by integrating decentralized models from multiple connected autonomous vehicles (CAVs) to enhance the performance of deep-learning (DL)-based object detection methods. However, traditional FL faces hurdles, such as extensive data synchronization requirements, limited data variance, and high communication costs. This article introduces a federated cooperative learning framework that addresses these challenges by combining data from both CAVs and roadside units. The framework combines local cooperative perception with global FL through a parameter-efficient FL adapter and a lazy communication strategy, improving DL-based object detection capabilities across diverse driving scenarios while significantly reducing bandwidth requirements. We also present a novel multiagent-multitown dataset Vehicle-to-Everything-Fed, specifically developed to validate the effectiveness of our approach under various conditions. Notably, our framework retains 97.51% of the detection accuracy achieved by full-model FL, while utilizing only 1.4% of the bandwidth typically required, demonstrating substantial improvements over conventional FL strategies. This study underscores the potential of our tailored approach to substantially enhance autonomous vehicle technologies with minimal resource utilization.

Split learning (SL) is widely regarded as a promising distributed machine learning framework with superior privacy-preserving properties, lower communication and computation costs. However, in real Internet of Things (IoT) scenarios, existing SL may not perform well because the local data of IoT devices often do not follow the same distribution. This leads to the model continuously adapting to the current data distribution in each training epoch, resulting in a catastrophic forgetting phenomenon. Existing methods typically attempt to add raw or generated data from previous devices in the current training epoch to review knowledge, but direct access to the local data of other devices carries serious privacy risks. Data augmentation techniques based on generative networks often have poor robustness and increase the computation cost on the device side. To address these challenges, we propose a new SL framework called SL without Forgetting (SLwF). To mitigate catastrophic forgetting without accessing any previous data, we propose a contrastive learning-based training method that leverages current training data to review previous knowledge, and learn new knowledge better. Furthermore, we adopt an exponential moving average (EMA)-based model update strategy to preserve lost knowledge, further alleviating the forgetting problem. We implement the SLwF framework in real IoT scenarios and extensively evaluated its performance using four publicly available datasets. Compared to other related research (e.g., IoTSL), SLwF performs better in terms of final accuracy and robustness while avoiding excessive device energy consumption.

Task migration and resource allocation are essential to integrate available resources for improving the efficiency of mobile-edge computing to support various computation-intensive and delay-sensitive Internet of Things applications, which cooperative optimization has yet been well addressed to achieve desirable performance. In this article, a deep reinforcement learning (DRL)-based adaptive cooperative optimization strategy is presented to fill this gap. Task migration and resource allocation are jointly employed to adaptively integrate available resources within cooperative edge nodes for processing various randomly offloaded tasks. The policy optimization to minimize the system cost and task dropout rates is formulated as Markov decision processes. A DRL algorithm that enhances deep deterministic policy gradient with a dual experience pool is proposed to jointly optimize the task migration and resource allocation in unknown stochastic application environments. Simulation experiments have been conducted to evaluate the performance of the presented strategy, and the results illustrate that it increases system rewards by 17.9%–61.5% and reduces task dropout rate by 5.2%–31.3% comparing with benchmarks.

Autonomous aerial vehicles (AAVs) have gained considerable attention as a platform for establishing aerial wireless networks and communications. However, the Line of Sight (LoS) dominance in air-to-ground (A2G) communications often leads to significant interference with terrestrial networks, reducing communication efficiency among terrestrial terminals. This article explores a novel uplink interference mitigation approach based on the collaborative beamforming (CB) method in multi-AAV network systems. Specifically, the AAV swarm forms an AAV-enabled virtual antenna array (VAA) to achieve the transmissions of gathered data to multiple base stations (BSs) for data backup and distributed processing. However, there is a tradeoff tradeoff between the effectiveness of CB-based interference mitigation and the energy conservation of AAVs. Thus, by optimizing the excitation current weights and hover position of AAVs as well as the sequence of data transmission to various BSs, we formulate an uplink interference mitigation multiobjective optimization problem (MOOP) to decrease interference affection, enhance transmission efficiency, and improve energy efficiency, simultaneously. In response to the computational demands of the formulated problem, we introduce an evolutionary computation method, namely chaotic nondominated sorting genetic algorithm II (CNSGA-II) with multiple improved operators. The proposed CNSGA-II efficiently addresses the formulated MOOP, outperforming several other comparative algorithms, as evidenced by the outcomes of the simulations. Moreover, the proposed CB-based uplink interference mitigation approach can significantly reduce the interference caused by AAVs to nonreceiving BSs.

In recent years, federated learning (FL) has continued to evolve with the advent of big data and the large language model (LLM), but it has also exposed numerous security and privacy issues. As a form of distributed machine learning, FL systems are more susceptible to poisoning attacks because training data are dispersed across different participants; additionally, the training achievement of FL may be subject to low-cost theft by some free-riders. Existing works have addressed defenses against the aforementioned two types of threats, but they often focus on defending against only one type and fail to effectively integrate defenses against multiple types of threats. However, in real-world Internet of Things (IoT) systems, the types of threats are not limited to just one category. In this work, we try to maintain the performance of the global model under poisoning attacks, preserve the privacy of the server under free-riders, and explore the balance between these two aspects. Therefore, this work proposes Federated Multi-Stage Asynchronous Roll-back (FedMAR), ensuring the quality of local updates; in addition, this work also provides privacy preservation in the global update process based on Rinyi Differential Privacy (RDP), and offers a certain basis for detecting free-riders. To validate the generalization of the proposed method, we conducted relevant experiments on both image and text datasets, and further investigated the robustness of the proposed method against poisoning attacks, model inversion attacks, data heterogeneity, and other aspects. The testing accuracy of the global model can even be improved by 7.2%.

With the rapid advancement of technologies such as artificial intelligence and the Internet of Things, video surveillance—being a core component of video IoT systems—has been widely adopted for underground coal mine safety monitoring. However, the dim lighting and heavy coal dust in underground mines result in poor visibility and significant detail loss in monitoring images, posing a major challenge to coal mine safety management. To address these issues, we propose a low-light image enhancement method tailored for underground coal mine environments, based on Zero-DCE. In our method, traditional convolutions are replaced with Ghost modules to reduce computational cost while maintaining feature extraction capability. Additionally, we incorporate global context blocks and a Vision Transformer branch to integrate more global information into the model. Specifically, the global context blocks improve the model’s ability to correct uneven illumination and prevent overexposure. Meanwhile, the Vision Transformer branch captures long-range dependencies and fuses local and global features to enhance brightness while mitigating color distortion. Furthermore, we replace the original quadratic iterative function with a reciprocal illumination mapping function, enabling more stable and perceptually aligned brightness adjustments. Experimental results on the coal mine underground personnel dataset demonstrate that our method outperforms several state-of-the-art low-light enhancement techniques, achieving superior results in both qualitative and quantitative evaluations. These findings indicate that our approach significantly improves the visibility and overall quality of underground coal mine monitoring images.

Homomorphic encryption (HE) is one of the more sophisticated methods of homomorphic cryptography (HC). HC efficiently contacts the interacting parties in open IoT and light-weighted network environments. This approach is capable of analyzing encrypted data without decryption. The operations use private and public keys. Then, during the assessment or evaluation, users may access the original data. Before conducting tests or evaluations, the customer must first encrypt the data and then decrypt it. Since consumers use several main cycles for the whole operation, which creates noise and computation overheads, the growth rate of computation overheads has increased. The growing ratio of noise to computation rate can interrupt the whole system, resulting in machine instability, protection, and privacy concerns. To resolve the security and privacy issues, the proposed schemes used different hardness assumptions, such as over-integer, learning with error, ideal lattices, bootstrapping, etc. In this article, we presents a comprehensive review of HE and its many varieties. The numerous possible applications of HE are covered at a high level in order to highlight the extent to which HE is used in the IoT and other lighted-weighted intelligent industry environments in a variety of various domains.

With the rapid development of Visual Internet of Things (VIoT) and text detection technology, they have been widely combined and applied to many industrial production sites, such as label text detection, achieving impressive results. However, there are still many shortcomings in the text detection technology: 1) the existing VIoT system has very limited detection precision for text with large scale changes, especially for some small-scale text detection; 2) the existing text detection algorithms cannot meet the actual situation, as the labels often contain handwritten texts, and the text to be detected is arbitrary shape; and 3) in the actual detection, there are many creases or defects on the text label. To solve the above problems, this article designs a text detection method based on a multiscale selection fusion feature pyramid and multisemantic spatial network (MSNet) to assist the VIoT system in detecting label text. First, a multiscale selective fusion feature pyramid is designed, which not only uses the texture extraction module to effectively improve the text texture feature and multiscale feature extraction ability, but also uses the cross-scale selective fusion block to selectively fuse the features of different stages to reduce the influence of pollution on detection. In addition, a MSNet is designed to capture the multisemantic spatial information of each feature channel by using the multiscale deep shared 1-D convolution, which effectively integrates global context dependence and multisemantic spatial prior. Experimental results show that the comprehensive index F-measure on the public datasets ICDAR2015, total-text, and CTW1500 is increased by 5.7%, 3.3%, and 3.8%, respectively. Furthermore, the precision, recall, and F-measure on the dataset label-text are 94.6%, 90.7%, and 92.6%, respectively. The label text detection VIoT system we designed has been deployed in the field and achieved excellent performance. The code of our proposed method can be found in:https://github.com/rebornone1/MSNet

The explosive growth of remote-sensing images generated by emerging space–air–ground integrated IoT networks makes centralized detector training infeasible due to limited bandwidth and strict data privacy constraints. While lightweight single-stage object detectors offer efficiency, they suffer significant accuracy degradation for small, dense, and arbitrarily oriented targets. Furthermore, existing federated object detection frameworks typically neglect client heterogeneity. To overcome these limitations, we propose a two-stage personalized federated detection framework. In Stage 1, we independently train a conventional single-stage rotated object detector on each client and aggregate model updates using an adaptive similarity momentum aggregation (ASMA) strategy, effectively pooling knowledge across non-IID client datasets to improve global generalization. In Stage 2, each client is equipped with a private selective depthwise attention convolution (SDAConv) module, leveraging Stage-1 priors to reconstruct fine-grained, client-specific features without additional communication overhead, thus tailoring predictions to local data distributions. Experiments conducted on five non-IID splits derived from DOTA-1.0, along with DIOR and VisDrone datasets, demonstrate improvements of up to +3.5 mAP compared to federated learning baselines under the same communication budget, simultaneously maintaining global robustness and enhancing local detection accuracy.

Clear monitoring images are crucial for the safe operation of coal mine Internet of Video Things (IoVT) systems. However, low illumination and uneven brightness in underground environments significantly degrade image quality, posing challenges for enhancement methods that often rely on difficult-to-obtain paired reference images. Additionally, there is a tradeoff between enhancement performance and computational efficiency on edge devices within IoVT systems.To address these issues, we propose a multimodal image enhancement method tailored for coal mine IoVT, utilizing an ISP operations within a differentiable CNN framework fusion architecture optimized for uneven illumination. This two-stage strategy combines global enhancement with detail optimization, effectively improving image quality, especially in poorly lit areas. A contrastive language-image pretraining (CLIP)-based multimodal iterative optimization allows for unsupervised training of the enhancement algorithm. By integrating traditional image signal processing (ISP) with convolutional neural networks (CNN), our approach reduces computational complexity while maintaining high performance, making it suitable for real-time deployment on edge devices. Experimental results demonstrate that our method effectively mitigates uneven brightness and enhances key image quality metrics, with preservation of original visual information (PSNR) improvements of 2.9%–4.9%, structural similarity (SSIM) by 4.3%–11.4%, and visual information fidelity (VIF) by 4.9%–17.8% compared to seven state-of-the-art algorithms. Simulated coal mine monitoring scenarios validate our method’s ability to balance performance and computational demands, facilitating real-time enhancement and supporting safer mining operations.

To address the growing challenge of energy efficiency in next-generation coordinated multipoint (CoMP) communication systems, this article develops a green CoMP optimization framework that integrates renewable energy harvesting, smart grid interactions, and real-time power control. We formulate a stochastic long-term weighted sum-rate maximization problem, incorporating transmit covariance variables and joint channel-aware precoding. To enable online implementation, we convert the time-averaged problem into an equivalent per-slot formulation and design an online dynamic beamforming and energy management (ODBEM) algorithm. The proposed ODBEM integrates three synergistic mechanisms: 1) dual-driven energy pricing; 2) Lyapunov drift-plus-penalty scheduling; and 3) momentum-based energy smoothing. We further conduct rigorous convexity and Karush–Kuhn–Tucker optimality analysis to ensure algorithmic correctness and convergence. Simulation results demonstrate that ODBEM outperforms baseline strategies in both throughput and energy cost, confirming its effectiveness for sustainable and adaptive CoMP transmission.

With the booming development of the underwater Internet of Things, underwater devices and data volume are explosively increasing. Thanks to the advantages of high efficiency and low complexity, the emerging rate splitting multiple access (RSMA) can be integrated with underwater optical wireless communication (UOWC), which can help improve resource utilization and system performance. However, the oceanic characteristics are distinctive and pose great challenges for RSMA-enabled UOWC networks. Precoding design is crucial for benefitting from RSMA-enabled systems, and thus, we explore the precoding optimization for RSMA-enabled UOWC networks over underwater turbulent channels. Specifically, the RSMA-enabled UOWC network is modeled, where a combined turbulent channel involving the effects of absorption, scattering, and underwater turbulence is considered, and a message transmission scheme with rate splitting design is analyzed. A precoding problem is formulated to maximize the ergodic sum rate (ESR) under the constraint of total transmitted power. Since the accurate expression of ESR is a non-closed form and intractable, we first propose a consecutive Fenton-Wilkinson (CFW)-based ergodic rate approximation approach to solve this formulation problem. Fenton-Wilkinson moment matching is consecutively employed to achieve a closed-form and low-complexity expression of the ergodic rate, as only Fenton-Wilkinson moment matching method can offer closed-form solutions for underlying parameters of the approximating log-normal distributions. For further solving the non-convex precoding problem, the successive convex approximation (SCA) approach is adopted, which is particularly applicable for resource-limited underwater environments. The effectiveness of the proposed CFW approach and precoding strategy is evaluated by extensive simulation results for various user deployments and different network loads.

Wearable device-based Human Activity Recognition (HAR) has attracted considerable interest with the rapid development of the Internet of things (IoT), and Federated Learning (FL) has been widely adopted in this domain for its ability to collaboratively train models across decentralized devices while preserving privacy. However, its performance is hindered by data heterogeneity arising from variations in the placement of the wearable devices, user behaviors, and physiological characteristics. In this work, we present LDA-FedHAR, a federated HAR framework designed for wearable devices by capturing more common knowledge from aligned client HAR data. It performs Local HAR Data Alignment (LDA) on each client, which is an entirely on-device alignment method that operates independently on local HAR data. By computing the transformation matrix solely from local HAR data and applying it to the data itself, LDA projects heterogeneous client data into a unified space, thereby reducing inter-client discrepancies at the source. To further enhance efficiency and robustness, we propose two IMU-specific variants, LDA(S-IMU) and LDA(C-IMU), which explore intra-and inter-IMU correlations based on practical placements of wearable devices. Experiments are conducted on 4 public HAR datasets: HHAR, Shoaib2014, OPPORTUNITY++, and PAMAP2. The results show that LDA effectively reduces inter-client discrepancies, and LDA-FedHAR along with its variants consistently outperforms state-of-the-art FL methods. Moreover, the improvements achieved by integrating LDA into other FL methods highlight its applicability.

Perceiving scene depth and 3-D structure is one of the key tasks for Internet of Video Things (IoVT) devices to understand and interact with the environment. Self-supervised monocular depth estimation has demonstrated significant potential in leveraging large-scale unlabeled datasets to achieve competitive performance, thereby playing an increasingly important role in depth estimation. Despite recent methods providing additional supervisory signals through self-distillation strategies to improve depth estimation, an effective method for generating pseudo-depth labels suitable for addressing occlusion issues among elements far from the camera remains unexplored. To address this limitation, we propose a patch-based self-distillation learning framework to exploit the potential of self-supervised monocular depth estimation in recovering fine-grained scene depth. In the proposed framework, elements far from the camera within the input image are enlarged by enlarging and cropping operations in the patch-based self-distillation branch. Guided by photometric consistency, the model learns the detailed occlusion relationships among elements from the enlarged patches, producing patch depth maps with fine structures. In the main branch, which takes full-scale images as input, patch depth maps serve as pseudo-depth labels through self-distillation loss to provide additional supervisory signals for regions where photometric consistency fails to offer effective supervision. This forces the depth estimation network to recover fine structures of elements far from the camera in full-scale input images. Regarding the architecture of the depth estimation network, we introduce a bin-center prediction. In this prediction, a global aggregator based on self-attention provides additional scene structure queries for adaptive scene depth discretization. Finally, to encourage the model to explore more general cues for depth inference beyond road plane cues, we propose a PatchMix data augmentation method to enhance the model’s generalization ability to unseen scenes. Extensive experiments on the KITTI dataset show that the proposed method significantly improves performance over the baseline, particularly in fine-grained scene depth estimation. Moreover, the model also exhibits good generalization performance when transferred to the Make3D and Cityscapes datasets.

Scalable video coding (SVC) and power division multiplexing (PDM) are crucial technologies for video streaming in internet-of-vehicle (IoV) networks due to their robustness over time-varying channels. However, the correlation of video tiers and channel fluctuations induce significant complexity in the joint design of SVC and PDM in IoV networks. To reduce such complexity, we propose a novel transmission strategy for SVC-based video streaming in PDM technology by facilitating cross-layer control across the application, data link, and physical layers. Specifically, we propose a concise framework where the modulation order, the power control, and prioritization of video tiers are jointly controlled. Moreover, we leverage the network abstraction layer units within an arbitrary group-of-pictures to improve the overall video data rate. The formulated joint control of the modulation order, the transmission power, and video-tier prioritization is proved to be a quasi-concave problem. Consequently, our proposed cross-layer optimization based SVC video transmission strategy could efficiently utilize the prioritized video tiers in the application layer, power control in the data-link layer, and modulation orders in the physical layer. Numerical results are used to demonstrate performance improvements over the benchmarks.

Self-supervised emotion recognition leveraging skeleton-based data offers a promising approach for classifying emotional expressions within the extensive amount of unlabeled data gathered by sensors in the Internet of Things (IoT). Recent advancements in this field have been driven by contrastive learning-based or generative learning-based self-supervised methods, which effectively tackle the issue of sparsely labeled data. In emotion recognition tasks, the emotional high-level semantics embedded in the skeleton data are more important than the subtle joint movements. Compared to existing methods, discrete label prediction can encourage SSL models to abstract high-level semantics in a manner similar to human perception. However, it is challenging to comprehensively capture emotional expressed in skeleton data solely from joint-based features. Moreover, emotional information conveyed through body movements may include redundant details that hinder the understanding of emotional expression. To overcome these challenges, we propose a novel discrete-label-based emotion recognition framework named the Appendage-Informed Redundancy-ignoring (AIR) discrete label framework. First, we introduce the Appendage-Skeleton Partitioning (ASP) module, which leverages limb movement data from the original skeleton to explore emotional expression. Next, we propose the Appendage-refined Multi-scale Discrete Label (AMDL) module, which transforms traditional self-supervised tasks into classification tasks. This design continuously extracts emotional semantics from skeleton data during pre-training, functioning similarly to predicting categories and subsequently classifying samples. To further reduce the nonessential information in skeleton data that may negatively impact the generation of accurate emotional categories, we propose the Appendage Label Refinement (ALR) module. It refines the generated categories by using the relationships between the skeleton and the various appendages obtained via ASP module. Finally, to maintain consistency across multiple scales, we introduce the Multi-Granularity Appendage Alignment (MGAA) method. By incorporating features from both coarse and fine scales, MGAA mitigates the encoder’s sensitivity to noise and enhances its overall robustness. We evaluate our approach on the Emilya, EGBM, and KDAE datasets, where it consistently outperforms state-of-the-art methods under various evaluation protocols.

Due to the advantages of flexible deployment and strong environmental adaptability of an unmanned aerial vehicle (UAV), UAVs serve as aerial base stations (BSs) to meet Quality of Services (QoSs) of ground users in internet of things (IoT) networks. NOMA (Non-Orthogonal Multiple Access) is a potential technique in wireless communications area, which can significantly improve sum spectrum efficiency (SE) of systems. To avoid the limitation of perfect CSI, opportunistic beamforming (OBF) is proposed, where a set of randomly generated weights is used to preprocess transmitted signals. Due to multiuser diversity gain introduced by OBF, OBF-NOMA systems can achieve approximate sum SE to conventional NOMA systems. Additionally, reconfigurable intelligent surfaces (RISs) are involved to overcome obstruction and obtain further improvements of SE. Therefore, this paper proposes a RIS-aid OBF-NOMA system in UAV-IoT networks, where random weights and opportunistic phase matrix are respectively applied in a UAV and RIS. Statistical characteristics of equivalent channels are derived in Nakagami-m (m≥1) fading channels. Theoretical asymptotic analyses of SE and bit error rate (BER) are then presented. Furthermore, a non-convex optimization problem is formulated to maximize SE. To obtain the optimal solution, we divide the problem into two sub-optimization problems and apply a joint iterative algorithm. Numerical results show that the proposed method achieves a satisfactory SE without complex channel estimation and perfect CSI.

Speech Emotion Recognition (SER) is important in improving human-computer interaction. Cross-Linguistic SER (CLSER) has been a challenging research problem due to significant variability in the linguistic and acoustic features of different languages. In this study, we propose a novel approach,HuMP-CAT, which combines HuBERT (Hidden Unit BERT), MFCC (Mel-Frequency Cepstral Coefficients), and Prosodic characteristics. These features are fused using a cross-attention transformer (CAT) mechanism during feature extraction. Transfer learning is applied to gain from a source emotional speech dataset to the target corpus for emotion recognition. We use IEMOCAP as the source data set to train the source model and evaluate the proposed method on seven data sets in five languages (i.e., English, German, Spanish, Italian, and Chinese). We show that, by fine-tuning the source model with a small portion of speech from the target datasets,HuMP-CATachieves an average accuracy of 78.75% across the seven datasets, with notable performance of 88.69% on EMODB in German language and 79.48% on EMOVO in Italian language. Our extensive evaluation demonstrates thatHuMP-CAToutperforms existing methods across multiple target languages.

Next-Generation Crowdsensing Networks (NGCNs) have become increasingly critical for smart cities, where data privacy and quality are pivotal concerns. Traditional trust mechanisms in crowdsensing mainly rely on static trust models, which are insufficient for dynamic security requirements. Zero-Trust security represents a promising opportunity, yet coming with notable challenges in NGCNs, including Unknown Workers Online Recruitment (UWOR), Information Elicitation Without Verification (IEWV), Privacy Preserving Data Evaluation (PPDE), and Dynamic Trust Abrupt Shift (DTAS). To address these challenges, we propose a Credibility-aware and Privacy-preserving Data collection scheme with Zero-trust (CPDZ) for secure and quality data collection in NGCNs. First, our CPDZ scheme encompasses a quality worker recruitment strategy with combinatorial multi-armed bandit models, utilizing Thompson Sampling for the secure and efficient resolution of the UWOR. Second, an active dispatching scheme for unmanned aerial vehicles is crafted to collect data as a gold standard to assist in overcoming the IEWV challenge. Third, as for the PPDE challenge, we propose a lightweight privacy-preserving scheme for dependable truth discovery and secure trust verification. Fourth, the DTAS challenge is managed by a dual verification scheme that integrates short-term and long-term trust assessments, ensuring stability and adaptability of the zero-trust security in our CPDZ scheme. Experiments confirm the superiority of our CPDZ scheme, showing a 12.5% increase in recruitment revenue and a 57.8% reduction in relative error compared to existing approaches.

While diffusion models have demonstrated remarkable success in computer vision tasks, their deployment in Internet of Things environments remains challenging. Edge devices face significant constraints in computational resources and must adapt to dynamic operating conditions. To address these limitations, we propose a novel system that accelerates AIgenerated content (AIGC) collaborative inference in dynamic edge networks. The proposed system introduces a multi-exit vision transformer-based U-Net architecture that enables efficient processing through adaptive exit point selection during the diffusion process, optimizing the trade-off between inference accuracy and computational efficiency. To optimize device-level operations, we develop an innovative generative AI-assisted reinforcement learning framework that determines optimal exit selection and offloading strategies to maximize generation quality and inference speed. Furthermore, we design a fine-tuning approach with policy reuse mechanisms that facilitates rapid reinforcement learning algorithm deployment across diverse environments. Extensive experimental evaluations demonstrate that our system outperforms existing algorithms in terms of balancing inference latency and generation quality, while also exhibiting improved adaptability to environmental variations.

In this paper, we address the problem of the operator’s economic profit maximization in a multi-access edge computing (MEC)-enabled time division multiple access (TDMA)-based air-ground integrated networking (AGIN) network. We consider to optimize task placement and replacement, unmanned aerial vehicle (UAV) placement, UAV flight time, access control, and task offloading ratios in user devices (UDs) and the UAV. The optimization is constrained by storage capacity, task processing quality of service (QoS) requirements, and TDMA requirements, etc. Our optimization is conducted in two time scales. Task placement and replacement are performed in a coarse-grained time scale (frame), while other optimizations are conducted in a fine-grained time scale (time slot). Due to the high dynamics of the environment, finding a solution is challenging. To address this problem, we present a hierarchical deep reinforcement learning (DRL) algorithm. The high-level component is a deep Q network (DQN) agent responsible for obtaining task placement and replacement solutions within a frame. The low-level component is an improved deep deterministic policy gradient (IDDPG) agent, which is used to address task processing-related issues within a time slot. Our simulations illustrate that the proposed algorithm has good performance in economic profit maximization compared with other algorithms.

To guarantee the low-congestion performance and quality of service (QoS) requirements of multi-services in Mega Low Earth Orbit Constellation Networks (MLEOCN), this paper focuses on the comprehensive communication link model in MLEOCN, commencing from users to access satellites, relayed by relay satellites, and finally delivered to the gateway by feeder satellites. Aiming at the problems of high congestion and low throughput in traditional path planning algorithms, we innovatively propose a multi-objective optimization service-correlated path optimization algorithm based on stochastic hill climbing strategy (MSCPO-SHCS). The algorithm initially achieves the joint optimization of three metrics through regular mapping and judicious weighting. Subsequently, it assesses the interplane hop via geometric parameter theory analysis (GPTA), then decouples the large-scale mixed integer optimization problem into the integer optimization problem superimposed linear programming problem, and ultimately employs the stochastic hill climbing strategy (SHCS) for path intelligent optimization. Based on the path Gaussianity assumption, we theoretically prove and numerically verify the convergence of the proposed algorithm. The simulation results indicate that the proposed algorithm boosts the throughput and load balancing coefficient compared with the greedy strategy, service-uncorrelated, minimum hop count, and resource allocation optimization. Additionally, it decreases the hop count compared with the maximum throughput and maximum balancing coefficient and maintains the optimal overall performance.

With its low latency, high throughput, good deployment flexibility, and cost-effectiveness, the low earth orbit (LEO) constellation is regarded as a promising technology for seamless coverage. Unlike geosynchronous orbiting (GSO) satellites, the highly dynamic evolution of LEO constellation topology poses a significant challenge to the traditional scheme of allocating wireless resources. This paper proposes a multisatellite cooperative coverage resource allocation for the LEO constellation. A multi-objective optimization problem focusing on throughput and coverage time is proposed for the overall service quality of the LEO constellation. To solve the complex coupling between multi-domain resources, the optimization problem is decomposed into three key subproblems, which are the beam placement problem, the joint beam association with power allocation problem, and the beam hopping time slot allocation problem. For each subproblem, an adaptive algorithm is proposed that effectively exploits the payload of LEO satellites to ensure the coverage performance of the constellation network. Simulation results demonstrate that the proposed coverage scheme enables fast convergence, enhances network throughput utility, and guarantees the stability and fairness of the communication services.

Device-free gesture recognition using mobile communication signals is a convenient and efficient technology with broad application prospects in smart homes and human-computer interaction. It utilizes the effect of gestures on surrounding signals to achieve gesture recognition. The cell-specific reference signals (CRS) information can be used to achieve the task in close-range training scenarios. However, when gestures are performed at long-range or in non-training scenarios, the recognition performance will significantly degrade. To enhance device-free gesture recognition capability in arbitrary scenarios, we propose the signal quality enhancement algorithm and the gesture spectrogram construction method to solve this problem. Specifically, we superimpose the CRS information from multiple carriers to improve the gesture signal-to-noise ratio and increase the gesture sensing range. Then, we extract the gesture dynamic components from the CRS information and construct gesture spectrograms to represent scenario-independent gesture motion patterns. Using the gesture spectrogram features, we design a deep network to accomplish the gesture recognition task. We built a prototype system on a software-defined radio platform. Experimental results show that our proposed method can effectively increase the gesture sensing range from 30m² to 228m² and achieve an average recognition accuracy of 82.5% for five types of gestures in arbitrary scenarios.

Unlabeled text representation learning (UTRL), encompassing static word embeddings such as Word2Vec and contextualized word embeddings such as bidirectional encoder representations from transformer (BERT), aims to capture semantic word relationships in a low-dimensional space without the need for manual labeling. These word embeddings are invaluable for downstream tasks such as document classification and clustering. However, the surge of short texts generated daily on social media platforms results in sparse word cooccurrences, compromising UTRL outcomes. Contextualized models such as recurrent neural network (RNN) and BERT, while impressive, often struggle with predicting the next word due to sparse word sequences in short texts. To address this, we introduce CGraphNet, a contrastive graph context prediction model designed for UTRL. This approach converts short texts into graphs, establishing links between sequentially occurring words. Information from the next word and its neighbors informs the target prediction, a process referred to as graph context prediction, mitigating sparse word cooccurrence issues in brief sentences. To minimize noise, an attention mechanism assigns importance to neighbors, while a contrastive objective encourages more distinctive representations by comparing the target word with its neighbors. Our experiments demonstrate CGraphNet's superior performance over other baselines, particularly in classification and clustering tasks on real-world datasets.

Node classification tasks aim to assign labels or categories to entire graphs based on their structural properties or node attributes. It can be adopted for various types of graph systems, including but not limited to network traffic, biological networks, knowledge graphs, etc., especially to social networks. This problem is well-studied, and solutions have demonstrated significant success in numerous real-world applications. However, in the situation where emerging categories are scarce or even have no labeled data, classical methods perform poorly on the whole, which has attracted growing attention. Based on this, in this article, we divide researches for node classification in social networks into two broad categories: traditional methods and novel strategies (few-shot/zero-shot learning). In traditional node classification methods, we summarize some classical methods for both homogeneous and heterogeneous networks, which includes unsupervised classifier, matrix factorization techniques, supervised methods, random-walk, and meta-path. Meanwhile, we introduce novel methods in few-shot or zero-shot learning. The article outlines the technical principles of various methods and analyzes their performance across different classes. It further summarizes the benchmark datasets used for evaluating node classification tasks. Finally, the major opportunities, challenges, and future research directions in few-shot and zero-shot learning for node classification in graph scenarios are discussed.

In multimedia social networks, the user's geo-location can be inferred by matching his shared images with the referenced satellite images, viz. cross-view image geo-localization. Although the existing most cross-view image geo-localization methods perform well in the center-misaligned scenario, in practical application, the shooting location of the query ground image is most likely not aligned with the center point of satellite images. Then, their geo-localization accuracy would drastically decrease. Therefore, we propose a novel cross-view image geo-localization model based on ground-to-satellite (G2S) transform, named CIG2S. First, the queried ground image is transformed into the aerial-view by spherical transform, generating G2S images, which could improve the similarity between ground and satellite images. Second, multiscale features are extracted from the original ground image, G2S images, and satellite images by twins-PCPVT. Furthermore, a dynamic similarity weighted loss function is designed to measure the distance between the query ground image and the referenced satellite image. Experimental results on three center-misaligned datasets, including VIGOR and the center-misaligned versions of CVUSA and CVACT, demonstrate that the proposed CIG2S model can significantly improve the geo-localization accuracy. For example, when compared with another vision-transformer-based model L2LTR-polar, CIG2S can outperform about 6.6% and 15.8% in the center-misaligned datasets CVUSA_CM and CVACT_CM.

Top-N recommendation systems are recognized as highly effective for delivering personalized services that cater to the varied interests of users. Nonetheless, current state-of-the-art (SOTA) analyses reveal a marked variability in their performance across users with differing levels of activity, which substantially undermines the quality of personalized recommendation services. Prevailing research tends to overlook this discrepancy, often presuming a uniform probability distribution in user preferences and employing a static model (such as a single latent vector) for user representation. This oversimplification impedes the adaptability of existing models to accommodate the spectrum of user activity levels. In our research, we introduce the variational kernel density estimation (VKDE) approach, an innovative nonparametric method designed to accurately capture the unique preference distributions of individual users. The VKDE framework integrates multiple local distributions to construct a comprehensive global preference profile for each user. We have developed a novel variational kernel function that delineates user-specific interests and constructs each local distribution accordingly. Additionally, we present a tailored sampling strategy that simplifies the complexity of the training process while preserving the efficacy of the recommendations. Empirical evaluations conducted on four widely recognized public datasets demonstrate that our VKDE model achieves superior performance over the SOTA alternatives, significantly enhancing accuracy for users with a broad range of activity levels.

Test-time adaptation (TTA) aims to boost the generalization capability of a trained model by conducting self-/unsupervised learning during the testing phase. While most existing TTA methods for video primarily utilize visual supervisory signals, they often overlook the potential contribution of inherent audio data. To address this gap, we propose a novel approach that incorporates audio information into video TTA. Our method capitalizes on the rich semantic content of audio to generate audio-assisted pseudo-labels, a new concept in the context of video TTA. Specifically, we propose an audio-to-video label mapping method by first employing pre-trained audio models to classify audio signals extracted from videos and then mapping the audio-based predictions to video label spaces through large language models, thereby establishing a connection between the audio categories and video labels. To effectively leverage the generated pseudo-labels, we present a flexible adaptation cycle that determines the optimal number of adaptation iterations for each sample, based on changes in loss and consistency across different views. This enables a customized adaptation process for each sample. Experimental results on two widely used datasets (UCF101-C and Kinetics-Sounds-C), as well as on two newly constructed audio-video TTA datasets (AVE-C and AVMIT-C) with various corruption types, demonstrate the superiority of our approach. Our method consistently improves adaptation performance across different video classification models and represents a significant step forward in integrating audio information into video TTA. The code and datasets will be made publicly available.

Most existing video moment retrieval (VMR) benchmark datasets face a common issue of sparse annotations-only a few moments being annotated. We argue that videos contain a broader range of meaningful moments that, if leveraged, could significantly enhance performance. Existing methods typically follow a generate-then-select paradigm, focusing primarily on generating moment-query pairs while neglecting the crucial aspect of selection. In this paper, we propose a new method, HyperAux, to yield auxiliary moment-query pairs by modeling the multi-modal hyper-interaction between video and language. Specifically, given a set of candidate moment-query pairs from a video, we construct a hypergraph with multiple hyperedges, each corresponding to a moment-query pair. Unlike traditional graphs where each edge connects only two nodes (frames or queries), each hyperedge connects multiple nodes, including all frames within a moment, semantically related frames outside the moment, and an input query. This design allows us to consider the frames within a moment as a whole, rather than modeling individual frame-query relationships separately. More importantly, constructing the relationships among all moment-query pairs within a video into a large hypergraph facilitates selecting higher-quality data from such pairs. On this hypergraph, we employ a hypergraph neural network to aggregate node information, update the hyperedge, and propagate video-language hyper-interactions to each connected node, resulting in context-aware node representations. This enables us to use node relevance to select high-quality moment-query pairs and refine the moments’ boundaries. We also exploit the discrepancy in semantic matching within and outside moments to construct a loss function for training the HGNN without human annotations. Our auxiliary data enhances the performance of twelve VMR models under fully-supervised, weakly-supervised, and zero-shot settings across three widely used VMR datasets: ActivityNet Captions, Charades-STA, and QVHighlights. We will release the source code and models publicly.

Feature selection (FS) is a very important technique for hyperspectral image (HSI) classification, as successfully selecting informative features can significantly increase the learning performance while reducing the computational cost. However, most of the existing FS methods tend to treat the HSI as a whole for FS, which does not fully consider the unique characteristics of HSIs and disregards the fact that different feature classes possess varying preferences for features. Thus, this paper proposes a superpixel segmentation based evolutionary multitasking algorithm for FS of HSIs, called SS-EMT. First, the superpixel segmentation method is used to partition the original HSI into several superpixel blocks, which can preserve well the information of different classes of the original image. Second, in order to explore each superpixel block efficiently, an evolutionary multitasking algorithm using particle swarm optimization is designed, which treats each superpixel block as a subtask and then optimizes these subtasks collaboratively by transferring useful knowledge among related subtasks. In addition, a new individual evaluation mechanism is devised to obtain multiple high-quality feature subsets with different numbers of features simultaneously in a single run, thus reducing the computational cost. Finally, extensive experimental results on four common HSI datasets under three classifiers validate that our proposed method outperforms several state-of-the-art FS methods.

Surrogate-assisted evolutionary algorithms (SAEAs) have shown promising performance in tackling expensive multiobjective optimization problems (EMOPs). However, existing SAEAs solve EMOPs separately, which ignore their optimization experiences earned before. Inspired by multitasking optimization paradigm for multitasking multiobjective optimization problems (MTMOPs), this article designs the first SAEA for tackling expensive MTMOPs (EMTMOPs) with adaptive knowledge transfer. First, a competitive surrogate selection is proposed to improve the generalization ability of approximating various EMOP tasks, where two types of surrogate models are trained and then compete for use to replace real expensive evaluations. Then, an adaptive solution selection is designed, which identifies promising transfer solutions to accelerate the solving of target task and selects promising infill solutions for real expensive evaluations to refine the surrogate models. The performance of our algorithm is validated on three commonly used benchmark suites and some real-world EMTMOPs. The experiments validate our superiority over several state-of-the-art SAEAs on most test cases.

With the advancement of Big Data technology, deep learning automatic modulation recognition (DLAMR) has undergone new improvements. Existing DLAMR methods focus mostly on the primary matching of the model itself or ubiquitous big communications data, which lack interpretability and ignore deep representations for the modulation mechanism of the communication signals; thus, difficulties in further improving the recognition accuracy and multiquadrant amplitude modulation (MQAM) discriminability in complex communication environments are encountered. In response to these challenges, this article proposes an innovative communication signal graph mapping method to address the uncertainty in the modulation mechanisms. Specifically, it models sampling points as nodes; connects inter- and intrasymbol points with edges to represent modulation mechanisms and propagation uncertainty; and maps amplitude, phase, in-phase, and quadrature values as node features. A deep graphical and temporal neuro-fuzzy methodology (GT-DNFS) that integrates graph attention networks and bidirectional long short-term memory networks is subsequently proposed for DLAMR. The numerical results show that GT-DNFS achieves a significantly higher recognition accuracy of 93.01%, and an MQAM (M=16, 64) discrimination of 94.5%. This research offers valuable insights for neuro-fuzzy networks and efficient DLAMR algorithm design.

Video Anomaly Detection (VAD) remains a fundamental yet formidable task in the video understanding community, with promising applications in areas such as information forensics and public safety protection. Due to the rarity and diversity of anomalies, existing methods only use easily collected regular events to model the inherent normality of normal spatial-temporal patterns in an unsupervised manner. Although such methods have made significant progress benefiting from the development of deep learning, they attempt to model the statistical dependency between observable videos and semantic labels, which is a crude description of normality and lacks a systematic exploration of its underlying causal relationships. Previous studies have shown that existing unsupervised VAD models are incapable of label-independent data offsets (e.g., scene changes) in real-world scenarios and may fail to respond to light anomalies due to the overgeneralization of deep neural networks. Inspired by causality learning, we argue that there exist causal factors that can adequately generalize the prototypical patterns of regular events and present significant deviations when anomalous instances occur. In this regard, we propose Causal Representation Consistency Learning (CRCL) to implicitly mine potential scene-robust causal variable in unsupervised video normality learning. Specifically, building on the structural causal models, we propose scene-debiasing learning and causality-inspired normality learning to strip away entangled scene bias in deep representations and learn causal video normality, respectively. Extensive experiments on benchmarks validate the superiority of our method over conventional deep representation learning. Moreover, ablation studies and extension validation show that the CRCL can cope with label-independent biases in multi-scene settings and maintain stable performance with only limited training data available.

Bike-sharing demand prediction involves complex, dynamic spatio-temporal dependencies and various influencing factors, thus becomes one of technical challenges in intelligent transportation systems. Existing methods often rely on predefined adjacency matrices based on distance or road connectivity, and typically ignore multi-scale temporal features and external factors such as weather, holidays, social events, and so on. To address these limitations, we propose a model based on dynamic time warping (DTW) and spatio-temporal graph attention network (GAT) to improve the accuracy of bike-sharing demand prediction. In the proposed model, we use a data-driven approach to construct an adjacency matrix that effectively reflects the real dependencies between bike-sharing stations, and temporal attention mechanism is integrated with graph attention network to capture dynamic spatio-temporal correlations hidden in the data. Moreover, multi-scale temporal gated convolutions are applied to fuse short-term and long-term temporal features. The experimental results demonstrate that our proposed model significantly outperforms recent baseline methods in terms of MAE and RMSE evaluation metrics. Meanwhile, we find that the external factors of weather, public facilities and traffic accidents have different influence on results, and the weather has the greatest impact on bike-sharing demand.

Platoon-based connected vehicles have recently received increasing attention from academia and industry since they are considered promising solutions to transform our mobility society into the next generation. Vehicular communication and platoon coordination are two aspects of enabling technologies for mobile edge computing (MEC)-enabled cooperative vehicle-infrastructure systems (CVIS), while few efforts have incorporated these two dimensions into a joint implementation framework. In this paper, we investigate the problem of joint car-following coordination and data transmission scheduling of vehicle platoons. We develop a two-tier hierarchical framework for vehicle platooning: a fuel-efficient mobility optimization layer for car-following coordination and a reliable vehicle-to-infrastructure (V2I) communication layer for data transmission scheduling. Specifically, we present a platoon-based fuel consumption minimization model and a car-following control protocol to derive fuel-efficient control inputs. We also propose a reliability-oriented and delay-constrained data transmission scheduling model that is driven by upper-layer car-following coordination. We derived a closed-form expression for the reliability-optimal data transmission scheduling solution, which incorporates platoon mobility, channel characteristics, and application requirements. With simulations, we show that our joint method improves fuel efficiency and communication reliability for platooning vehicles. In particular, the proposed method reduces the platoon’s fuel consumption per time slot by 16.4%, meanwhile making the communication reliability 1.31 times higher than other traditional methods.

With the rapid expansion of interactions across various domains such as knowledge graphs and social networks, anomaly detection in dynamic graphs has become increasingly critical for mitigating potential risks. However, existing anomaly detection methods often assume noise-free dynamic graphs, overlooking the prevalence of noisy dynamic graphs in real-world applications. Specifically, noisy dynamic graphs affected by structural noises-such as spurious and missing nodes and edges-struggle to consistently provide reliable structural evidence for anomaly detection. To tackle this challenge, we propose an Evolutionary Perception Method (EPM) for identifying anomalous nodes in noisy dynamic graphs by resisting the interference of structural noises. EPM primarily consists of two components: a dynamic fitter and a filtering reviser. The dynamic fitter characterizes the interaction dynamics of nodes that removes and generates links at each period as a multiple superposition state, utilizing various link prediction algorithms to fit evolutionary mechanisms. Additionally, the filtering reviser designs evolutional entropies to quantify the evolutional uncertainty in multiple superposition states, further designing the Kalman filter to optimize these entropies. Extensive experiments show that the proposed EPM method surpasses state-of-the-art approaches in detecting anomalous nodes in noisy dynamic graphs.

In unsupervised graph anomaly detection, existing methods usually focus on detecting outliers by learning local context information of nodes, while often ignoring the importance of global context. However, global context information can provide more comprehensive relationship information between nodes in the network. By considering the structure of the entire network, detection methods are able to identify potential dependencies and interaction patterns between nodes, which is crucial for anomaly detection. Therefore, we propose an innovative graph anomaly detection framework, termed CoCo (Context Correlation Discrepancy Analysis), which detects anomalies by meticulously evaluating variances in correlations. Specifically, CoCo leverages the strengths of Transformers in sequence processing to effectively capture both global and local contextual features of nodes by aggregating neighbor features at various hops. Subsequently, a correlation analysis module is employed to maximize the correlation between local and global contexts of each normal node. Unseen anomalies are ultimately detected by measuring the discrepancy in the correlation of nodes’ contextual features. Extensive experiments conducted on six datasets with synthetic outliers and five datasets with organic outliers have demonstrated the significant effectiveness of CoCo compared to existing methods.

In the era of Big Data, large-scale machine learning models have revolutionized various fields, driving significant advancements. However, large-scale model training demands high financial and computational resources, which are only affordable by a few technological giants and well-funded institutions. In this case, common users like mobile users, the real creators of valuable data, are often excluded from fully benefiting due to the barriers, while the current methods for accessing largescale models either limit user ownership or lack sustainability. This growing gap highlights the urgent need for a collaborative model training approach, allowing common users to train and share models. However, existing collaborative model training paradigms, especially federated learning (FL), primarily focus on data privacy and group-based model aggregation. To this end, this paper intends to address this issue by proposing a novel training paradigm named decentralized relay learning (DeRelayL), a sustainable learning system where permissionless participants can contribute to model training in a relay-like manner and share the model. In detail, this paper presents the architecture and workflow of DeRelayL, designs incentive mechanisms to ensure sustainability, and conducts theoretical analysis and numerical simulations to demonstrate its effectiveness

Collaborative sensing has emerged as a novel sensing paradigm, entailing multi-sensor data sharing and multimodal modeling to collaboratively understand sensing behaviors. However, current solutions, i.e., data-level and decision-level fusion methods, fall short of generality, expert knowledge, and holistic/chronic perspective. In this paper, we proposeLLMCoSento revisit collaborative sensing with Large Language Models (LLMs). Specifically,LLM-CoSendesigns a semantic-level fusion approach for inference results for collaborative sensing. Such an approach is characterized by its generality, making it applicable to any heterogeneous devices, and its expert knowledge incorporation, which provides chronic, holistic, and insightful perspectives on the inference results. Regarding inference absence challenges, we propose a personalized model design method to constrain inference time, and a voting-based two-pass prompt engineering strategy for token completion. Regarding inference error challenges, we propose an accuracy restoration strategy for personalized models, and a two-level error estimator coupled with self-correction. Experimental results of human digital system use case on four corresponding benchmark datasets showLLM-CoSencan decrease inference absence by 72.83% and inference errors by 7.65% on average.

With the explosive growth of information and the continuous expansion of applications, Industrial Internet of Things (IIoT) is facing huge data processing and storage pressure. With mobile edge computing (MEC) technology, the computing power network connects the geographically distributed computing nodes and then coordinates the allocation and scheduling of resources, transmits data, and eventually relieves the pressure of the industrial site. However, the rigorous demands of IIoT for real-time and stability pose some daunting challenges. To this end, we propose an online computation offloading approach with dual stability guarantee, named OCODSG. Specifically, the Lyapunov function is used to optimize the stability of the virtual queue, and the system stability is optimized based on the network jitter measurement. Moreover, the Dueling Double Deep Q Network (D3QN) algorithm based on deep reinforcement learning (DRL) is used for model autonomous training, while Gaussian noise is added to the network parameter space to encourage exploration and enhance algorithm robustness. Finally, experimental results on both simulated and real datasets demonstrate that OCODSG improves service efficiency and system stability.

Unmanned aerial vehicle (UAV)-assisted mobile edge computing (MEC) is emerging as a promising paradigm to provide aerial-terrestrial computing services in close proximity to mobile devices (MDs). However, meeting the demands of computation-intensive and delay-sensitive tasks for MDs poses several challenges, including the demand-supply contradiction between MDs and MEC servers, the demand-supply discrepancy between MDs and MEC servers, the trajectory control requirements on energy efficiency and timeliness, and the different time-scale dynamics of the network. To address these issues, we first present a hierarchical architecture by incorporating terrestrial-aerial computing capabilities and leveraging UAV flexibility. Furthermore, we formulate a joint computing resource allocation, computation offloading, and trajectory control problem to maximize the system utility. Since the problem is a non-convex and NP-hard mixed integer nonlinear programming (MINLP), we propose a two-timescale joint computing resource allocation, computation offloading, and trajectory control (TJCCT) approach for solving the problem. In the short timescale, we propose a price-incentive model for on-demand computing resource allocation and a matching mechanism-based method for computation offloading. In the long timescale, we propose a convex optimization-based method for UAV trajectory control. Besides, we theoretically prove the stability and polynomial complexity of TJCCT. Extensive simulation results demonstrate that the proposed TJCCT is able to achieve superior performances in terms of the system utility, average processing rate, average completion delay, average completion ratio, and average cost, while meeting the energy constraints despite the trade-off of the increased energy consumption.

Low Earth Orbit (LEO) constellations and Unmanned Aerial Vehicle (UAV) networks enable wide coverage for the sixth generation (6 G) mobile communication. However, it is a challenge to achieve high scheduling success rate, ultra-low latency, and efficient load balance in the Space-Air-Ground Integrated 6 G Network (SAGGIN). This paper addresses the following issue:How to effectively and orderly transmit time-sensitive traffic in SAGGIN under strict deadlines, limited computational ability, and restrained link capacity?Specifically, this paper uses Software-Defined Networking (SDN) and designs a joint optimization method to enhance the traffic transmission ability of SAGGIN. Considering response time, computing cost, and link capacity in SAGGIN, the scheduling, computing, and load balance issues are modeled as a multi-objective optimization problem that minimizes the worst-case response time and computing cost of data frames while maximizing the network flow. Then, this paper leverages a Federated Reinforcement Learning (FRL) scheme to solve the problem. Results show that the FRL could achieve great scheduling, computing, and load balance performance. Specifically, our method can successfully schedule 80% of the traffic at most when the current network load is around 90%. Furthermore, the computational delay could reduce around 50%.

Federated Learning (FL) has significant potential to protect data privacy and mitigate network burden in mobile edge computing (MEC) networks. However, due to the system and data heterogeneity of mobile clients (MCs), client selection and bandwidth allocation is key for achieving cost-efficient FL in MEC networks with limited bandwidth. To address these challenges, we investigate the issue of joint client selection and bandwidth allocation for reducing the cost (i.e., latency and energy consumption) of FL training. We formulate the problem and decompose it into a holistic subproblem to reduce the number of rounds and a partial subproblem to reduce the costs of FL each round. We propose a joint class-balanced client selection and bandwidth allocation (CBCSBA) framework to address the whole problem. Specifically, for the holistic subproblem, CBCSBA combines MCs into groups, each having data distribution as close as possible to class-balanced distribution; For the partial subproblem, CBCSBA reduces costs by exploratively selecting a group and sequentially optimizing the latency and energy consumption of MCs within the group. Experimental results show that CBCSBA outperforms the baseline frameworks in reducing latency by 28.2% and energy consumption by 25.3% on average in the considered four datasets.

To reduce redundant traffic transmission in both wired and wireless networks, optimal content placement problem naturally occurring in many applications is studied. In this paper, considering the limited cache capacity, unknown popularity distribution and non-stationary user demands, we address this problem by jointly optimizing content caching and routing with the objective of minimizing transmission cost. By optimizing the routing with theroute-to-least cost-cachepolicy, the content caching process is modeled as a Markov decision process (MDP), aiming to maximize caching reward. However, the optimization problem consists of multiple nodes selecting caching contents, which leads to the combinatorial increase of the number of action dimensions with the number of possible actions. To handle this curse of dimensionality, we propose an intelligent caching algorithm by embedding action branching architecture into a dueling double deep Q-network (D3QN) to optimize caching decisions, and thus the agent at the controller can adaptively learn and track the underlying dynamics. Considering the independence of each branch, a marginal gain-based replacement rule is proposed to satisfy cache capacity constraint. Our simulation results show that compared with the prior art, the caching reward and hit rate of the proposed algorithm are increased by 35.3% and 33.6% respectively on average.

As a distributed machine learning method, federated learning (FL) can collaboratively train a global model with multiple devices without sharing the original data, thus protecting certain privacy. However, due to the strong heterogeneity of edge nodes (ENs) participating in FL, the quality of data uploaded to the parameter server (PS) varies significantly. Without an appropriate incentive mechanism, low-quality contributors may receive disproportionately high rewards, while high-quality contributors may lack sufficient motivation, leading to inefficient participation and suboptimal global model performance. Consequently, it is critical to develop an effective incentive mechanism to promote fairness for the FL process. To address the issues of existing FL incentive mechanisms lacking privacy protection performance analysis, we propose a fairness-aware incentive mechanism for multi-server FL in edge-enabled wireless differential privacy (DP) networks. Specifically, the wireless channel noise is used to provide DP protection for the local model gradients uploaded by ENs. Next, the interaction between the PSs and ENs is modeled as a Stackelberg game. Furthermore, we solve the Stackelberg game process using backward induction and theoretically propose optimal strategies for both the PSs and ENs. Finally, extensive numerical simulations using real datasets demonstrate the superior performance of our theoretical analysis of the proposed scheme.

The increasing popularity of earable devices stimulates great academic interest to design novel head gesture-based interaction technologies. But existing works simply consider it as a singular activity recognition problem. This is not in line with practice since users may have different body movements such as walking and jogging along with head gestures. It is also beneficial to recognize body movements during human-device interaction since it provides useful context information. As a result, it is significant to recognize such composite activities in which actions of different body parts happen simultaneously. In this paper, we propose a system called CHAR to recognize composite head-body activities with a single IMU sensor. The key idea of our solution is to make use of the inter-correlation of different activities and design a multi-task learning network to extract shared and specific representations. We implement a real-time prototype and conduct extensive experiments to evaluate it. The results show that CHAR can recognize 60 kinds of composite activities (12 head gestures and 5 body movements) with high accuracies of 89.7% and 85.1% in sufficient data and insufficient data cases, respectively.

Acoustic-based human gesture recognition (HGR) offers diverse applications due to the ubiquity of sensors and touch-free interaction. However, existing machine learning approaches require substantial training data, making the process time-consuming, costly, and labor-intensive. Recent studies have explored cross-modal methods to reduce the need for large training datasets in behavior recognition, but they typically rely on open-source datasets that closely align with the target domain, limiting flexibility and complicating data collection. In this paper, we propose${\sf Img2Acoustic}$, a novel cross-modal acoustic-based HGR approach that leverages models trained on open-source image datasets (i.e., EMNIST, Omniglot) to effectively recognize custom gestures detected via acoustic signals. Our model incorporates a task-aware attention layer (TAAL) and a task-aware local matching layer (TALML), enabling seamless transfer of knowledge from image datasets to acoustic gesture recognition. We implement${\sf Img2Acoustic}$on commercial devices and conduct comprehensive evaluations, demonstrating that our method not only delivers superior accuracy and robustness compared to existing approaches but also eliminates the need for extensive training data collection.

For visual disbalance defects (VDDs) in low-light images, such as brightness unevenness and color imbalance, existing enhancement methods struggle to extract defect features from local regions and apply adaptive enhancement based on varying degrees of these defects. To address these challenges, we propose an unsupervised multi-modal enhancement method based on a high-order adaptive curve, named CLIP-AE. Specifically, we introduce a multi-modal recurrent optimization approach utilizing contrastive language-image pre-training (CLIP). This method iteratively optimizes variable embedded prompts and an Adaptive Enhancement Module (AEM) to establish dependencies between the prompts and detailed style features in the images, guiding the AEM to perform adaptive image enhancement. Additionally, we implement a progressive feature alignment strategy to enhance the model's ability to perceive style features and improve optimization efficiency by using multiple enhanced images with identical content features and incremental style features. In the AEM, the optimized Hyperparameters Generative Network (HGN) generates the optimal hyperparameters, which drive a High-Dimensional Nested Gamma correction (HDN-Gamma) to perform pixel-wise adaptive enhancement for VDDs. HDN-Gamma further maps pixel values using specific enhancement curves to avoid artifacts. Extensive experiments demonstrate that our method effectively improves visual disbalance defects and reduces artifacts. Compared to seven state-of-the-art algorithms, our method shows significant improvements (PSNR: 16.46%, 16.89%, and 15.14%; SSIM: 9.26%, 8.02%, and 9.85%; MUSIQ: 6.37%, 6.54%, and 7.45%) on the LOL, SICE, and MIT-Adobe FiveK datasets. Our approach offers a novel solution for applying multimedia technology in low-light image enhancement tasks.

Service Function Chaining (SFC) is widely deployed by telecom operators and cloud service providers, offering traffic QoS guarantees and other additional functions for various applications. The network state at the time of SFC deployment can differ significantly from the runtime conditions, leading to excessive resource allocation and consequent energy waste. The existing SFC reconfiguration methods face the challenge of meeting the latency requirements of delay-sensitive applications while achieving significant energy savings. This paper proposes FR-SFCO, a flow rate-aware SFC offloading framework on programmable data planes for delay-sensitive flows. Specifically, we designed a TCAM-friendly table matching method for FR-SFCO to reduce the flow entries needed for SFC offloading in programmable switches and support larger numbers of offloaded SFC. Then, we proposed a dual-threshold-based offloading trigger mechanism that, according to the real-time traffic arrival rate, can fast offload SFC flows before they default to servers. Building on this, we propose DQN-AOTA, an adaptive offloading thresholds adjustment algorithm based on Deep Q-Learning, which can wisely change the offloading thresholds by interacting with a dynamic network traffic environment to minimize the packet loss and long-term energy consumption. Finally, we build a testbed using BMv2 software switches and Docker containers for extensive evaluation. The experimental results demonstrate the effectiveness of our solution which not only meets the latency constraints for delay-sensitive SFC flows but also reduces energy expenditure by at least 14.6%.

In disaster scenarios, conventional terrestrial multi-access edge computing (MEC) paradigms, which rely on ground infrastructure, may become unavailable due to infrastructure damage. With high-probability line-of-sight (LoS) communication, flexible mobility, and low cost, uncrewed aerial vehicle (UAV)-assisted MEC is emerging as a promising paradigm to provide edge computing services for ground user devices (UDs) in disaster-stricken areas. However, the limited battery capacity, computing resources, and spectrum resources also pose serious challenges for UAV-assisted MEC, which can potentially shorten the service time of UAVs and degrade the quality of experience (QoE) of UDs without an effective control approach. To this end, in this work, we first present a hierarchical architecture of multiple-UAV-assisted MEC networks that enables the coordinated provision of edge computing services by multiple UAVs. Then, we formulate a joint task offloading, resource allocation, and UAV trajectory control optimization problem (JTRTOP) to maximize the QoE of UDs while considering the energy and resource constraints of UAVs. Since the problem is proven to be a future-dependent and NP-hard problem, we propose a novel online joint task offloading, resource allocation, and UAV trajectory control approach (OJTRTA) to solve the problem. Specifically, the JTRTOP is first transformed into a per-slot real-time optimization problem (PROP) using the Lyapunov optimization framework. Then, a two-stage optimization method based on game theory and convex optimization is proposed to solve the PROP. Simulation results show that the proposed OJTRTA outperforms various benchmark approaches and achieves at least a 10% improvement in the QoE of UDs compared to deep reinforcement learning (DRL)-based algorithms, thereby validating the superiority of the proposed approach.

Predicting the causal flow by fusing multimodal perception is fundamental for constructing the bodily awareness of soft robots. However, forming such a predictive model while fusing the multimodal sensory data of soft robots remains challenging and less explored. In this study, we leverage the free energy principle within a Bayesian probabilistic deep learning framework to merge visual, pressure, and flex sensing signals. Our proposed multimodal association mechanism enhances the fusion process, establishing a robust computational methodology. We train the model using a newly collected dataset that captures the grasping dynamics of a soft gripper equipped with multimodal perception capabilities. By incorporating the current state and image differences, the forward model can predict the soft gripper's physical interaction and movement in the image flow, which amounts to imagining future motion events. Moreover, we showcase effective predictions across modalities as well as for grasping outcomes. Notably, our enhanced variational autoencoder approach can pave the way for unprecedented possibilities of bodily awareness in soft robotics.

Demand response (DR) plays an essential role in smart grids to reconfigure the load profile to match the energy supply for reliable and economic operation. This article presents an online adaptive DR strategy based on stochastic learning and optimization for smart microgrids with renewable energy to maximize the operation profit. To enable prompt interaction with the stochastic dynamics of usage demands, renewable generations and real-time pricing, a novel event-driven continuous-time Markov control processes model is introduced to formulate the DR optimization. Based on performance sensitivity analysis, a stochastic learning algorithm that combines potentials estimate and policy iteration is developed to find the optimal DR policy online. The presented strategy is environment-adaptive and computation-efficient, which is competent for real-time control and optimization in unknown environments. Simulations have been conducted to evaluate the performance of the presented strategy, and the results demonstrate the effectiveness.

With the explosive growth of smart devices and applications, the demand for mobile service with higher data rate and better quality of service is growing rapidly. Ultra-dense networks, capable of providing higher network throughput, remain one of the key technologies for next-generation mobile communications. However, the densification of network further reduces the coverage of base stations and the distance between each other, which in turn leads to unnecessary and frequent handovers (HOs), affects the stability and reliability of communication links. HO failures can even occur due to the improper HO control parameter (HCP) values. To this end, a HO type prediction and parameter optimization method based on machine learning is proposed. First, the HO is divided into four categories: successful handover (SHO), ping-pong handover (PPHO), too-late handover (TLHO), and too-early HO (TEHO). Second, we combine reinforcement learning with supervised learning and propose a novel adaptive HCP adjusting scheme. Specifically, deep Q-network dynamically selects HCP values through environmental information and supervised learning-based HO prediction results. Simulation results demonstrate that our proposed scheme achieves a prediction accuracy of 94.83%, while reducing the PPHO rate by 15%, the TEHO rate by 2%, and the TLHO rate by 3%.

Incorporating an active reconfigurable intelligent surface on an autonomous aerial vehicles (AAVs), denoted as an aerial reconfigurable intelligent surface (ARIS), introduces a novel dimension for secure transmissions. Given the constraint of limited battery capacity in AAVs, energy management emerges as a key challenge within AAV networks. In response, we propose a secure energy efficiency (SEE) transmission scheme for ARIS networks, where active ARIS is strategically deployed to enhance information security. In addition, a SEE optimal problem is formulated by considering the imperfect wiretap channel state information to optimize the active beamforming vector and the ARIS position. For this non-convex problem, we first reformulate the fractional SEE objective into an equivalent form and subsequently decompose it into two distinct subproblems: optimizing the AAV’s position and designing the active beamforming. For the AAV’s position optimization, we propose a sophisticated deep deterministic policy gradient algorithm that enables the AAV to autonomously determine the optimal ARIS position through a self-learning strategy. Regarding beamforming design, we transform this aspect into a quadratic constrained quadratic programming problem and design an alternating direction multiplier method to optimize the reflection coefficient. Subsequently, an alternating optimization algorithm is proposed to synergistically solve these subproblems. Empirical simulations validate our proposed scheme, indicating an improvement in SEE of up to 47.2%. This significant improvement underscores the efficacy of the proposed ARIS-assisted secure transmission scheme in enhancing both security and energy efficiency in AAV networks.

Next-generation Internet of Things (IoT) technology is vital for sixth-Generation (6G) communication systems, driving exponential growth in spectrum resource demand. Spectrum sensing, essential for identifying unused spectrum, and Non-Orthogonal Multiple Access (NOMA), which allows efficient frequency band sharing among users, can significantly improve spectrum efficiency. However, current sensing methods do not fully support NOMA, resulting in suboptimal performance. Motivated by such a circumstance, we propose a feature-based spectrum sensing method for uplink communication in power-domain NOMA IoT scenarios with multi-user interference, aiming to maximize both static and dynamic spectrum efficiency. Firstly, we introduce the notion of orbits to represent non-fully occupied spectral holes. Then we elaborate on the sensing criterion as well as workflow and design the two-stage spectrum sensing framework, which proposes the orbit estimation sensing algorithm in the stage 1 and accurate sensing threshold in the stage 2, to mitigate false alarm fluctuations. The closed-form solution for the estimation threshold and accurate threshold configuration are derived thereafter. Simulation results show that our proposed multi-orbit sensing method has stable performance and achieves average 30% system throughput gains compared to the latest NOMA techniques at 5 dB.

With the rapid development of space technology, the role of satellite communications has become progressively significant. Non-terrestrial communication is deemed a critical scenario in the sixth generation (6G) communication systems, which showcases seamless connectivity, minimal geographic constraints and substantial communication capacity. Simultaneously, satellites and terminals spring up, spatial density increases, which further emphasizes the scarcity of spectrum resources. Consequently, to improve spectrum utilization for non-terrestrial communication is a significant concern. Spectrum sensing, which allows dynamic resource reuse, plays an important role in 6G. However, high mobility in non-terrestrial scenarios poses great challenges, such as fast time-varying channels, Doppler effect, etc., which seriously affect sensing accuracy and cannot well support optimal spectrum utilization. Motivated by such circumstances, this paper proposes an elastic sensing method for the downlink non-terrestrial communication scenario. Firstly, we design the system architecture and sensing workflow. To overcome the negative effects raised by high mobility, we propose the elastic sensing criterion and multi-area dividing scheme for the sensing zone. Thresholds affected by the elastic sensing are derived for different areas. Finally, the numerical results show that from -10 dB to -5 dB, the proposed method can improve the total performance by an average of 28.3% while stabilizing the false alarm probability around 0.1 typical level and demonstrating higher constancy compared with traditional technologies from −10 dB to −5 dB.

Distributed sparse Gaussian process (dGP) models provide an ability to achieve accurate predictive performance using data from multiple devices in a time efficient and scalable manner. The distributed computation of model, however, risks exposure of privately owned data to public manipulation. In this paper we propose a secure solution for dGP regression models using multi-key homomorphic encryption. Experimental results show that with a little sacrifice in terms of time complexity, we achieve a secure dGP model without deteriorating the predictive performance compared to traditional non-secure dGP models. We also present a practical implementation of the proposed model using several Nvidia Jetson Nano Developer Kit modules to simulate a real-world scenario. Thus, secure dGP model plugs the data security issues of dGP and provide a secure and trustworthy solution for multiple devices to use privately owned data for model computation in a distributed environment availing speed, scalability and robustness of dGP.

Deep Neural Networks (DNNs) have demonstrated remarkable performance in classification and regression tasks on RGB-based pathological inputs. The network’s prediction mechanism must be interpretable to establish trust in the clinical routine. One principal approach to interpretation is feature attribution. Feature attribution methods identify the importance of input features for the output prediction. Building on the Information Bottleneck Attribution (IBA) method, we recognize the RGB’s input regions with high mutual information with the network’s output for each prediction. IBA identifies input regions that have sufficient predictive information. In this paper, we introduce "IBATree", a novel approach that combines IBA with decision trees to enhance both the interpretability and accuracy of DNNs in cancer cell classification. Our method leverages the information bottleneck framework to inject noise into feature maps and then isolates the most informative features for model predictions while maintaining high classification performance. We evaluated our proposed approach on three datasets—CNMC, ISBI2016, and BreaKHis—demonstrating competitive accuracy and producing clear interpretations. This makes IBATree particularly suitable for clinical applications, where understanding the rationale behind predictions is crucial. Our results show that IBATree provides reliable predictions and valuable insights into feature importance, paving the way for its application in various biomedical domains.

The challenge of interpretability remains a significant barrier to adopting deep neural networks in healthcare domains. Although tree regularization aims to align a deep neural network’s decisions with a single axis-aligned decision tree, however, relying on one tree for all inputs often leads to sub-optimal performance and interoperability. To address this limitation, we propose an enhanced tree regularization method that integrates a post-hoc visual explainable model such as Grad-CAM. This approach guides the deep model to be well-approximated by decision trees tailored to the salient regions identified by Grad-CAM in the input space. We rigorously validate the effectiveness of this framework on two cancer cell datasets: CNMC, which focuses on acute lymphoblastic leukemia cells, and ISBI2016, which comprises benign and malignant skin lesions. The results demonstrate that the proposed method delivers simpler and more interpretable explanations without compromising accuracy, thereby advancing the interpretability of deep learning models in critical healthcare applications.

Cooperative co-evolution (CC) is a promising direction in solving large-scale multiobjective optimization problems (LMOPs). However, most existing methods of grouping decision variables face some difficulties when searching in the huge search space. Specifically, the methods of grouping decision variables can be classified into two types, i.e., high-consumption grouping methods and non-consumption grouping methods. On the one hand, the former ones divide the decision variables into different groups based on the correlation analysis between variables, which consume much evaluation. This way may lead to premature convergence within limited computational resources. On the other hand, the later ones allocate the decision variables into sub-groups based on some metrics, e.g., order and size, which consume no evaluation while may cause the search fall into local optima. To alleviate the above issues, this paper proposes a CC-based algorithm with a variable-importance grouping (VIG) method, called VICCA. Firstly, the decision variables are classified into several subgroups according to their importance quantified by a meta-gene construction method. Secondly, a CC strategy is designed to simultaneously optimize all subgroups of decision variables formed by VIG using the differential evolution operator, which aims to accelerate the convergence speed. Thirdly, a global evolutionary strategy is proposed to optimize original decision variable space by the competitive swarm optimizer, aiming to maintain the diversity. Finally, the experiments demonstrate that our proposed VICCA has the significant advantage in solving LMOPs when compared with state-of-the-art evolutionary algorithms.

Surrogate-assisted evolutionary algorithms (SAEAs) have demonstrated promising optimization performance in addressing expensive dynamic optimization problems or expensive multimodal optimization problems. However, none of existing SAEAs are designed specifically for tackling expensive dynamic multimodal optimization problems (EDMMOPs). Therefore, in this paper, a first SAEA for tackling EDMMOPs is proposed. First, a nearest density clustering is designed to divide the population into a number of subpopulations, enhancing the diversity of the population. Then, a surrogate-assisted evolutionary optimizer is developed to construct surrogate models for each subpopulation and evolve all solutions in subpopulations by means of the built surrogate models, accelerating the population's converge towards several optimal solutions rapidly. Finally, a transfer learning-based prediction is devised to generate initial samples for next environment by leveraging the stored training samples in the previous environments. To assess the performance of our proposed algorithm, a set of complex benchmark problems is adopted, and the experimental results confirm its superior performance over several competitive algorithms on most test cases.

By sharing model parameters instead of raw data to train machine models, Federated Learning (FL) can protect End equipment Workers (EWs)’ data privacy. However, due to energy constraints and selfishness, EWs may not be willing to participate or train slowly, which affects the performance of global FL model. To address these issues, we propose a three-stage Stackelberg game-based wireless powered FL framework to incentivize all players to participate in the system while ensuring the successful completion of FL tasks. Specifically, Base Station (BS) publishes the FL task and wants to obtain a better FL model at a lower cost. EWs train local FL models, and want to get more payment with less energy consumption. When EWs train and upload their local models, Charging Service Provider (CSP) transmits energy to them via Wireless Power Transfer (WPT) while charging fees. In order to obtain the optimal strategy for all participants, we analyze the proposed game problem using the backward induction method. Meanwhile, we prove that the unique Stackelberg equilibrium and Nash equilibrium can be obtained, and we obtain the approximate optimal solution of BS using the subgradient method. Finally, extensive simulations are conducted to evaluate the performance of the proposed method in different scenarios. The results show that the proposed method improves the utility of three parties by an average of 19.09% - 51.86% compared with the benchmark methods.

Mobile Edge Caching (MEC) can potentially alleviate Internet transmission congestion by delivering content at the network edge. However, current MEC solutions suffer from low resource utilization efficiency and often fail to meet user Quality of Experience (QoE), primarily due to dynamic user requests and obsessive pursuit of direct caching hits. Given the prevalence of recommendation systems, users often lack precise requests when using recommendation-based applications like TikTok and Taobao, insted passively enjoying recommended content. In this paper, we introduce a recommendation-enabled MEC architecture to enhance resource utilization and QoE. We develop a recommendation-enabled soft caching model and formulate the optimization problem as maximizing joint system revenue. To address this, we propose an attention-assisted federated learning deep Q-network algorithm. We conduct the simulations by using the real-world MIND dataset. The results demonstrate that our proposed algorithm outperforms existing baselines, demonstrating its effectiveness in improving resource utilization and QoE.

Recent advances in the diffusion model mark a significant leap in AI-generated image technology while extending its application to the Internet of Things (IoT). However, deploying these models on resource-constrained edge devices presents considerable challenges, primarily due to their high computational energy demands and stringent quality requirements. In response to these challenges, we introduce a collaborative inference system tailored for green edge networks. First, we propose a multi-exit U-ViT model that achieves the balance between inference quality and processing speed by allowing adaptive selection of exit points during diffusion for efficient processing. Next, we develop a novel generative AI-assisted reinforcement learning algorithm that controls the exit selections and offloading decisions of the device to achieve maximum global gain. Furthermore, we design a novel policy network incorporating an attention-based state-embedded policy network to enhance the algorithm’s ability to perceive and make decisions about the state of the environment. Experimental results demonstrate that our system achieves energy-efficient inference while ensuring the quality of the generated content.

Explainable decision-making is critical for building trust in autonomous vehicles. We investigate the use of a pre-trained large language model (LLM) to derive comprehensible driving decisions from multi-modal time-series data captured by a monocular camera on an autonomous vehicle. Leveraging a graph-of-thought structure, the LLM learns policies that perform robustly while generating natural language rationales. We generate a novel multi-modal dataset with sequential images, scene labels, and driving actions. Results demonstrate our method produces human- understandable explanations for its driving choices, providing transparency. Our work indicates incorporating language-based reasoning enables accountable and transparent decision-making for self-driving cars, making LLM a potential solution for autonomous driving.

Computation offloading is widely used in vehicular edge computing (VEC) networks to satisfy the computational intensity and latency sensitivity requirements. However, many existing offloading algorithms do not comprehensively consider the dynamically changing characteristics of heterogeneous tasks within a roadside unit (RSU), resulting in tasks timeout and being dropped. In this paper, we design a competitive and cooperative computation offloading (C3O) model to reduce task execution latency. Specifically, when intensive heterogeneous tasks are generated, these vehicles jointly compete for the computing resource of a RSU, or they can also offload tasks to the task vehicle (TaV) with free computing resource. Meanwhile, We analyze the latency model of local execution and offloading to RSU or TaV execution and formulate a sequential task offloading decision problem, NP-hard. To address it, we propose a multi-agent reinforcement learning algorithm based on C3O (MARC3O) to intelligently determine the computation offloading policy for each vehicle according to the state of VEC networks. Simulation results demonstrate that the proposed algorithm can significantly reduce task execution latency and improve task completion rates compared with baseline schemes.

To address network congestion and data privacy concerns, federated learning (FL) that combines multiple clients and a parameter server has been widely used in mobile edge computing (MEC) networks to process the abundant data generated by mobile clients. However, the existing client sampling methods do not adequately consider the data heterogeneity and system heterogeneity. Parameter server selects inappropriate clients to participate in the FL training process. This inevitably leads to slower convergence of the global model and higher energy consumption. In this paper, we design a client sampling model with the goal of selecting suitable clients to improve the energy efficiency of FL in heterogeneous MEC networks. Then we propose an energy-efficient client sampling strategy by quantifying the communication capability, computation capability and data quality of clients. Based on the quantization results, clients are assigned with a corresponding sampled probability. Simulation results show that our proposed strategy can effectively accelerate the convergence of the global model and reduce the energy consumption compared with the baseline schemes.

The upcoming sixth-generation (6G) of ubiquitous connectivity communications systems is driven by the next-generation of Internet of Things (IoT) technology. Accordingly, the demand for spectrum resources is growing exponentially. Spectrum sensing, which dynamically explores spectrum holes, is expected to be crucial in the 6G era. In the meantime, Non-Orthogonal Multi-Access (NOMA), an efficient means of reusing resources, can enable multiple users to share the same frequency band stably. The combination of both technologies holds promise for more effective use of spectrum resources in future commu-nications. In this paper, we present a spectrum sensing method for the uplink communication scenario in NOMA with multi-user interference, which aims to make effective use of both static and dynamic gain on spectrum efficiency. Firstly, the sensing criterion and workflow are outlined. The closed-form solution for the sensing threshold configuration is derived thereafter. The simulation results demonstrate the feasibility of the proposed approach, which can increase the system throughput up to 19.7%, when compared to NOMA without spectrum sensing.

Convolutional Neural Networks and Attention-based Transformer have emerged as the preferred models for medical image processing. Recently, specific network architectures relying solely on multilayer perceptrons (MLPs) have gained popularity and demonstrated excellent results in various computer vision tasks. In particular, CycleMLP has demonstrated good performance in dense prediction tasks owing to its adaptability to image size and linear computational complexity. However, the basic operator of CycleMLP has a fixed sampling location for any feature map and samples very few target organs in medical images characterized by an extreme imbalance between foreground and background. Therefore, effectively extracting the features of target organs becomes challenging. In this paper, we propose a new MLP-like module, SlideMLP, by considering the sparsity of target organs in medical images. This module extracts a set of offsets from the input feature maps and utilizes these offsets to re-select the sampling points. This approach effectively enhances the sampling rate of target organs while retaining the advantages of CycleMLP. Additionally, we constructed a U-shaped network with a pure MLP using this module and assessed its robustness using two datasets with different modalities. Comparative results with state-of-the-art methods demonstrate that the method proposed in this paper can achieve a substantial Dice Similarity Coe cient (DSC) while utilizing fewer parameters.

The collaboration between clouds and edges unlocks the full potential of edge-cloud systems. Edge-cloud platform has brought about significant decentralization, heterogeneity, complexity, and instability. These characteristics have posed unprecedented challenges to the optimal scheduling problem in the edge-cloud system, including inaccurate decision-making and slow convergence. In this paper, we propose a curiosity-driven collaborative request scheduling scheme in edge-cloud systems, namely Cur-CoEdge. To tackle the challenge of inaccurate decision-making, we introduce a time-scale and decision-level interaction mechanism. This mechanism employs a small-large-time-scale scheduling learning framework, facilitating mutual learning between different decision levels. To address the challenge of slow convergence, we investigate the underlying reasons, such as the sparse reward-setting in reinforcement learning. In response, we develop a curiosity-driven collaborative exploration approach that fosters intrinsic curiosity in the cloud and simultaneously motivates dispatchers to explore the environment both individually and collectively. The effectiveness of this collaborative exploration is also supported by theoretical proof of convergence. Finally, we implement a prototype system on a network hardware system along with two real-world traces. Evaluations demonstrate significant improvements, with up to a 26% increase in time efficiency, a 40% rise in system throughput, and a 71% enhancement in convergence speed.

Vehicular Edge Computing (VEC) allows vehicles to offload their delay-sensitive tasks to nearby Road Side Units (RSUs) for processing, which improves network quality of service (QoS). However, the self-interested SDN controller is unwilling to ask RSUs to provide free computing resources for vehicles. At the same time, complicated dependencies between vehicular subtasks may cause non-ideal task delay and energy consumption. In order to solve these problems, this paper proposes a Stackelberg game-based Dependency-aware task Offloading and resource Pricing framework (SDOP). Specifically, we first model a vehicular edge network that partially offloads dependency-aware tasks. Then, we depict the interaction between the SDN controller and vehicles as a Stackelberg game, with the goal of maximizing the utility of both parties. Next, we present a Gradient Ascent Plus Genetic algorithm (GAPG) to solve the problem. Finally, numerous simulations are performed, and the results show that compared with other baseline schemes, the proposed GAPG can significantly improve the utility of both the SDN controller and vehicles under various scenarios.

Federated learning, as a distributed machine learning paradigm, offers promising solutions for vehicular edge computing (VEC) networks. However, federated learning in VEC with classification tasks still faces two key challenges: i) Delayed data labeling hampers supervised training; ii) Dynamic vehicle behavior complicates training scheduling and model uploads to edge servers. In this paper, we propose a semi-asynchronous federated learning algorithm for VEC. Specifically, it utilizes knowledge distillation to generate soft labels from raw data for supervised training, and estimates model training and uploading time through trajectory prediction. We further logically group vehicles based on the characteristics of their dynamic behavior. We then employ synchronous aggregation within groups and asynchronous aggregation between groups to optimize model performance while reducing latency. Finally, we conduct separate comparative experiments for all components, demonstrating that each component possesses unique advantages. Experiment results show that the proposed algorithm outperforms existing schemes in terms of accuracy and latency. The code is available at: https://github.com/dyxcode/Semi-Asynchronous-Federated-Learning.

This paper investigates the joint trajectory optimization and resource allocation problem in an UAV-Assisted NOMA-MEC System, aiming to minimize the system overhead. First, considering user mobility and Non-Orthogonal Multiple Access (NOMA) technology, we transform UAV trajectory optimization and resource allocation problem as a dynamic coverage location problem. Second, we design a Low-complexity Online Trajectory optimization and Resource allocation Scheme based on Lyapunov and convex optimization (LOTRS) with the goal of minimizing the system overhead. Simulation results show that compared with other benchmark schemes, the proposed LOTRS performs best in terms of system overhead in various scenarios.

This paper proposes a Stacklberg game-based Dependent task Offloading and resource Pricing framework (SDOP), where vehicles partially offload their dependent substaks to the SDN controller and pays corresponding fees. Firstly, we model the interaction between the SDN controller and vehicles as a Stackelberg game, where both parties wish to maximize their utility. Then, we employ the backward induction approach to analyze the investigated problem, and prove the existence and uniqueness of Nash and Stackelberg equilibrium. Next, we propose a Gradient Ascent Plus Genetic algorithm (GAPG) to solve the considered problem. Finally, extensive simulation results show that the proposed GAPG outperforms other baseline schemes under various scenarios.

This paper investigates dynamic model partitioning and resource allocation in split federated learning, aiming to maximize the utility of clients and the Central Server (CS). We first model the interactions between the CS and clients as a Stackelberg game, where the CS acts as the leader to set payment and allocate computation resources, while clients as followers to determine model partitioning strategies. Then, we transform the problem into a bi-level optimization and propose a Nash-Equilibrium-based Stackelberg Algorithm (NESA) to solve it. Finally, the experimental results indicate that a Stackelberg equilibrium exists between the CS and clients, and NESA achieves higher utility and improves accuracy and convergence speed.

Mobile edge computing (MEC) as a potential technology can offload tasks from user devices (UDs) to network edges to alleviate network congestion and reduce task execution delay. However, computation offloading faces two challenges: 1) Poor wireless channel quality causes high transmission delay; 2) Computing tasks may be obtained by eavesdroppers (Eves) during task offloading. Therefore, we consider deploying intel-ligent reflecting surface (IRS) in MEC networks to increase data transmission rate and ensure data transmission security. This paper investigates the issue of joint computation offloading and resource allocation in a multi-IRS assisted MEC network. Our goal is to minimize task execution delay. To address this problem, we propose a multi-agent deep deterministic policy gradient algorithm to determine the optimal offloading strategy for each UD. Simulation results show that the proposed algorithm can significantly reduce task execution delay and ensure data transmission security.

Mobile edge-cloud computing utilizes the computing resources of edge devices and cloud servers to execute complex deep neural networks (DNNs) for collaborative inference. However, many existing collaborative inference methods do not fully consider the limited resources of edge devices, resulting in high inference latency. In this paper, we design an integrated computational framework that combines model partition and compression to reduce inference latency. Specifically, we partition a DNN model at the middle layer and deploy the previous layer on the edge device and the subsequent layer on the cloud server respectively. We propose a collaborative dual-agent reinforcement learning algorithm called CPCDRL to determine partition point and compression ratios. It enables adaptive adjustments of compression ratios based on various partition points, with the overarching goal of minimizing the inference latency across the entire DNN model. The proposed algorithm can significantly reduce computational latency while minimizing accuracy loss compared to the baseline schemes.

Computation offloading, resource allocation, and endurance issues in unmanned aerial vehicle (UAV)-aided mobile edge computing (MEC) networks have always been a research focus. UAV-aided MEC allows mobile users (MUs)' tasks to be offloaded to drones for processing in special scenarios, such as natural disasters or military attacks. However, as the number and size of offloaded tasks increase, a single UAV is difficult to meet all computational demands, result in the decline of QoS. To address this issue, this paper presents a collaborative computation offloading scheme where multiple UAVs can cooperate to handle massive tasks. Firstly, considering that battery-limited UAVs cannot complete all tasks and sustain flight without charging, we incorporate charging stations (CS) into multi-UAV-assisted MEC networks. Subsequently, we design a price-based incentive mechanism to maximize the total revenue obtained from UAVs' collaborative computation. Then, we formulate the joint optimization problem of computation offloading, resource allocation and charging scheduling as a Markov Decision Process (MDP), and propose a Twin Delayed Deep Deterministic policy gradient (TD3) algorithm to find optimal strategies. Finally, extensive simulations demonstrate that the proposed TD3 algorithm outperforms other benchmark methods, achieving the highest overall system utility under different scenarios.

Summary By providing distributed and ultra‐low‐latency communication between industrial devices and resource components, the Industrial Internet of Things (IIoT) is at the forefront of a new trend. Such a distributed paradigm is viewed as a collection of autonomous computing resources utilized by multiple heterogeneous devices to achieve higher‐quality interconnection and data exchange. However, stringent requirements of exceptional service and fairness guarantees pose many formidable challenges. To this end, this study investigates the aforementioned concerns in an integrated manner and further proposes a fairness‐aware task offloading method, called FOIMAM. Specifically, the ‐norm is introduced to accommodate the Pareto plane under the non‐Euclidean geometry framework while the evaluation and elimination of low‐quality solutions are completed based on survival scores. Particularly, the fairness requirements are formulated as a multi‐constraint problem and resolved using weighted max‐min fairness. Eventually, numerical results indicate that the proposed method brings substantial improvement in both service efficiency and fairness guarantees.

The rapid advancement and wide application of the Internet of Things technology (IoT) have brought unprecedented convenience to people’s production and life. A great number of devices are connected to the IoT network to provide various services for people, which also makes the IoT more vulnerable to various cyber-attacks. This paper designs a novel IoT web attack detection architecture, which combines the powerful knowledge expression ability and high interpretability of symbolic artificial intelligence (AI) with the adaptive learning ability of connectionist AI to form a closed loop of knowledge embedding and extraction, effectively improve the detection ability of web attacks. The architecture solves the “black box” feature of deep learning models and can obtain knowledge from the trained detection model and add it to the training process of the new model to improve detection capabilities. It also uses the advantages of blockchain technology to realize intelligent sharing between different detection systems, solve the problem of difficult detection model updates and training data acquisition “bottlenecks”. To better detect web attacks, we propose a semi-supervised learning method based on an interpretable convolutional neural network (CNN) to reduce misjudgments during self-training and improve detection accuracy. Additionally, we propose a new feature method to extract the features of web logs in IoT devices, which can help the system to detect web attacks in IoT more quickly and accurately. Simulation results on two different datasets show that the proposed architecture and method can effectively detect web attacks in IoT and reduce the false positive rate.

As an important part of Internet of Things (IoT), the Internet of Vehicles (IoV) has been widely used in traffic intersection control, automatic driving, intelligent navigation, etc. However, due to the dynamic topology and high mobility, IoV faces the challenge of frequent disconnections, which will lead to deterioration in the performance of data dissemination. Motivated by the above, air-to-ground (A2G) integrated IoV is used to bridge the communication gaps between terrestrial vehicles to achieve efficient information transmissions. This paper investigates the application of low altitude platform stations (LAPSs) and reconfigurable intelligent surface (RIS) in A2G integrated IoV, where multiple relaying LAPSs equipped with RISs are adopted to improve the spatial multiplexing gain and create the smart radio environment. To make full use of the advantages of LAPS-and-RIS enhanced transmissions, we formulate a weighted sum rate (WSR) maximization problem by jointly considering the location, power, and phase shift. To tackle this challenging non-convex problem, we design an iterative optimization scheme, where three optimization variables are processed in turn. Simulation results demonstrate that the proposed WSR maximization scheme can significantly improve the communication performance in comparison with other state-of-the-art schemes and the baseline scheme.

The rapid expansion of digital infrastructure has led to increased security threats. Deep Learning (DL) algorithms have emerged as potent tools for detecting cyberattacks in IoT ecosystems. However, challenges like imbalanced class distribution and vast data volumes remain, resulting in inaccurate classification outcomes and inflated accuracy rates. Additionally, memory-constrained IoT devices often find it challenging to accommodate robust DL methods. This paper introduces an innovative approach that addresses class imbalance and the challenges posed by high-dimensional data in intrusion detection systems. Our framework encompasses: (1) a conditional Generative Adversarial Network (cGAN) for minority class upsampling, (2) an auxiliary autoencoder for dimensionality reduction, and (3) an unique hybrid uncertainty-based transformer architecture for efficient network traffic classification. We undertake extensive experiments on two specific datasets: BoT-IoT and CICIDS2018, affirming the efficacy of our hybrid DL-based approach. Initially, we assess the quality of synthetic data produced by various techniques, comparing their Principal Component Analysis (PCA) plots to authentic data. Our GAN-generated data closely mirror the PCA of real data, denoting a high similarity in distribution. Subsequently, we benchmark our auxiliary autoencoder against established dimensionality reduction techniques. The results indicate that our auxiliary autoencoder has significantly lower noise levels than contemporary methods, reducing the data storage volume of network traffic by 93.02% on BoT-IoT and 96.25% on CICIDS2018 datasets. Lastly, we illustrate the enhanced capability of our uncertainty-based attention model in detecting cyberattacks across both datasets.

Computation offloading involves transmitting compute-intensive tasks from mobile users (MUs) to edge environments. This compensates for the limitations of terminal devices in computing performance and resource storage capabilities. However, with the growing demand for offloading compute-intensive tasks, the burden on edge server networks has intensified. On the other hand, the response time of application has increased, leading to a decline in user experience. Therefore, selecting a reliability metric caused by congestion becomes an important issue for analyzing the quantitative characteristics of edge networks. The current research primarily focuses on the precise validation offloading task results. Typically, methods like task redistribution and third-party assistance are employed to ensure task reliability. However, these measures lead to increased time and energy consumption. In this paper, we propose a more versatile reliability metric based on the probability distribution of average waiting time in a multi-queue model. Additionally, to incentive MUs to offload more tasks and enhance the economic utility of edge server providers (ESPs), we employ a Stackelberg game to model the dynamic interaction between ESPs and MUs. Finally, we utilize the alternating direction method of multipliers (ADMM) algorithm to derive the optimal strategies for ESPs and MUs. Simulation results demonstrate that our proposed approach surpasses the baselines in terms of reliability indicator. Moreover, it achieves faster convergence and decision-making in comparison to conventional heuristic methods.

Effective data management schemes have always been the major demand in universal industrial Internet of Things (IoT) systems, especially in resource-constrained scenarios. In realistic wastewater treatment process (WTP), only limited monitoring data resource can be available due to some digital constraint. Aiming at this practical issue, this work explores utilization of deep neural network to deal with such practical issue in the objective situation. Therefore, a deep learning-based data management scheme for intelligent control of WTP under resource-constrained IoT systems, is proposed in this paper. Firstly, a specific data encoding and preprocessing approach is developed for the objective business scenario. Then, the detailed workflow of a deep neural network structure is applied to predict key intermediate parameters which can further guide control decision. Finally, a comprehensive series of experiments are conducted on a real-world dataset which covers a range of one year. Both efficiency and robustness of the proposal are tested by introducing several performance metrics. The results show that it can have proper prediction effect in such resource-constrained environment, which can facilitate following intelligent control operations.

With the rapid development of autonomous driving and edge computing, vehicular edge computing (VEC) has become an emerging paradigm that allows vehicles with abundant computational resources to work as edge nodes. By introducing vehicles as infrastructures, VEC has the potential to improve users’ quality of experience and decrease operator’s deployment expenditure, especially for hot spots. In this article, a novel VEC-based resource reservation framework is designed to handle the time-varying computation requests. To articulate realistic scenarios, the online durations of provider vehicles (PVs) are assumed to be different. Besides, the PVs will not always be online to wait for the reservation assignment for the limited revenue, i.e., the PVs are dynamic and the computational resource reservation points (CRRPs) are static. In this way, dynamic matching is leveraged to model the interaction between the PVs and CRRPs. To prevent the CRRPs from manipulating their preferences for better partners, a strategy-proof and stable resource reservation algorithm is proposed to ensure all CRRPs are truthful during the resource reservation procedure. Finally, numerical simulation results are presented to validate the proofness, truthfulness, and performance of our proposed resource reservation algorithm.

Recent research studies have made significant progress in acoustic-based gesture recognition. However, existing methods lack the capability to expand to customized gestures and adapt to different practical environments. We propose a highly scalable gesture recognition system called EchoGest which integrates a well-designed feature-wise transformation layer into prototypical network framework, and accomplishes unseen gesture recognition with a device’s built-in speaker and microphone. Our key insight involves gauging the similarity between query sample representations and class prototypes in the embedding space, and thus enabling the scalability to unseen gestures. Meanwhile, we introduce a feature transformation layer to linearly adjust feature maps and propose an efficient two-stage training strategy to obtain regularized parameters for this layer. Specifically, this layer employs affine transformation to enhance intermediate feature activations and yield more diverse feature distributions for cross-domain recognition, and it improves recognition accuracy by 10% in 1-shot cases. We train the system with a collected a letter gestures (i.e., writing ’A’ to ’Z’) dataset and test it on a digit gestures (i.e., writing ’0’ to ’9’) dataset with 10 volunteers. The results show that EchoGest can recognize unseen digit gestures with an accuracy of 93.7% in 2-shot cases, and 93.2% in the leave-one-user-out testing setting. We also explore a semi-supervised clustering approach in which each user’s data can be used to update his or her prototypes for personalized customization. The comprehensive experiments also verify that EchoGest remain good performance across various environments, age groups, and different devices.

The power inspection is an important application of UAV-assisted power internet of video things (IoVT) for maintaining the safety of the power system. Due to the limitations of distance and angle, the resolution of the images captured by UAV is low, which seriously impacts the effects of small insulator defects detection. To address this problem, we propose a small-size defects detection method based on multi-scale feature interaction transformer for UAV-assisted Power IoVT. For the algorithm, we design a super-resolution reconstruction-assisted small object detection algorithm, the super-resolution module generates high-resolution images with the requirements of object detection function, which greatly improves the small object detection performance. Moreover, we design multi-scale feature interaction transformer network (MFITN), compared with the traditional non-local attention mechanism, the network structure can capture dependencies in multi-scales features, furthermore, the advantage assist the super-resolution module to generate more realistic image information to further improve small object detection. In addition, we propose a distributed model deployment strategy to deploy our high computational complexity algorithm in the edge side of the IoVT system, which can drive the overall algorithm to perform low-latency edge computation by relying only on the limited computing power devices. Experiments demonstrate that our method has better small object detection performance (mAP=81.3%, FPS=49.7), the super-resolution reconstruction is able to recover more realistic detail information, the distributed computing method can reduce the response latency by 33.4%-87.2%, which all contribute UAV-assisted Power IoVT system to realize accurate and fast power insulator defects detection.

With the significant increase in the number of motor vehicles, road-related issues such as traffic congestion and accidents have also escalated. The development of an accurate and efficient traffic flow forecasting model is essential for helping car owners plan their journeys. Despite advancements in forecasting models, there are three remaining issues: (i) failing to effectively use cyclical data; (ii) failing to adequately capture spatial dependencies; and (iii) high time complexity and memory usage. To tackle the aforementioned challenges, we present a novel Spatial-Temporal Graph Attention Gated Recurrent Transformer Network (STGAGRTN) for traffic flow forecasting. Specifically, the use of a Spatial Transformer module allows for the extraction of dynamic spatial dependencies among individual nodes, going beyond the limitation of only considering neighboring nodes. Subsequently, we propose a Temporal Transformer to extract periodic information from traffic data and capture long-term dependencies. Additionally, we utilize two additional classical techniques to complement the aforementioned modules for extracting characteristics. By incorporating comprehensive spatial-temporal characteristics into our model, we can accurately predict multiple nodes simultaneously. Finally, we have successfully optimized the computational complexity of the Transformer module from O(n2) to O(nlogn). Our model has undergone extensive testing on four authentic datasets, providing compelling evidence of its superior predictive capabilities.

Video surveillance as an important function of internet of video things (IoVT) system has been widely used in coal mine monitoring for coal mine safety with excellent results, however, there are still many shortcomings: 1) Existing coal mine IoVT systems have limited detection accuracy for small-sized objects; 2) Coal mine video surveillance systems generally adopt centralized cloud computing, transmission of massive data causes high latency, which seriously affects the response speed of object detection function; 3) The concept drift caused by the data stream seriously affect the detection effect of the offline algorithm. To address the above issues, we propose a small object detection method based federated intelligence to assist coal mine IoVT for object detection. First, we design a lightweight neural network Rep-ShuffleNet to improve YOLOv8, the state-of-the-art YOLO algorithm, to maintain high detection accuracy while dramatically increasing the inference speed, and with the advantage of lightweight, it can be deployed to embedded devices for low-latency edge computing; Moreover, we design a federated learning-based MLC-FL algorithm for local algorithms’ automatic and efficient optimization by asynchronous communication and data interaction reduction strategy. The experimental results show that with the assistance of federated intelligence model optimization strategies, the lightweight YOLOv8 has excellent detection performance (mAP: 94.6%, APsmall: 86.7%, FPS: 21.6), thus to assist coal mine IoVT to realize accurate and real-time underground small object detection.

The growing utilization of unmanned aerial vehicles (UAVs) across diverse industries has led to increased interest in UAV-assisted data acquisition for the Internet of Things (IoT). The security of image data collected by UAVs during transmission within the IoT has become a critical concern. This article focuses on the security challenges associated with UAV-assisted image data collection in the IoT and presents a dedicated framework designed to enhance the security of this process. Given the high-resolution nature of UAV-captured images, traditional encryption methods face difficulties in directly and effectively encrypting such data. To address this issue, this article introduces an efficient chaotic image encryption algorithm integrated into the proposed protection framework. The algorithm features a novel 1-D chaotic system for generating effective chaotic sequences. For the scrambling phase, a chaotic four-spiral transformation method is employed, and the diffusion process utilizes the Fibonacci matrix. This strategic approach aims to minimize pixel correlation within the image, thereby bolstering the overall security of the encryption process. Experimental validation conducted on authentic UAV image data sets demonstrates the superior, practical, secure, and efficient characteristics of the proposed algorithm.

Vehicular edge computing (VEC) is an effective paradigm in Internet of Vehicles (IoV), which allows vehicles to offload delay-sensitive tasks to nearby road side units (RSUs) for processing, thereby enhancing the Quality of Service (QoS). However, the software defined networking (SDN) controller that manages RSUs often have individual rationality and selfishness, and thus is unwilling to provide free computation resources to vehicles. Meanwhile, the dependency relationships among vehicular subtasks are not well investigated, resulting in unsatisfactory task latency and energy consumption. In order to effectively motivate the selfish SDN controller to participate in computation offloading and comprehensively consider all dependency situations among multiple subtasks, this article proposes a Stackelberg game-based dependency-aware task offloading and resource pricing framework (SDOP). Specifically, we first model the interaction between the SDN controller and vehicles as a Stackelberg game, where both parties wish to maximize their utility. Then, we employ the backward induction approach to analyze the investigated problem, and prove the existence and uniqueness of Nash and Stackelberg equilibrium. Next, we propose a gradient ascent plus genetic algorithm (GAPG) to solve the considered problem. Finally, extensive simulation results show that the proposed GAPG can significantly improve the utility of both the SDN controller and vehicles under various scenarios, when compared with other baseline schemes.

With the increasing pervasiveness of smart earphones, it is appealing to propose more unobtrusive and convenient wearable authentication methods. Researchers have designed earphone-based authentication systems which utilize high-frequency audio signals to scan ear canal structure. Nevertheless, they possess shortcomings of low unobtrusiveness and robustness. In this article, we put forward an earphone-based passive authentication system which makes use of physiological and behavioral acoustic signals caused by a user’s natural actions, including putting on earphones and inner organs’ activities, respectively. By introducing attention mechanism into the network design, our method adaptively weighs two channel signals, and extracts stable fingerprints for different people, which relieves model retraining for unseen users and improves its scalability. We have built a real-time prototype called EarPrint by designing the earphones and a mobile application, and conducted comprehensive experiments under diverse settings. Experimental results demonstrate that EarPrint has low false acceptance rate (FAR) and equal error rate (EER) less than 1% and 5% in most cases, respectively.

Human-centric communication metaverse relies on the convergent integration of multiple existing technologies such as 5G and beyond networks, virtual reality, augmented reality, and digital twins, and thus their security vulnerabilities and vulnerability to interference attacks may also be inherited by the metaverse. In particular, existing security policies may be inefficient for communication interference problems encountered in multi-device collaborative computing in a metaverse 5G environment and lack adaptability to metaverse applications. In this paper, we propose a novel intelligent game anti-interference collaborative computing model that accurately describes the interference relationships among source devices, cooperating devices, and interferers in metaverse collaborative computing. We model the offensive and defensive confrontation between multiple metaverse devices as a Stackelberg game, where the source device is the leader, the collaborative computing device acts as the sub-leader, adjusts its antijamming strategy according to the source device’s strategy to improve the source device’s communication anti-jamming performance, and the jammer acts as the follower. We design an intelligent Stackelberg Game-theoretic Policy-based Learning (SGPL) algorithm for jamming resistance in metaverses over 5G and Beyond Networks, where the leaders (co-computing devices) update their training parameters using the total derivatives of the objective function, while the followers (i.e., jammers) update their training parameters using an independent gradient dynamics strategy. Loops are eased and convergence is accelerated by introducing differential dynamics into the leader training network to reflect the interaction structure of the critic and actor network layers. Finally, numerical results demonstrate the effectiveness of the proposed SGPL algorithm in metaverse anti-jamming countermeasures. The proposed SGPL algorithm has the potential to be generalized to other metaverse applications with multi-user attack and defense characteristics.

Low Earth Orbit (LEO) satellites have emerged as crucial enablers of direct connections with remote terrestrial terminals. However, energy limitations and insufficient antenna capabilities at the terminals often hamper these connections, resulting in inefficient communications and frequent ping-pong handovers. This paper proposes a Distributed Collaborative Beamforming (DCB)-based uplink communication paradigm for enabling ground-space direct communications. Specifically, DCB treats the terminals that are unable to establish efficient direct connections with the LEO satellites as distributed antennas, forming a virtual antenna array to enhance the terminal-to-satellite uplink achievable rates and durations. However, such systems need multiple trade-off policies that jointly balance the terminal-satellite uplink achievable rate, energy consumption of terminals, and satellite switching frequency to satisfy the scenario requirement changes. Thus, we formulate a long-term multi-objective optimization problem to optimize these goals simultaneously. To address availability in different terminal cluster scales, we reformulate this problem into an action space-reduced and universal Multi-Objective Markov Decision Process (MOMDP). Then, we propose an Evolutionary Multi-Objective Deep Reinforcement Learning (EMODRL) algorithm to obtain multiple policies, in which the low-value actions are masked to speed up the training process. Simulation results show that DCB enables terminals that cannot reach the uplink achievable rate threshold to achieve efficient direct uplink transmission. Moreover, the proposed algorithm outmatches various baselines and saves 30% handover frequency with a similar uplink achievable rate compared with the rate greedy method, which thus reveals that the proposed method is an effective solution for enabling direct ground-space communications.

This paper proposes an active aerial reconfigurable intelligent surface (ARIS) assisted secure communication framework by integrating sensing and positioning against a mobile eavesdropper. In the proposed scheme, the base station (BS) beamforms the private information to the legitimate user and jams the eavesdropper with artificial noise (AN), while reconfiguring the phases and amplitudes of the passive signal by the active ARIS for promoting secure communications. To acquire the channel state information of the time-vary wiretap channel, the BS tracks the position of the eavesdropper by exploiting the reflected AN. Based on the tracked position of the eavesdropper in the previous time slot, we propose a secure communication scheme that aims to maximize the secrecy rate in the current time slot. This scheme is assisted by the ARIS through jointly optimizing the passive beamforming of the privacy information and AN, the reflection matrix of the ARIS, and the position of the ARIS. In the case of this non-convex quandary with highly coupled variables, we opt to disassemble it into three constituent subproblems and design an alternating optimization framework, where the optimal power beamforming at the BS is derived using a successive convex approximation method and semi-positive definite relaxation technique, the reconfigurable coefficient of the ARIS is optimized using the majorization-minimization algorithm, and the optimal position of the ARIS using the three-dimensional network is obtained by the deep deterministic policy gradient algorithm. Simulation results demonstrate the superior performance of the proposed scheme in the context of the secrecy rate when compared with benchmark schemes. By adopting the active beamforming and positioning technique, the secrecy rate can be increased by 38.3% and 10.8%, respectively.

Smartphones are widely used as portable data collectors for wearable and healthcare sensors that can passively collect data streams related to the environment, health status, and behaviors. Recent research shows that the collected data can be used to monitor not only the physical states but also the mental health of individuals. However, extracting the features of digital phenotypes that characterize major depressive disorder (MDD) is technically challenging and may raise significant privacy concerns. Addressing such challenges has become the focus of many researchers. This article provides a comprehensive analysis of several key issues related to ubiquitous sensing to aid in detecting MDD. Specifically, this article analyzes existing methodologies and feature extraction algorithms used to detect possible MDD through digital phenotyping from smartphone data. In particular, five types of features are summarized and explained, namely, location, movement, rhythm, sleep, and social and device usage. Finally, related limitations and challenges are discussed to provide paths for further research and engineering.

The emergence of next-generation latency-critical applications places strict requirements on network latency and stability. Edge cloud, an instantiated paradigm for edge computing, is gaining more and more attention due to its benefits of low latency. In this work, we make an in-depth investigation into the network QoS, especially end-to-end latency, at both spatial and temporal dimensions on a nationwide edge computing platform. Through the measurements, we collect a multi-variable large-scale real-world dataset on latency. We then quantify how the spatial-temporal factors affect the end-to-end latency, and verify the predictability of end-to-end latency. The results reveal the limitation of centralized clouds and illustrate how could edge clouds provide low and stable latency. Our results also point out that existing edge clouds merely increase the density of servers and ignore spatial-temporal factors, so they still suffer from high latency and fluctuations. Based on a quantified latency impact factor, we have proposed several optimization strategies for edge cloud latency and validated their effectiveness. We also propose a robust prototype edge cloud model based on lessons we learn from the measurement and evaluate its performance in the production environment. Evaluation result shows that edge clouds achieve 84.1% latency reduction with 0.5 ms latency fluctuation and 73.3% QoS improvement compared with the centralized clouds.

User-centric clustering is a valid solution to enhance the coverage and throughput for future mobile communication networks. However, the size of clusters, the location of nodes, and the number of cooperating nodes within the cluster can all have an impact on the data rate of the typical user. In this paper, the user-centric clustering with limited cooperation (LC) in downlink cell-free (CF) architecture is considered, and the effect of composite channels and intra-cluster cooperation on the data rate of the typical user is analyzed from a theoretical derivation level. Specifically, the user classification, the distributions of distances between the serving nodes, and the average data rates of each type of user are given, respectively. The approximate expressions of the Laplace transform (LT) of interfering power for different types of users are obtained with the Gauss-Hermitian integral approximation, and the long-term average data rate of the typical user is derived. Finally, Monte Carlo simulations are executed to verify the accuracy of the theory. The results show that shadowing fading should not be ignored for accurately evaluating user performance, and it is particularly important to reasonably select the radius of the cluster and the cooperation threshold that controls whether the access points cooperate or not.

Visual tracking is an important research topic in the field of computer vision. The current Siamese tracker based on the region proposal network (SiamRPN) has achieved promising tracking results in terms of efficiency and performance. However, through our empirical study, we have observed that deep features learned by SiamRPN are of substandard quality, as the salient regions within the deep features fail to correspond accurately with meaningful objects. To address this limitation, we propose an approach to enhance the quality of the learned deep features through the incorporation of an attention mechanism. Attention mechanisms have been shown to be effective in distinguishing similar objects, as they suppress background objects while highlighting target information that is most relevant. As a result, a new tracking method with channel and spatial attention termed SiamATTRPN is explored. To verify the effectiveness of SiamATTRPN, experiments on benchmark datasets demonstrate that our proposed tracker outperforms the baseline tracker significantly.

To broaden domain knowledge and enable advanced analytics, machine learning (ML) algorithms increasingly utilize comprehensive datasets across diverse sectors. However, these disparate datasets held by various stakeholders raise concerns over data heterogeneity, privacy, and security. Decentralized ML research aims to protect data privacy and integrate knowledge bases, especially knowledge graphs, to address data heterogeneity challenges. Yet, the question of how to foster trustworthy collaborations in decentralized ML ecosystems remains underexplored. This study pioneers two innovative socio-economic mechanisms designed to ensure dependable collaborations with socio-ethical integrity within a decentralized knowledge inference framework, enabling participants to share knowledge while maintaining data privacy and ethical standards. We employ an evolutionary game theory model to analyze the dynamic interactions between requestors and workers, focusing on achieving a stable equilibrium through theoretical and numerical evaluations. Furthermore, we explore how various critical factors, such as incentive schemes and the accuracy of identifying malicious workers, influence the system's equilibrium, providing insights into optimizing collaborative efforts in decentralized ML ecosystems.

Recent multiobject tracking (MOT) methods usually use very deep neural networks to achieve competitive accuracy, which inevitably results in degraded inference speed. To strike a better balance between tracking accuracy and speed, in this work, we propose to compress the MOT model via knowledge distillation (KD), enabling the more lightweight student model to obtain similar performance as the teacher model. Nonetheless, despite KD has been well studied for simpler tasks such as image classification, the complexity of MOT poses new challenges because the MOT model is more sensitive to foreground information than the classification model. To deal with that, we first propose attention-guided feature distillation, which focuses the student model on the crucial region (foreground and the region with strong discrepancy against itself) of the teacher’s feature map. Moreover, we propose foreground mask, which leverages the knowledge from the teacher model to filter out the low-quality soft labels from the background, thereby reducing their negative effects for distillation. Evaluations on several benchmarks demonstrate that the proposed KD method can make the student network achieve leading performance, meanwhile running faster than the teacher network 20.0%–27.4% and reducing the parameters 28.5%–87.1%. To the best of our knowledge, this is the first work to compress the MOT model via KD.

In unsupervised domain adaptation (UDA), a classifier is applied to the target domain without or with limited labels, when the target domain has no or few labels. Recently, inspired by their capabilities of long-distance feature dependencies, vision transformer (ViT)-based methods have been used in UDA, however, they ignore the fact that ViT lacks strength in extracting local feature details. To handle the above problems, the purpose of this article is to demonstrate how to take advantage of both convolutional operations and transformer mechanisms for adversarial UDA by using a hybrid network structure called transformer fused convolution (TFC). TFC integrates local features with global features to boost the representation capacity for UDA which can enhance the discrimination between foreground and background. Moreover, to improve the robustness of the TFC, we leverage an uncertainty penalty loss to make incorrect classes have consistently lower scores. Extensive experiments validate the significant performance gains compared to conditional adversarial domain adaptation (CDAN) on all five datasets including DomainNet ($\uparrow ~8.5$%), VisDA-2017 ($\uparrow ~14.9$%), Office-Home ($\uparrow ~18.9$%), Office-31 ($\uparrow ~11.5$%), and ImageCLEF-DA ($\uparrow ~5.5$%).

Multidocument aspect-based summarization (AspSumm) aims to generate focused summaries based on the target aspects from a cluster of relevant documents. Generating such summaries can better satisfy readers’ specific points of interest, as readers may have different concerns about the same articles. However, previous methods usually generate aspect-based summaries based on the given aspects without using the relationship among aspects to assist in the summarization. In this work, we propose a two-stage general framework for multidocument AspSumm. The model first discovers the latent relationship among aspects and then uses relevant sentences selected by aspect discovery to generate abstractive summaries. We exploit latent dependencies among aspects using a tag mask training (TMT) strategy, which increases the interpretability of the model. In addition to improvements in summarization over aspect-based strong baselines, experimental results show that our proposed model can accurately discover multidomain aspects on the WikiAsp dataset.

Human gait refers to a daily motion that represents not only mobility but can also be used to identify the walker by either human observers or computers. Recent studies reveal that gait even conveys information about the walker’s emotion. Individuals in different emotion states may show different gait patterns. The mapping between various emotions and gait patterns provides a new source for automated emotion recognition. Compared to traditional emotion detection biometrics, such as facial expression, speech, and physiological parameters, gait is remotely observable, more difficult to imitate, and requires less cooperation from the subject. These advantages make gait a promising source for emotion detection. This article reviews current research on gait-based emotion detection, particularly on how gait parameters can be affected by different emotion states and how the emotion states can be recognized through distinct gait patterns. We focus on the detailed methods and techniques applied in the whole process of emotion recognition: data collection, preprocessing, and classification. Finally, we discuss possible future developments of efficient and effective gait-based emotion recognition using state-of-the-art techniques in intelligent computation and big data.

In recent years, surrogate-assisted evolutionary algorithms (SAEAs) have been sufficiently studied for tackling computationally expensive multiobjective optimization problems (EMOPs), as they can quickly estimate the qualities of solutions by using surrogate models to substitute for expensive evaluations. However, most existing SAEAs only show promising performance for solving EMOPs with no more than 10 dimensions, and become less efficient for tackling EMOPs with higher dimensionality. Thus, this article proposes a new SAEA with a simplified helper task for tackling high-dimensional EMOPs. In each generation, one simplified task will be generated artificially by using random dimension reduction on the target task (i.e., the target EMOPs). Then, two surrogate models are trained for the helper task and the target task, respectively. Based on the trained surrogate models, evolutionary multitasking optimization is run to solve these two tasks so that the experiences of solving the helper task can be transferred to speed up the convergence of tackling the target task. Moreover, an effective model management strategy is designed to select new promising samples for training the surrogate models. When compared to five competitive SAEAs on four well-known benchmark suites, the experiments validate the advantages of the proposed algorithm on most test cases.

Intelligent detection techniques for online spamming have been a hot concern in academia. Although much technical progress has been achieved in recent years, two aspects of challenges are still confronted by scholars. For one thing, spamming activities are accompanied by multisource attributes, such as behaviors and semantics. For another, spamming is a cross-platform activity, where multiple platforms are exploited simultaneously to expand the influential reach. The above circumstances actually make spamming detection tend to become a fuzzy detection task. Existing works typically consider one-sided attribute and lack cross-platform multifeature fusion, which limiting the effectiveness of detection. To handle the current challenges, this article proposes a cross-field deep learning-based fuzzy spamming detection approach via the collaboration of behavior modeling and sentiment analysis. First of all, a cross-field deep learning-based technical framework is put forward to implement multisource feature fusion from mixed context. It first extracts multisource features from single fields and then integrates them into a hybrid-field feature space. In addition, three cross-field datasets based on real-world social network datasets are constructed, and utilized in the evaluation of our proposed approach. The findings demonstrate that our proposal improves the detection accuracy by about 7% to 12%, in comparison to five other baseline approaches.

Protein methylation is one of the most important reversible post-translational modifications (PTMs), playing a vital role in the regulation of gene expression. Protein methylation sites serve as biomarkers in cardiovascular and pulmonary diseases, influencing various aspects of normal cell biology and pathogenesis. Nonetheless, the majority of existing computational methods for predictingprotein methylation sites(PMSP) have been constructed based on protein sequences, with few methods leveraging the topological information of proteins. To address this issue, we propose an innovative framework for predicting Methylation Sites using Graphs (GraphMethySite) that employs graph convolution network in conjunction with Bayesian Optimization (BO) to automatically discover the graphical structure surrounding a candidate site and improve the predictive accuracy. In order to extract the most optimal subgraphs associated with methylation sites, we extend GraphMethySite by coupling it with a hybrid Bayesian optimization (together named GraphMethySite$^+$) to determine and visualize the topological relevance among amino-acid residues. We evaluated our framework on two extended protein methylation datasets, and empirical results demonstrate that it outperforms existing state-of-the-art methylation prediction methods.

Millimeter wave (mmWave) with abundant spectrum resources can realize high-rate communications in vehicular networks. However, the mobility of vehicles and the blocking effect of mmWave propagation bring new challenges to communication security. Cooperative communication is envisioned as a promising physical layer security (PLS) approach to enhance the secrecy performance, but it will induce extra energy consumption of vehicles. This paper proposes a deep recurrent reinforcement learning (DRRL)-based energy-efficient cooperative secure transmission scheme in mmWave vehicular networks, where eavesdropping vehicles attempt to intercept the multi-user downlink communications. We jointly design the mmWave beam allocation, the cooperative nodes selection, and the transmit power of vehicles. Specifically, the mmWave base station selects idle vehicles as relays to overcome the severe blocking attenuation of legitimate transmissions and controls the transmit power to reduce energy consumption. Moreover, to ensure secure transmission, a cooperative vehicle is selected to transmit jamming signals to the eavesdropping vehicles while the legitimate users are not disturbed. We conduct comprehensive interference analysis for both direct transmission and relay-aided transmission, and derive the theoretical expressions for the secrecy capacity. We then design the Dueling Double Deep Recurrent Q-Network (D3RQN) learning algorithm to maximize the total secrecy capacity subject to the energy consumption constraint. We set the energy consumption punishment mechanism to avoid relay vehicles consuming too much power for forwarding signals. We demonstrate that the proposed scheme can rapidly adapt to the highly dynamic vehicular networks and effectively improve secrecy performance while reducing the energy consumption of vehicles.

In the Internet of Things (IoT) employing centralized machine learning, security is a major concern due to the heterogeneity of end devices. Malicious devices could launch poisoning attacks to degrade machine learning models. Distributed machine learning (DML) with blockchain provides a potential solution. Once local weights are recorded on the blockchain, model aggregation with defensive schemes can be executed on smartphones to prevent attacks. However, blockchain with the proof-of-work (PoW) consensus mechanism wastes computing resources and adds latency to DML. Computing resources can be utilized more efficiently with proof-of-useful-work (uPoW), which secures transactions by solving relevant real-world problems. We propose a novel uPoW method to minimize per-round latency of DML. The uPoW mining process schedules DML instances among multi-access edge computing (MEC) servers by solving a multi-way number partitioning problem. Moreover, poisoning attacks on heterogeneous training data pose significant challenges to blockchain-based DML. To address this problem, we propose a novel aggregation protocol, named$\mathit{Corrected Krum}$, to counter such attacks and improve the convergence speed of DML. By leveraging the mean-field approximation method, training errors are corrected to reduce the negative impact of poisoning attacks. Simulation results show that our proposed blockchain approach can significantly speed up DML compared with benchmarks.

With the increasing popularity and demands for large language model applications on mobile devices, it is difficult for resource-limited mobile terminals to run large-model inference tasks efficiently. Traditional deep reinforcement learning (DRL) based approaches have been used to offload large language models (LLMs) inference tasks to servers. However, existing DRL solutions suffer from data inefficiency, insensitivity to latency requirements, and non-adaptability to task load variations, which will degrade the performance of LLMs. In this paper, we propose a novel approach based on active inference for LLMs inference task offloading and resource allocation in cloud-edge computing. Extensive simulation results show that our proposed method has superior performance over mainstream DRLs, improves in data utilization efficiency, and is more adaptable to changing task load scenarios.

The 5G networks have extensively promoted the growth of mobile users and novel applications, and with the skyrocketing user requests for a large amount of popular content, the consequent content delivery services (CDSs) have been bringing a heavy load to mobile service providers. As a key mission in intelligent networks management, understanding and predicting the distribution of CDSs benefits many tasks of modern network services such as resource provisioning and proactive content caching for content delivery networks. However, the revolutions in novel ubiquitous network architectures led by ultra-dense networks (UDNs) make the task extremely challenging. Specifically, conventional methods face the challenges of insufficient spatio precision, lacking generalizability, and complex multi-feature dependencies of user requests, making their effectiveness unreliable in CDSs prediction under 5G UDNs. In this article, we propose to adopt a series of encoding and sampling methods to model CDSs of known and unknown areas at a tailored fine-grained level. Moreover, we design a spatio-temporal-social multi-feature extraction framework for CDSs hotspots prediction, in which a novel edge-enhanced graph convolution block is proposed to encode dynamic CDSs networks based on the social relationships and the spatio features. Besides, we introduce the Long-Short Term Memory (LSTM) to further capture the temporal dependency. Extensive performance evaluations with real-world measurement data collected in two mobile content applications demonstrate the effectiveness of our proposed solution, which can improve the prediction area under the curve (AUC) by 40.5% compared to the state-of-the-art proposals at a spatio granularity of 76m, with up to 80% of the unknown areas.

Model partitioning is a promising technique for improving the efficiency of distributed inference by executing partial deep neural network (DNN) models on edge servers (ESs) or Internet-of-Things (IoT) devices. However, due to heterogeneous resources of ESs and IoT devices in mobile edge computing (MEC) networks, it is non-trivial to guarantee the DNN inference speed to satisfy specific delay constraints. Meanwhile, many existing DNN models have a deep and complex architecture with numerous DNN blocks, which leads to a huge search space for fine-grained model partitioning. To address these challenges, we investigate distributed DNN inference with fine-grained model partitioning, with collaborations between ESs and IoT devices. We formulate the problem and propose a multi-task learning based asynchronous advantage actor-critic approach to find a competitive model partitioning policy that reduces DNN inference delay. Specifically, we combine the shared layers of actor-network and critic-network via soft parameter sharing, and expand the output layer into multiple branches to determine the model partitioning policy for each DNN block individually. Experiment results demonstrate that the proposed approach outperforms state-of-the-art approaches by reducing total inference delay, edge inference delay and local inference delay by an average of 4.76%, 10.04% and 8.03% in the considered MEC networks.

Fabric metaverse employs intelligence fibers embedded with flexible sensors to unknowingly gather and transmit massive hypermodal data around humans to a deep neural network-based metaverse inference service (DMS) for continual and real-time analysis. Each DMS has one primary branch and multiple side branches that allow early termination of service with differential accuracy and energy consumption. However, the continual provisioning of compute-intensive DMS with varying requirements for service model, accuracy, delay, and reliability poses a challenge for edge servers characterized by restricted computing resources and intermittent green energy. In this paper, we focus on a continual individualized DMS provisioning problem in the fabric metaverse consisting of a side branch insertion subproblem and a server activation and service deployment subproblem, and formulate them as Integer linear Programming and Markov Decision Process, respectively. Then, we propose a green continual inference (GCI) system, where a pruner with provable approximation ratios trims superfluous branches of every model to the given number$K$to minimize total overflow accuracy between accuracy demands and reserved branches assigned to users. Based on this exit result, each DMS is further divided into several blocks with dependencies to exploit constrained resources of computing and energy in a fine-grained manner. Finally, a learning-based scheduler is merged into GCI to maximize request throughput while minimizing the activation number of edge servers on different demand scenarios, by adaptively activating suitable servers and deploying required blocks and their corresponding backups on selected servers. Theoretical analyses, simulations, and experiments demonstrate that the GCI is promising compared with baseline algorithms.

With the rapid development of edge intelligence cloud (EIC), mobile users are not satisfied with a single artificial intelligence inference service, but require multiple inference services with chain dependencies to process data. Each AI service chain (AISC) is provided as a series of interconnected virtual network functions (VNFs) on-demand deployed on edge servers. However, AISCs experience unpredictable failures and potential attacks in EIC, which may violate different inference requirements of mobile users for reliability, security, and accuracy. How to optimally deploy VNFs and BVNFs on trusted edge servers, and select secure links to form satisfactory AISCs, meanwhile throughput of receiving requests is maximized while deployment cost of computing resources used to create VNFs and BVNFs with different model sizes is minimized in real-time, is a challenging problem. In this paper, the problem is first formulated as an integer linear programming and proved to be NP-hard. Then, we consider the problem under two online backup scenarios: one is an on-site scenario where AISC requests from the mobile devices arrive one by one, and link securities between VNFs and corresponding BVNFs are ignored because they are always on the same edge server; another is an off-site scenario where a set of AISC requests are given, and VNFs and BVNFs are deployed on different servers. Finally, two online algorithms with provable competitive ratios are proposed to solve the above two problems in polynomial time. Theoretical analyses and experiments based on real network topologies demonstrate that our algorithms are promising compared to baseline algorithms.

Unmanned aerial vehicles (UAVs) are playing an increasingly important role in assisting fast-response post-disaster rescue due to their fast deployment, flexible mobility, and low cost. However, UAVs face the challenges of limited battery capacity and computing resources, which could shorten the expected flight endurance of UAVs and increase the rescue response delay during performing mission-critical tasks. To address these challenges, we first present a three-layer post-disaster rescue computing architecture by leveraging the aerial-terrestrial edge capabilities of mobile edge computing (MEC) and vehicle fog computing (VFC), which consists of a vehicle fog layer, a UAV client layer, and a UAV edge layer. Moreover, we formulate a joint task offloading and resource allocation optimization problem (JTRAOP) with the aim of maximizing the time-average system utility. Since the formulated JTRAOP is proved to be NP-hard, we propose an MEC-VFC-aided task offloading and resource allocation (MVTORA) approach, which consists of a game theoretic algorithm for task offloading decision, a convex optimization-based algorithm for MEC resource allocation, and an evolutionary computation-based hybrid algorithm for VFC resource allocation. Simulation results validate that the proposed approach can achieve superior system performance compared to alternative approaches, especially under heavy system workloads.

Recent developments in unmanned aerial vehicles (UAVs) and mobile edge computing (MEC) have provided users with flexible and resilient computing services. However, meeting the computation-intensive and delay-sensitive demands of users poses a significant challenge due to the limited resources of UAVs. To address this challenge, we consider a multi-UAV-assisted MEC system. Based on this system, we formulate a multi-objective optimization problem aiming at minimizing the total task completion delay, reducing the total UAV energy consumption, and maximizing the total number of offloaded tasks. Since the problem is a mixed-integer non-linear programming (MINLP) and NP-hard problem, we propose a joint task offloading, computation resource allocation, and UAV trajectory control (JTORATC) approach. The problem is split into three components to cope with the coupling of these decision variables, and then solved individually to obtain the corresponding decisions. Specifically, the sub-problem of task offloading is solved by using distributed splitting and threshold rounding methods, the sub-problem of computation resource allocation is solved by adopting the Karush-Kuhn-Tucker (KKT) method, and the sub-problem of UAV trajectory control is solved by employing the successive convex approximation (SCA) method. Simulation results show that the proposed JTORATC has superior performance compared with the other benchmark methods.

Unmanned aerial vehicles (UAVs) are playing a pivotal role in wireless networks due to their high mobility and on-demand deployment advantages. However, the UAV-enabled communications are susceptible to be wiretapped by eavesdroppers due to the strong line-of-sight (LoS) dominated air-ground channel. In this paper, we consider a UAV-enabled secure communication scenario, in which a group of UAVs form a UAV-enabled virtual antenna array (UVAA) to transmit information towards the remote base stations (BSs) via collaborative beamforming (CB), while multiple known and unknown eavesdroppers aiming to wiretap the information. Specifically, a secure communication multi-objective optimization problem (SCMOP) is formulated to achieve the maximization of the worst-case secrecy rate, the minimization of the maximum sidelobe level (SLL) as well as the minimization of the flight energy consumption of UAVs by obtaining optimal locations and excitation current weights concerning the UAVs as well as determining an optimal receiver BS that can achieve superior communication performance. To solve the formulated SCMOP which is demonstrated to be non-convex and NP-hard, an improved multi-objective salp swarm algorithm (IMSSA) with several specific operating factors is proposed. Simulations results demonstrate that the proposed IMSSA can deal with the formulated SCMOP effectively and outperforms other benchmark strategies. Moreover, the multi-hop relay is introduced to verify the reasonability of the UVAA system, and two benchmark schemes of the formulated SCMOP are introduced to demonstrate the necessity of the formulated SCMOP. In addition, the performance of the UVAA system under certain unexpected circumstances is estimated. Finally, experimental implementation is conducted by using a Raspberry Pi and the results demonstrate the practicality of the proposed CB-based secure communication approach in real-world scenarios.

The popularity of microservices in industry has sparked much attention in the research community. Despite significant progress in microservice deployment for resource-intensive services and applications at the network edge, the intricate dependencies among microservices are often overlooked, and some studies underestimate the importance of system context extraction in deployment strategies. This paper addresses these issues by formulating the microservice deployment problem as a max-min problem, considering system cost and quality of service (QoS) jointly. We first study the attention-based microservice representation (AMR) method to achieve effective system context extraction. In this way, the contributions of different computing power providers (users, edge servers, or cloud servers) in the networks can be effectively paid attention to. Subsequently, we propose the attention-modified soft actor-critic (ASAC) algorithm to tackle the microservice deployment problem. ASAC leverages attention mechanisms to enhance decision-making and adapt to changing system dynamics. Our simulation results demonstrate ASAC's effectiveness, prioritizing average system cost and reward compared to the other state-of-the-art algorithms.

Foundation models (FMs) have shown great success in natural language processing, computer vision, and multimodal tasks. FMs have a large number of model parameters, thus requiring a substantial amount of data to help optimize the model during the training. Federated learning has revolutionized machine learning by enabling collaborative learning from decentralized data while still preserving clients’ data privacy. Despite the great benefits foundation models can have empowered by federated learning, their bulky model parameters cause severe communication challenges for modern networks and computation challenges especially for edge devices. Moreover, the data distribution of different clients can be different thus inducing statistical challenges. In this paper, we propose a novel two-stage federated learning algorithm called FedFMSL. A global expert is trained in the first stage and a local expert is trained in the second stage to provide better personalization. We construct a Mixture of Foundation Models (MoFM) with these two experts and design a gate neural network with an inserted gate adapter that joins the aggregation every communication round in the second stage. To further adapt to edge computing scenarios with limited computational resources, we design a novel Sparsely Activated LoRA (SAL) algorithm that freezes the pre-trained foundation model parameters inserts low-rank adaptation matrices into transformer blocks, and activates them progressively during the training. We employ extensive experiments to verify the effectiveness of FedFMSL, results show that FedFMSL outperforms other SOTA baselines by up to 59.19% in default settings while tuning less than 0.3% parameters of the foundation model.

Unmanned aerial vehicles (UAVs) as aerial relays are practically appealing for assisting the Internet of Things (IoT) network. In this work, we aim to utilize a UAV swarm to assist the secure communication between the micro base station (MBS) equipped with the planar antenna array (PAA) and the IoT terminal devices by collaborative beamforming (CB), so as to counteract the effects of the eavesdropper colluding in the time domain. Specifically, we formulate a UAV swarm-enabled secure relay multi-objective optimization problem (US*****RMOP) for simultaneously maximizing the achievable sum rate of the associated IoT terminal devices, minimizing the achievable sum rate of the eavesdropper and minimizing the energy consumption of UAV swarm, by jointly optimizing the excitation current weights of both MBS and UAV swarm, the selection of the UAV receiver, the position of UAVs and user association order of IoT terminal devices. Furthermore, the formulated US*****RMOP is proved to be a non-convex, NP-hard and large-scale optimization problem. Therefore, we propose an improved multi-objective grasshopper algorithm (IMOGOA) with some specific designs to address the problem. Simulation results exhibit the effectiveness of the proposed UAV swarm-enabled collaborative secure relay strategy and demonstrate the superiority of IMOGOA.

This paper proposes a novel design on the wireless powered communication network (WPCN) in dynamic environments under the assistance of multiple unmanned aerial vehicles (UAVs). Unlike the existing studies, where the low-power wireless nodes (WNs) often conform to the coherent harvest-then-transmit protocol, under our newly proposed double-threshold based WN type updating rule, each WN can dynamically and repeatedly update its WN type as an E-node for non-linear energy harvesting over time slots or an I-node for transmitting data over sub-slots. To maximize the total transmission data size of all the WNs over$T$slots, each of the UAVs individually determines its trajectory and binary wireless energy transmission (WET) decisions over times slots and its binary wireless data collection (WDC) decisions over sub-slots, under the constraints of each UAV's limited on-board energy and each WN's node type updating rule. However, due to the UAVs’ tightly-coupled trajectories with their WET and WDC decisions, as well as each WN's time-varying battery energy, this problem is difficult to solve optimally. We then propose a new multi-agent based hierarchical deep reinforcement learning (MAHDRL) framework with two tiers to solve the problem efficiently, where the soft actor critic (SAC) policy is designed in tier-1 to determine each UAV's continuous trajectory and binary WET decision over time slots, and the deep-Q learning (DQN) policy is designed in tier-2 to determine each UAV's binary WDC decisions over sub-slots under the given UAV trajectory from tier-1. Both of the SAC policy and the DQN policy are executed distributively at each UAV. Finally, extensive simulation results are provided to validate the outweighed performance of the proposed MAHDRL approach over various state-of-the-art benchmarks.

Energy-efficiency (EE) optimization of long-term evolution (LTE) networks dedicated to vehicle-to-vehicle communications (LTE-V2V) is critical for connected vehicles. In this paper, we integrate perimeter control methodologies from transportation science into EE optimization to make vehicular communications adaptive to temporal-spatial dynamics of macroscopic traffic flows in multiple urban regions. Specifically, we develop a hierarchical framework of joint LTE-V2V EE optimization and perimeter traffic flow control. Its goal is to minimize the total traffic network delay, defined as the integral of the vehicle accumulations in the urban regions over a prediction horizon time, meanwhile maximizing the energy efficiency of the LTE-V2V communications in the same regions. We propose a model predictive perimeter controller at a low level, using a macroscopic fundamental diagram (MFD) to capture the relationship between the traffic density and the outflow of each urban region. We also propose a high-level EE optimization model and an iterative algorithm, considering the multi-region coordinated traffic dynamics, to jointly optimize vehicular transmission power and beacon frequency. Simulation results validate our proposed models and show that our method outperforms the latest solutions by improving at least 9.57% EE of the multiple regions. Our method can also provide 27.69% improvement in resource utilization fairness, indicating a fairer EE performance distribution among these regions.

Energy efficiency is a significant requirement of resource management and design optimization in information networks. In this article, we propose an iterative fractional programming framework embedded with a distributed primal-dual extra-gradient projection algorithm, which addresses a wide class of the energy-efficiency optimization problems in wireless ad hoc networks with full-duplex radios and multi-packet reception capability. Specifically, we propose a model convexification mechanism by joining an affine transformation and an exponential transformation into the nonlinear fractional programming, which enables us to deal with the challenge arising from the complexity and non-convex structure of the original problem. With the model convexification, we can map the non-convex power control space into a convex space and equivalently derive a sequence of convex subproblems, which relaxes the convexity assumption widely adopted in the existing literature. We further propose a distributed primal-dual algorithm based on extra-gradient projection to solve the convex subproblem at each iteration of the fractional programming. The convergence of the proposed iterative fractional programming and the distributed optimization method is theoretically proven. Numerical results also verify the proposed method and demonstrate its superior performance over other representative distributed and centralized schemes in terms of achieving global energy efficiency.

The advancement of Internet of Things (IoT) technology has significantly transformed the dynamic between humans and devices, as well as device-to-device interactions. This paradigm shift has led to profound changes in human lifestyles and production processes. Through the interconnectedness of numerous sensors and controllers via networks, the IoT facilitates the seamless integration of humans with diverse devices, leading to substantial economic advantages. Nevertheless, the burgeoning IoT industry and the rapid proliferation of various IoT devices have also introduced a multitude of security vulnerabilities. Cyber attackers frequently exploit cyber attacks to compromise IoT devices, jeopardizing user privacy and property security, thereby posing a grave menace to the overall security of the IoT ecosystem. In this paper, we propose a novel IoT Web attack detection system based on a joint embedded prediction architecture (JEPA), which effectively alleviates the security issues faced by IoT. It can obtain high-level semantic features in IoT traffic data through non-generative self-supervised learning. These features can more effectively distinguish normal data from attack data and help improve the overall detection performance of the system. Moreover, we propose a feature interaction module based on a dual-branch network, which effectively fuses low-level features and high-level features, and comprehensively aggregates global features and local features. Simulation results on multiple datasets show that our proposed system has better detection performance and robustness.

The development of deep learning and edge computing provides rapid detection capability for surface defects. However, components produced in actual industrial manufacturing environments often have tiny surface defects and training data for each specific defect type is limited. Meanwhile, network resources at the edge of industrial networks are difficult to guarantee. It is challenging to train a proper surface defect detection model for each specific surface defect type and provide a real-time surface defect detection service. To address the challenge, in this paper, we propose a real-time surface defect detection framework based on transfer learning with multi-access edge-cloud computing (MEC) networks. Furthermore, we improve the original YOLO-v5s framework by introducing the spatial and channel attention mechanism, and adding an additional detection head to enhance the detection ability on tiny surface defects. Evaluation results demonstrate that the proposed framework has superior performance in terms of improving detection accuracy and reducing detection delay in the considered MEC network.

Industry 5.0 facilitates the intelligent upgrade of smart factories in Industrial Internet of Things (IIoT), and also introduces a plethora of data processing challenges. Mobile edge computing offloads data to edge servers for processing, easing the data processing pressure and reducing system cost. However, smart factories contain numerous sensitive information, and offloading them to edge servers directly may pose a risk of data leakage. To address these challenges, we investigate a localedge collaborative smart factory system. Specifically, we firstly model the tasks as a directed acyclic graph, and formulate the offloading problem as a Markov decision process, considering the optimization of latency, energy consumption and the number of overtime tasks. Then, we propose a security-aware computation offloading method using federated reinforcement learning in IIoT, named SCOF. SCOF employs federated learning, keeping data for local computation and uploading model parameters to edge servers for aggregation. The data transmission passes through an artificial noise channel to protect against eavesdropping. Meanwhile, SCOF utilizes differential privacy to protect data security and employs deep reinforcement learning for selecting near-optimal offloading decisions. Finally, abundant experiments are conducted under a real dataset. The results show that SCOF has better perfomance than the state-of-the-art baseline algorithms.

The widespread adoption of Industrial Internet of Things (IIoT) has significantly transformed various aspects of industrial manufacturing. However, the massive volume and complexity of IIoT data highlight the need for innovative solutions to enhance the overall performance of IIoT systems. In this regard, mobile edge computing, assisted by deep reinforcement learning, can alleviate the burden on IIoT systems through computation offloading. Nevertheless, in increasingly digitized industrial environments, how to make real-time, efficient task offloading decisions remains a subject of deep exploration. To address this issue, we propose a two-stage resource allocation and task offloading method, named MCORM. In the first stage, we use the Combinatorial Upper Confidence Bound algorithm, based on the combinatorial multi-armed bandit problem, to solve the resource allocation problem. In the second stage, the Multi-Agent Proximal Policy Optimization algorithm is employed to determine the approximate optimal offloading strategy. Specifically, the Convolutional Block Attention Module is utilized to process observation information, focusing on important features. Finally, extensive experiments are conducted using both simulated and real datasets. The results demonstrate that our proposed algorithm MCORM can reduce latency and energy consumption effectively, promoting efficient industrial production.

Deploying Latency-Critical (LC) services and Best-Effort (BE) services together is expected to improve resource utilization in edge clouds. However, co-locating LC and BE services on edge clouds presents unique challenges. Unlike cloud datacenters, edge clouds are heterogeneous, resource-constrained, and geographically distributed, leading to fiercer competition for resources and greater difficulty in balancing fluctuating co-located workloads. Due to the lack of consideration for the characteristics of edge environments, previous solutions designed for cloud datacenters are no longer applicable. To address these challenges, we introduceTango, a harmonious scheduling framework forKubernetes-based edge cloud systems with mixed services.Tangoincorporates novel components and mechanisms for elastic resource allocation on the edge, as well as two traffic scheduling algorithms that efficiently manage distributed edge resources.Tangofosters harmony not only by supporting compatible mixed services but also by offering collaborative solutions that complement each other. Based on a non-intrusive design forKubernetes,Tangofurther enhances it with automatic scaling and traffic scheduling capabilities. Compared to state-of-the-art approaches, experiments on large-scale hybrid edge clouds, driven by real workload traces, show thatTangoimproves system resource utilization by 36.9%, QoS-guarantee satisfaction rate by 11.3%, and throughput by 47.6%.

Mobile edge-cloud computing networks can provide distributed, hierarchical, and fine-grained resources, and have become a major goal for future high-performance computing networks. The key is how to jointly optimize service caching and computation offloading. However, the joint service caching and computation offloading problem faces three significant challenges of dynamic tasks, heterogeneous resources, and coupled decisions. In this paper, we investigate the issue of joint service caching and computation offloading in mobile edge-cloud computing networks. Specifically, we formulate the optimization problem as minimizing the long-term average service latency, which is NP-hard. To solve the problem, we conduct in-depth theoretical analyses and decompose it into two sub-problems: service caching processing and computation offloading processing. We are the first to propose a novel hierarchical deep reinforcement learning algorithm to solve the formulated problem, where multiple edge agents and a cloud agent collaboratively determine the caching-action and offloading-action, respectively. The results obtained through trace-driven simulations reveal that the proposed framework outperforms several prevailing algorithms concerning the average service latency across diverse scenarios. In a complex real scenario, our framework achieves an approximately 33% convergence improvement and a remarkable 39% reduction in the average service latency when compared to reinforcement learning-based algorithms.

The multi-hop broadcast is of crucial significance to emergency message dissemination in vehicular ad hoc networks (VANETs). However, current solutions focus on a single and fixed goal, which cannot satisfy the dynamic and diverse emergency message requirements. In this article, we propose an adaptive broadcast-relay selection scheme to fill up this gap. An adaptive control message is designed to reflect the dynamic and diverse emergency message requirements. An adaptive relay pattern switching mechanism is designed to accommodate such requirements based on the adaptive control message. Delay-sensitive messages are broadcasted by an adaptive sender-based relay pattern, in which the link quality is used to address the inherent transmission reliability problem. Delay-insensitive messages are broadcasted by an adaptive receiver-based relay pattern, in which the time interval of adjacent potential relays is set to address the inherent packet collision problem. The unique features of our solution are twofold. One is the stronger adaptivity due to the implementation of the dynamic relay patterns, and the other is the wider applications due to the satisfaction of multiple types of emergency messages. Extensive simulations demonstrate the advantages of our solution in terms of transmission delay, dissemination speed, and adaptability in different scenarios.

A wireless federated learning system is investigated by allowing a server and multiple workers to exchange uncoded information via orthogonal wireless channels. Since the workers frequently upload local gradients to the server via band-limited channels, the uplink transmission from the workers to the server becomes a communication bottleneck. Therefore, a one-shot distributed principle component analysis (PCA) is leveraged to reduce the dimension of uploaded gradients to relieve the communication bottleneck. A PCA-based wireless federated learning (PCA-WFL) algorithm and its accelerated version (i.e., PCA-AWFL) are proposed based on the low-dimensional gradients and the Nesterov’s momentum. For the non-convex empirical risk, a finite-time analysis is performed to quantify the impacts of system hyper-parameters on the convergence of the PCA-WFL and PCA-AWFL algorithms. The PCA-AWFL algorithm is theoretically certified to converge faster than the PCA-WFL algorithm. Besides, the convergence rates of PCA-WFL and PCA-AWFL algorithms quantitatively reveal the linear speedup with respect to the number of workers over the vanilla gradient descent algorithm. Numerical results are used to demonstrate the improved convergence rates of the proposed PCA-WFL and PCA-AWFL algorithms over the benchmarks.

Current mobile networks are facing dramatic growth in wireless traffics due to the prosperity of streaming media services. Cooperative edge caching, enabling multiple edge nodes to cache and share contents by exploiting the spatial/temporal user request differentiation, is regarded as a promising method to enhance Quality of Experience (QoE). However, frequent content sharing between BSs consumes operation cost such as the usage of cross-edge bandwidth and energy consumption. Therefore, new challenges incurred by performance-cost trade-off arise. In this paper, we propose a user preference-aware content caching and migration (PACM) scheme for video content delivery in a cost-efficient edge network. In this scheme, the dynamic user request preference and the long-term content migration cost budget are considered for content placement and delivery. To navigate a good performance-cost trade-off, we formulate the content caching and migration to be a long-term optimization problem. Then, the Lyapunov optimization method is used to decompose the problem into a series of real-time optimizations. As the decomposed problem is NP-hard, we design a novel collective reinforcement learning (CRL) algorithm that can realize online efficient decision-making by interacting with training experience. Simulation results show that the CRL algorithm has a high convergence rate and the proposed scheme can achieve quasi-optimal performance in terms of user-perceived latency, cache hit rate, and video stalling rate.

High-mobility unmanned aerial vehicles (UAVs) can serve as dual-function aerial service platforms for the Internet of Things (IoT), providing both sensing and communication services for IoT nodes without a base station (BS), particularly in emergency situations. In this paper, a UAV-assisted integrated sensing and communications (ISAC) system is proposed for IoT, which simultaneously senses the status information around the IoT and sends the sensing information to both the IoT nodes and a data collection center. In order to assess the sensing performance of ISAC, the radar estimation rate is introduced as a significant metric from the perspective of information theory. Considering the mutual interference between sensing and communications, the radar estimation rate is maximized through the coordinated optimization of UAV task scheduling, transmit power allocation, and 3D flight parameters under the constraint of communication rate. The formulated non-convex mixed-integer programming problem is divided into three subproblems, including UAV task scheduling optimization, UAV sensing and communication power optimization, and UAV 3D flight parameters optimization. The optimal solutions can be achieved by proposing a three-layer iterative optimization algorithm to optimize the three subproblems iteratively. The simulation results show that the radar estimation rate can well measure the sensing performance of the ISAC, which can be effectively improved by optimizing the 3D UAV flight parameters.

The future integrated sensing and communication (ISAC) networks is expected to equip with sufficient computation resources. However, current research focuses on single-domain resource allocation in ISAC and computing force networks, leaving the joint optimization of sensing, communication, and computation resource allocation unexplored. In this paper, we propose a novel approach to this problem by deep incorporating computation resources, combined with a federated learning framework, while considering sensing precision and power consumption. Firstly, a multi-objective optimization is designed, involving Cramer-Rao Bound, sum rate of ISAC networks, and power consumption of computing force networks. Subsequently, the multi-objective optimization is transformed into a multi-task learning model. We aim to obtain joint optimization of sensing, communication, and computation resource allocation via deep learning techniques. Towards the multi-task learning model, the multiple-gradient descent algorithm is utilized to obtain the multi-objective optimization. Furthermore, a practical low-complexity the multiple-gradient descent algorithm is developed to reduce the computational cost. Finally, the effectiveness of the proposed deep learning algorithms is verified by simulations results.

If the future traffic of small base stations (SBSs) can be foreseen, we can systematically adjust the system resources to meet the quality of service (QoS) of users and realize the effective assignment of network resources. To this end, a dynamic channel allocation schemes based on traffic prediction is proposed. First, the machine learning is adopted to extract temporal and spatial features of the service traffic or load in a certain region, and then the prediction results and graph theory are both used to realize the division of a given frequency band and bandwidth allocation, in order to achieve the purpose of coordinating the interference between SBSs and improve the system throughput; Secondly, oriented to the fluctuation of service traffic in the region, a dynamic channel allocation method based on user satisfaction is proposed to fulfill the dynamic adjustment of the total system bandwidth and channel allocation, so as to utilize the frequency band resources more effectively. Simulations show that our proposed method improves the number of bandwidths allocated per SBS by a factor of 4.932 and 1.225 on average compared to OCA and CA-CM, and it realizes the data rate requirement of most users with less bandwidth.

This work investigates the secure resource collaboration among selfish edge servers for multi-access edge computing (MEC)-enabled VR systems in a dynamic scenario. Due to the time-varying and stochastic nature of VR user requests, the edge servers usually have significant differences in workload. To this end, we first propose a type judgment method to perceive their service capability and divide them into two types, i.e., the requesting node (RN) with a poor service capability and the cooperative node (CN) with a powerful service capability. To promote collaboration among self-interest nodes, we then model the competitive interactions among RNs and CNs as a multi-leader and multi-follower Stackelberg game. For the RN (as the leader), we design a novel pricing strategy based on deep reinforcement learning (DRL) to motivate CNs to provide resource assistance. Meanwhile, an optimal selling strategy for the CN (as the follower) is presented to maximize its payoffs from the network. To overcome the security problem during the resource collaboration, we finally introduce the blockchain as a secure and trusted platform for resource publishing and trading, where an efficient consensus mechanism called Proof-of-Trust (PoT) is developed to improve the performance of blockchain. The simulation results show that the proposed approach achieves superior performance.

Unmanned aerial vehicle (UAV) and sidelink technology are becoming more and more important in emergency communication. To optimize overall energy efficiency, joint subchannel, transmit power, and multi-UAV trajectory optimization algorithms are examined in a multi-cell heterogeneous network of UAV and sidelink with quality of service (QoS) sensitivity restrictions. To allocate subchannel appropriately in each period, a grouping and matching approach is first developed that can handle the subchannel assignment of multi-cell. Then, successive convex approximation method is used to approximate the non-deterministic polynomial hard problem of power allocation. Taylor expansion approximation method is finally introduced to deal with multi-UAV trajectory optimization. In addition, the complexity analysis is provided and numerical results confirm the optimization methods’ reasonableness.

Computation offloading tends to be an effective way for mitigating computing pressure of user equipments (UEs). By computation offloading, the task can be handled in network edge and/or cloud center to compensate insufficient resources and capabilities of UEs. In this study, we construct a three-tier cloud-edge integration network, where user tasks are offloaded to satellite based edge server and further to the remote ground cloud server via backhaul links. The optimization problem is modeled for minimizing system energy consumption and considers user association, power allocation, task scheduling, and bandwidth assignment jointly. By the proposed schemes based on relaxation transformation and fractional programming, four subproblems are transformed into corresponding convex optimization problems and solved respectively. In order to find the global optimal solutions, a joint iterative algorithm for three-tier computation offloading problem is designed. In numerical simulations, we compare different communication schemes and computation offloading schemes to present the rationality and superiority of the designed algorithm for reducing system energy consumption.

Unmanned aerial vehicles (UAVs) have been demonstrated to be a prominent component for wireless communications. In this work, we consider an emergency communication scenario wherein a UAV-based relay system collects data from ground users, and then uses different UAV-enabled virtual antenna arrays (UVAAs) to transmit the collected data to several remote base stations (BSs) via collaborative beamforming (CB). However, several adjacent aerial users (AUs) are carrying out other missions at the same time, which may be interfered by the signal transmitted by the UVAAs. Thus, we formulate a reliable and energy-efficient communication multi-objective optimization problem (RECMOP) to jointly maximize the minimum receiving signal-to-noise ratio (SNR) of the BSs, minimize the maximum average receiving SNR of the AUs, and minimize the propulsion power consumption of the UAVs, so that diminishing the energy cost while enhancing the system performance. The formulated RECMOP is intricate since it is proven to be NP-hard and non-convex. Therefore, an improved multi-objective gravitational search algorithm (IMOGSA) with several specific designs is proposed to handle the formulated problem. Simulation results manifest that the proposed IMOGSA can effectively solve the formulated RECMOP, and it outperforms other benchmarks in both smaller and larger scale UAV networks. Moreover, extended simulation demonstrates the robustness of the proposed CB-based approach under several unexpected circumstances.

The super data transmission capability and connectivity of wireless technologies have promoted the arrival of the Internet of Things (IoT) era. However, the distinct characteristics of IoT devices make them vulnerable to malicious attacks such as hackers and viruses. This paper designs a novel IoT intrusion detection architecture that combines knowledge extraction and sharing, which can extract human understandable knowledge from the trained deep learning model and apply it to the training process of the detection model. The obtained knowledge can also be shared with other detection systems based on the blockchain, which will effectively improve the intrusion detection capabilities of the IoT and realize collective learning. In addition, we propose a CNN-based semi-supervised learning method under the constraints of rules, which can effectively alleviate the catas-trophic interference generated during the self-training process and improve detection accuracy. Simulation results confirm the effectiveness of the proposed architecture and method.

With the increasingly sophisticated algorithms of simultaneous localization and mapping (SLAM), it is difficult for mobile terminals with limited resources to exploit the performance of SLAM algorithms fully. Traditional deep reinforcement learning (DRL)-based approaches have offloaded SLAM tasks to servers. However, existing solutions suffer from low data efficiency and poor generalization problems. This paper proposes a novel approach based on recent advances in rewardless active inference for SLAM back-end optimization. Specifically, the reward function is replaced with simple rewardless guidance in active inference. In addition, instead of simply considering the SLAM task as a whole, we delve into the sub-tasks of back-end optimization of SLAM for offloading and resource allocation. Simulation results show the superior performance of the proposed scheme.

Quantum reinforcement learning (QRL) can outperform classical reinforcement learning (RL) by utilizing quantum parallel theory and quantum phenomena such as superposition and entanglement. Although some excellent work has been done on QRL, most existing works either fail to show the exponential advantage of quantum computation over classical computation in terms of performance or are too demanding on quantum devices. In this paper, we provide a novel perspective on combining quantum computing and RL with faster convergence speed and relatively relaxed demands on quantum devices. Specifically, we propose a method to construct a world model with quantum circuit that allows it to interact in a quantum way. In addition, we use Grover's algorithm to efficiently extract high-value information from the quantum world model. Extensive simulation results show that the proposed method can have superior performance compared to classical RL algorithms.

One of the main challenges in designing deep learning networks for autonomous driving is the lack of labeled data. Recent trends that address this problem involve the use of unlabeled data. In this paper, we propose a unified semi-supervised and federated learning (FL) approach that is designed to offer cost efficient and practical training of deep learning object detection models for autonomous driving. In our implementation, we assume that each vehicle is given some well-labeled image data which are coupled with unlabeled image data captured by its cameras. Each of the vehicles has a local object detection model, which will be trained leveraging a semi-supervised learning method with both labeled and unlabeled data. The local model parameters are uploaded to a cloud server and aggregated to update a global FL model which in turn is shared with all the vehicles involved. Performance evaluations showed that our proposed approach is a promising solution as it allows continuous training and thus improved performance in autonomous driving.

To break data silos and address the challenge of green communication, federated learning (FL) is widely used at network edges to train deep learning models in mobile edge computing (MEC) networks. However, many existing FL algorithms do not fully consider the dynamic environment, resulting in slower convergence of the model and larger training energy consumption. In this paper, we design a dynamic asynchronous federated learning (DAFL) model to improve the efficiency of FL in MEC networks. Specifically, we dynamically choose a certain number of mobile devices (MDs) by their arrival order to participate in the global aggregation at each epoch. Meanwhile, we analyze the energy consumption model of local update and upload update, and formulate the problem as a dynamic sequential decision problem to minimize the energy consumption, which is NP-hard. To address it, we propose an energy-efficient algorithm based on deep reinforcement learning named DDAFL, to intelligently determine the number of MDs participating in global aggregation according to the state of MEC networks at each epoch. Compared with baseline schemes, the proposed algorithm can significantly reduce energy consumption and accelerate model convergence.

This work proposes a novel three-layer federated learning (FL) framework with parameter selection and pre-synchronization (PSPFL) to achieve fast and accurate model training. The basic idea of PSPFL is that clients select partial model parameters for transmission and then base stations aggregate them cooperatively (i.e., pre-synchronization) and send the aggregated results to the server for global model update periodically. However, there is an intrinsic trade-off between parameter transmission overhead and model training loss. To strike a desirable balance between them, we investigate the optimal parameter pre-synchronization round and local training round under PSPFL. Specifically, we propose a Deep Q-Network (DQN)-based method to obtain the local training round and parameter pre-synchronization round. Finally, extensive experiments are conducted to evaluate the performance of the proposed method on commonly used datasets. The results show that the proposed method can reduce the sum of FL completion time and training loss by an average of 8.17%-18.82% compared to benchmarks.

Co-locating Latency-Critical (LC) and Best-Effort (BE) services in edge-clouds is expected to enhance resource utilization. However, this mixed deployment encounters unique challenges. Edge-clouds are heterogeneous, distributed, and resource-constrained, leading to intense competition for edge resources, making it challenging to balance fluctuating co-located workloads. Previous works in cloud datacenters are no longer applicable since they do not consider the unique nature of edges. Although very few works explicitly provide specific schemes for edge workload co-location, these solutions fail to address the major challenges simultaneously.

Tile-based streaming and super resolution are two representative technologies adopted to improve bandwidth efficiency of immersive video steaming. The former allows selective download of contents in the user viewport by splitting the video into multiple independently decodable tiles. The latter leverages client-side computation to reconstruct the received video into higher quality using advanced neural network models. In this work, we propose CASE, a collaborated adaptive streaming and enhancement framework for mobile immersive videos, which integrates super resolution with tile-based streaming to optimize user experience with dynamic bandwidth and limited computing capability. To coordinate the video transmission and reconstruction in CASE, we identify and address several key design issues including unified video quality assessment, computation complexity model for super resolution, and buffer analysis considering the interplay between transmission and reconstruction. We further formulate the quality-of-experience (QoE) maximization problem for mobile immersive video streaming and propose a rate adaptation algorithm to make the best decisions for download and for reconstruction based on the Lyapunov optimization theory. Extensive evaluation results validate the superiority of our proposed approach, which presents stable performance with considerable QoE improvement, while enabling trade-off between playback smoothness and video quality.

In this paper, a new and calibrated light field (LF) video dataset is introduced, which focuses on outdoor scenes and objects. Each video stream is 10 seconds long and it is captured with a dense camera array that consists of$5\times 5$camera modules in$1640\times 1232$resolution at 40 frames per second. As multiple cameras in an array setup may suffer from various conditions of camera settings, lens structure, and lighting variations, the resulting images can be negatively affected by geometric distortion and colour difference. To address that, a unified calibration method involving both spatial calibration and colour correction is employed to correct inconsistences and achieve a better image quality with reduced image distortion. This video dataset would be suitable for further research and investigation of a variety LF applications, such as autonomous driving and immersive media.

Mobile edge computing aims to provide cloud-like services on edge servers located near Mobile Devices (MDs) with higher Quality of Service (QoS). However, the mobility of MDs makes it difficult to find a global optimal solution for the coupled service placement and request scheduling problem. To address these issues, we consider a three-tier MEC network with vertical and horizontal cooperation. Then we formulate the joint service placement and request scheduling problem in a mobile scenario with heterogeneous services and resource limits, and convert it into two Markov decision processes to decouple decisions across successive time slots. We propose a Cyclic Deep Q-network-based Service placement and Request scheduling (CDSR) framework to find a long-term optimal solution despite future information unavailability. Specifically, to solve the issue of enormous action space, we decompose the system agent and train them cyclically. Evaluation results demonstrates the effectiveness of our proposed CDSR on user-perceived QoS.

Edge clouds have become a de-facto paradigm to deliver low and stable networks to delay-critical applications such as web services and AR/VR. A unique form of edge clouds is those crowdsourced from third parties, e.g., idle PCs or workstations. Such crowdsourced edge platforms can better sink computations closer to users, reduce the purchase cost, and eliminates the carbon generated during manufacturing. Yet, they also face the challenge of out-of-control hardware, e.g., a server dropping in/out anytime. In this paper, we perform the first-of-its-kind measurement of Quality of Service (QoS) for a large-scale crowdsourced edge platform, which covers over 10,000 edge servers, 100,000 users and 10,000,000 user requests. The measurement takes a holistic QoS view: (1) First, we look at how much hardware resources are provided by edge servers, how much time they are available for service deployment, and what are the major abnormal behaviors. (2) Second, we analyze the factors affecting service stability and quantify the resource utilization pattern of containerized services hosted on those edge servers. (3) Third, we investigate the spatial and temporal features of user requests handled by the platform. Many useful and somehow surprising findings are obtained through the above measurements. We also derive insightful implications that could help edge platforms and edge applications to better deliver their services to users.

The emergence of next-generation latency-critical applications places strict requirements on network latency and stability. Edge cloud, an instantiated paradigm for edge computing, is gaining more and more attention due to its benefits of low latency. In this work, we make an in-depth investigation into the network QoS, especially end-to-end latency, at both spatial and temporal dimensions on a nationwide edge computing platform. Through the measurements, we collect a multi-variable large-scale real-world dataset on latency. We then quantify how the spatial-temporal factors affect the end-to-end latency, and verified the predictability of end-to-end latency. The results reveal the limitation of centralized clouds and illustrate how could edge clouds provide low and stable latency. Our results also point out that existing edge clouds merely increase the density of servers and ignore spatial-temporal factors, so they still suffer from high latency and fluctuations. Based on the observations, we propose a robust prototype edge cloud model based on lessons we learn from the measurement and evaluate its performance in the production environment. The further evaluation result shows that edge clouds achieve 84.1% latency reduction with 0.5ms latency fluctuation and 73.3% QoS improvement compared with the centralized clouds.

As the research and applications of large language model (LLM) become increasingly sophisticated, it is difficult for resource-limited mobile terminals to run large-model inference tasks efficiently. Traditional deep reinforcement learning (DRL) based approaches have been used to offload LLM inference tasks to servers. However, existing solutions suffer from data inefficiency, insensitivity to latency requirements, and non-adaptability to task load variations. In this paper, we propose an active inference with rewardless guidance algorithm using expected future free energy for offloading decisions and allocating resources for the LLM inference task offloading and resource allocation problem of cloud-edge networks systems. Experimental results show that our proposed method has superior performance over mainstream DRLs, improves in data utilization efficiency, and is more adaptable to changing task load scenarios.

This paper proposes a new on-demand wireless energy transfer (WET) scheme of multiple unmanned aerial vehicles (UAVs). Unlike the existing studies that simply pursuing the total or the minimum harvested energy maximization at the Internet of Things (IoT) devices, where the IoT devices' own energy requirements are barely considered, we propose a new metric called the hungry-level of energy (HoE), which reflects the time-varying energy demand of each IoT device based on the energy gap between its required energy and the harvested energy from the UAVs. With the purpose to minimize the overall HoE of the IoT devices whose energy requirements are not satisfied, we optimally determine all the UAVs' trajectories and WET decisions over time, under the practical mobility and energy constraints of the UAVs. Although the proposed problem is of high complexity to solve, by excavating the UAVs' self-attentions for their collaborative WET, we propose the multi-agent graph reinforcement learning (MAGRL) based approach. Through the offline training of the MAGRL model, where the global training at the central controller guides the local training at each UAV agent, each UAV then distributively determines its trajectory and WET based on the well-trained local neural networks. Simulation results show that the proposed MAGRL-based approach outperforms various benchmarks for meeting the IoT devices' energy requirements.

Recently proposed split learning (SL) is a promising distributed machine learning paradigm that enables machine learning without accessing the raw data of the clients. SL can be viewed as one specific type of serial federation learning. However, deploying SL on resource-constrained Internet of Things (IoT) devices still has some limitations, including high communication costs and catastrophic forgetting problems caused by imbalanced data distribution of devices. In this article, we design and implement IoTSL, which is an efficient distributed learning framework for efficient cloud-edge collaboration in IoT systems. IoTSL combines generative adversarial networks (GANs) and differential privacy techniques to train local data-based generators on participating devices, and generate data with privacy protection. On the one hand, IoTSL pretrains the global model using the generative data, and then fine-tunes the model using the local data to lower the communication cost. On the other hand, the generated data is used to impute the missing classes of devices to alleviate the commonly seen catastrophic forgetting phenomenon. We use three common data sets to verify the proposed framework. Extensive experimental results show that compared to the conventional SL, IoTSL significantly reduces communication costs, and efficiently alleviates the catastrophic forgetting phenomenon.

Serverless architecture enables various intelligent applications to be run without managing infrastructure. In this architecture, the computing cost is generally proportional to the number of requested stateless functions and this number can affect the task completion time and, thus, it is prominent to decide an appropriate number of requested stateless functions. In this article, we propose a latency-guaranteed and energy-efficient task offloading (LETO) system where an Internet of Things (IoT) device decides the number of stateless functions requested to the cloud by considering the deadline on the task completion time and its energy level. To minimize the computing cost while guaranteeing sufficiently short task completion time and low energy outage probability, we formulate a constrained Markov decision process (CMDP) problem and convert the CMDP problem into an equivalent linear programming (LP) model. By solving the LP model, the optimal policy on the number of requested stateless functions can be achieved. Evaluation results illustrate that LETO can cut down the operating expenditure (OPEX) by up to 59% compared to a latency-guaranteed offloading scheme while keeping the task completion time and the energy outage probability below desirable levels.

Federated learning (FL) is an emerging technique to support privacy-aware and resource-constrained machine learning, where a base station (BS) will coordinate a set of distributed Internet of Things (IoT) devices to train a shared machine learning model with their local data sets. Nevertheless, due to the frequent interactions between BS and distributed IoT devices for the aggregating/distributing learning model parameters, the performance of FL is fundamentally restricted by the randomness of channel condition. To address this issue, we utilize the intelligent reflecting surface (IRS) to improve the efficiency of learning model aggregation/distribution. In addition, we consider two transmission protocols to enable the model aggregation from IoT devices to BS, i.e., frequency division multiple access (FDMA) and nonorthogonal multiple access (NOMA). For both protocols, we formulate the total training latency minimization problem under the available energy constraints of IoT devices, to jointly optimize the phase shifts of IRS, communication resource scheduling, and transmit power and local computing frequencies of IoT devices. Moreover, we further develop the efficient multidimensional resource management algorithms to solve the formulated training latency minimization problems. Numerical results demonstrate that the proposed IRS-assisted FL systems can achieve significant latency reduction as compared with other benchmark methods, and the NOMA-based model aggregation method exhibits a lower total training latency than the FDMA-based counterpart.

Secure ultrareliable low-latency communication (URLLC) has become a crucial requirement of mission-critical Internet of Things (IoT) applications and use cases, including automotive driving, remote surgery, and many others. However, it is still challenging to protect initial access of massive IoT devices over wireless channels, especially when malicious quantum adversaries paralyze the initial access by overhearing and tampering critical wireless messages, i.e., preambles. We propose a nested hash access system with post-quantum encryption to solve this issue. The system performs random repetition coding and nested hash coding on multidomain physical-layer resources to encode and decode preambles precisely and resiliently. Particularly, a subtle compression and encryption mechanism based on quasi-cyclic (QC)-moderate-density parity-check (MDPC) code is proposed between repetition and hashing operations to avoid passive eavesdropping during the preamble encoding process. We show that the code information can be maintained at 128-bit or higher privacy level, depending on the length of repetition code. Besides, the preamble decoding process can be proved secure agaisnt active attacks with a tolerable loss of decoding errors. Then, we formulate two nonconvex integer programming problems, each problem corresponding to the minimization of upper bound of preamble decoding error in an example application scenario. Finally, we can derive the expressions of system failure probability to evaluate the reliability of URLLC system under mission-critical IoT scenarios. Simulation results show the effectiveness of our proposed scheme despite attack.

The dramatic progresses of wireless technologies and wearable devices have significantly promoted the development and popularity of smart home, while digital twin (DT) emerges as a game changer benefiting from its enhanced capabilities of visualization and interaction. The DT is able to build a realtime and continuous visual replica of a physical object or process, and to provide realtime monitoring, anomaly prediction, smart interaction, and lifecycle management. This paper presents a DT model to empower healthcare monitoring in the smart home with the goals of graphical monitoring, healthcare prediction, and intelligent control. High fidelity DT of the house and its equipments is created for visualized monitoring, and two suites of devices are deployed for continuously acquiring the users’ electrocardiograph (ECG) waves and the WiFi signals in the house. Two intelligent algorithms are then developed to perform fall detection from WiFi signals and to screen atrial fibrillation from ECG waves collected by wearable devices. Experimental results well validate the proposed model’s effectiveness for smart home monitoring, and the advantages of the developed smart algorithms for healthcare prediction over counterparts.

With the development of networking technology, the computing system has evolved towards the multi-tier paradigm gradually. However, challenges, such as multi-resource heterogeneity of devices, resource competition of services, and networked system dynamics, make it difficult to guarantee service-level agreement (SLA) for the applications. In this paper, we propose a multi-tier edge-cloud computing framework, EdgeMatrix, to maximize the throughput of the system while guaranteeing different SLA priorities. First, in order to reduce the impact of physical resource heterogeneity, EdgeMatrix introduces the Networked Multi-agent Actor-Critic (NMAC) algorithm to re-define physical resources with the same quality of service as logically isolated resource units and combinations, i.e., cells and channels. In addition, a multi-task mechanism is designed in EdgeMatrix to solve the problem of Joint Service Orchestration and Request Dispatch (JSORD) for matching the requests and services, which can significantly reduce the optimization runtime. For integrating above two algorithms, EdgeMatrix is designed with two time-scales, i.e., coordinating services and resources at the larger time-scale, and dispatching requests at the smaller time-scale. Realistic trace-based experiments proves that the overall throughput of EdgeMatrix is 36.7% better than that of the closest baseline, while the SLA priorities are guaranteed still.

To support rapidly increasing services and applications from users, multi-tier computing is emerged as a promising system-level computing architecture by distributing computing/caching/communication/networking capabilities between cloud servers to users, especially deploying edge servers at network edges (e.g., base stations). However, due to heterogeneous content requests of users and a high-cost hit manner with direct hits, edge caching is still a most serious issue to be addressed. In this paper, we investigate the issue of recommendation-enabled edge caching in mobile two-tier (edge-cloud) computing networks. Particularly, we integrate recommender systems and edge caching to support both direct hits and soft hits and thus improve the resource utilization of edge servers. We model the factors affecting the user quality of experience as a comprehensive system cost and further formulate the problem as a multi-agent Markov decision process with the goal of minimizing the long-term average system cost. To address the formulated problem, we propose a decentralized recommendation-enabled edge caching framework that leverages a discrete multi-agent variant of soft actor-critic and federated learning. The proposed framework enables each edge server to learn its best policy locally and generate judicious decisions independently. Finally, trace-driven simulation results demonstrate that the proposed framework converges to a better caching policy and outperforms several existing algorithms on average system cost reduction.

In practical cell-free (CF) massive multiple-input multiple-output (MIMO) networks with distributed and low-cost access points, the asynchronous arrival of signals at the user equipments increases multi-user interference that degrades the system performance. Meanwhile, rate-splitting (RS), exploiting the transmission of both common and private messages, has demonstrated to offer considerable spectral efficiency (SE) improvements and its robustness against channel state information (CSI) imperfection. The signal performance of a CF massive MIMO system is first analyzed for asynchronous reception capturing the joint effects of propagation delays and oscillator phases of transceivers. Taking into account the imperfect CSI caused by asynchronous phases and pilot contamination, we derive novel and closed-form downlink SE expressions for characterizing the performance of both the RS-assisted and conventional non-RS-based systems adopting coherent and non-coherent data transmission schemes, respectively. Moreover, we formulate the design of robust precoding for the common messages as an optimization problem that maximizes the minimum individual SE of the common message. To address the non-convexity of the design problem, a bisection method is proposed to solve the problem optimally. Simulation results show that asynchronous reception indeed destroys both the orthogonality of the pilots and the coherent data transmission resulting in poor system performance. Besides, thanks to the uniform coverage properties of CF massive MIMO systems, RS with a simple low-complexity precoding for the common message obtained by the equal ratio sum of the private precoding is able to achieve substantial downlink sum SE gains, while the application of robust precoding to the common message is shown to be useful in some extreme cases, e.g., serious oscillator mismatch and unknown delay phase.

Interactions between transcription factor and target gene form the main part of gene regulation network in human, which are still complicating factors in biological research. Specifically, for nearly half of those interactions recorded in established database, their interaction types are yet to be confirmed. Although several computational methods exist to predict gene interactions and their type, there is still no method available to predict them solely based on topology information. To this end, we proposed here a graph-based prediction model called KGE-TGI and trained in a multi-task learning manner on a knowledge graph that we specially constructed for this problem. The KGE-TGI model relies on topology information rather than being driven by gene expression data. In this paper, we formulate the task of predicting interaction types of transcript factor and target genes as a multi-label classification problem for link types on a heterogeneous graph, coupled with solving another link prediction problem that is inherently related. We constructed a ground truth dataset as benchmark and evaluated the proposed method on it. As a result of the 5-fold cross experiments, the proposed method achieved average AUC values of 0.9654 and 0.9339 in the tasks of link prediction and link type classification, respectively. In addition, the results of a series of comparison experiments also prove that the introduction of knowledge information significantly benefits to the prediction and that our methodology achieve state-of-the-art performance in this problem.

With the explosive growth of mobile multimedia services and artificial intelligence applications involving automatic speech analysis (ASA), mobile devices are increasingly unable to handle these computation-intensive tasks generated by users due to the limited computing resource. Besides, the existing cloud computing paradigm is not capable of processing such real-time and delay-sensitive ASA tasks. In this paper, by leveraging mobile edge computing and deep learning (DL), we investigate task offloading for DL-empowered ASA in mobile edge-cloud computing networks to minimize the total time for processing ASA tasks, thereby providing an agile service response. Specifically, to accelerate the processing of ASA tasks, we decompose a convolutional neural network based encoder-decoder model and deploy the encoder at edge servers to extract the features of ASA tasks. Moreover, edge servers derive the user tolerance limit by using a linear regression model for further enhancing the quality of experience of users. Based on some certain network constraints (i.e., user association and edge servers’ storage/computing capacity), we propose a low-complexity and distributed offloading framework to solve the formulated complex problem. Evaluation results demonstrate the effectiveness of the proposed framework on reducing the total time and improving the satisfaction rate of users.

With the rapid growth of the Industrial Internet of Things, a large amount of industrial data that needs to be processed promptly. Edge computing-based computation offloading can well assist industrial devices to process these data and reduce the overall time overhead. However, there are dependencies among tasks and some tasks have high latency requirements, so completing computation offloading while considering the above factors faces important challenges. In this paper, we design a computation offloading method based on a directed acyclic graph task model by modeling task dependencies. In addition to considering traditional optimization objectives in previous computation offloading problems (e.g., latency, energy consumption, etc.), we also propose an age of information (AoI) model to reflect the freshness of information and transform the task offloading problem into an optimization problem for latency, energy consumption, and AoI. To address this issue, we propose a method based on an improved dueling double deep Q-network computation offloading algorithm, named ID3CO. Specifically, it combines the advantages of deep Q-network, double deep Q-network, and dueling deep Q-network algorithms while further utilizing deep residual neural networks to improve convergence. Extensive simulations are conducted to demonstrate that ID3CO outperforms the existing baselines in terms of performance.

The breakthrough of artificial intelligence (AI) techniques has accelerated their applications in a wide range of industries, such as security protection, transportation, agriculture, and medical care. With the support of edge computing environments, providing latency guaranteed AI as a Service (AIaaS) can accelerate the deployment of data-intensive and computation-intensive AI applications and reduce the investment cost of the customers. However, the deployment architecture and working mechanism design, and performance optimization problems specific for AIaaS with configurable data quality and model complexity have not been studied in existing works. To address the problem, we propose a configurable model deployment architecture (CMDA) for edge AIaaS and present a flexible working mechanism by enabling the joint configuration of data quality ratios (DQRs) and model complexity ratios (MCRs) for the AI tasks. Along with commonly used resource allocation operations, the manager can improve the energy and delay performance of AI services with the desired quality of results (QoRs). We develop an energy-delay minimization problem under the framework of CMDA and propose a polynomial regression based relaxing method to solve the task configuration subproblem. We conduct experiments and simulations on the ImageNet classification and the common objects in context (COCO) object detection tasks using state-of-the-art deep learning models. We present the corresponding result quality tables (RQTs) and QoR regression models to illustrate the proposed method. The results of single task configuration and multi-task configuration and resource allocation on ImageNet classification and COCO object detection tasks demonstrate that the proposed method can achieve over$5\times$HDEC improvement compared with non-optimization schemes, and also show that joint configuration of DQR and MCR can achieve over$1.2\times$HDEC improvement compared with the methods that only configure DQR or MCR.

For mission-critical massive machine-type communications (mMTC) applications, the messages are required to be delivered in real-time. However, due to the weak security protection capabilities of the low-cost and low-complexity machine-type devices, active jamming attack in the uplink access is a serious threat. Uplink access jamming (UAJ) can increase the number of dropped/retransmitted packets and restrict or prevent the normal device access. To tackle this vital and challenging problem, we propose a novel UAJ detection method based on the joint space-time sparsity (JSTS). Our key insight is that the JSTS-based feature will be significantly impacted if UAJ happens, since only a small fraction of the devices are active and the traffic pattern for each device is sporadic in the normal state. Unlike the existing detection methods under batch mode (i.e., all sample observations are collected before making a decision), the JSTS-based detection is performed in a sequential manner by processing the received signals one by one, which can detect UAJ as quickly as possible. Moreover, the proposed JSTS-based method does not rely on the prior knowledge of the attackers, since it only cares the abrupt change in the JSTS-based feature on each frame. Numerical results evaluate and confirm the effectiveness of our method.

Edge computing is a commonly used paradigm for providing low-latency computation services by locally deploying computation and storage resources close to the user equipments (UEs). Since the computation resource demand of the offloaded tasks of a UE is naturally a random variable, it is possible that the real-time computation capacity demand of a resource-limited hosting virtual machine (VM) or edge computing server (ECS) is larger than its computation capacity, causing unexpected delay or delay-jitter to the services, which should be avoided if possible, for delay-sensitive applications. We consider an edge computing scenario wherein the transmission links are unmanageable and computation resource demands of VM servers are stochastic. We propose a novel Logistic function-based service reliability probability (SRP) estimation model without specifying the distributions of the resource demands. We study the average SRP maximization problem (ASRPMP) in a VM-based edge computing server (ECS) by jointly optimizing the service quality ratios (SQRs) and the computation resource allocations, and we propose an alternative optimization algorithm (AOA) by decomposing the problem into a resource allocation problem (RAP) and a service quality control problem (SQCP). Based on the derived analytical solutions of the two subproblems, we propose an effective and low-complexity heuristic AOA (HAOA) to solve the ASRPMP. The simulation results obtained from both synthetic Gaussian workload data and PlanetLab trace data demonstrate that, given the same target SQR or computation resource, the proposed method can achieve similar performance compared with the convex AOA (CAOA) method with much higher complexity, and can improve the reliability of the services compared with the baseline weighted allocation method (WAM) in both high and low SRP regimes.

The term “metaverse” was first introduced in Neal Stephenson’s 1992 science fiction novel, Snow Crash. It is conceived as the successor to the contemporary Internet, wherein users, represented as avatars, can interact with others or with applications within a three-dimensional (3D) virtual space, which is ubiquitously accessible. Although the metaverse remains a digital construct, establishing a sophisticated virtual societal framework—including a stable economic system—is paramount as users acquire assets and foster communities therein[4]. The implications become profound and potentially unpredictable should any single entity gain dominance over this virtual societal infrastructure. Such anxieties have been vividly portrayed in recent cinematic offerings such as “Ready Player One” and “Free Guy.” In response, blockchain technology emerges as a promising countermeasure. Trailblazing metaverse platforms leveraging blockchain, such as Decentraland, CryptoVoxels, and Sandbox, utilize cryptocurrency and nonfungible tokens (NFTs) to define programmable assets or access privileges[11]. These tokens may facilitate a borderless and frictionless payment layer, ensuring the uniqueness, persistence, and tradability of users’ digital assets[9]. Furthermore, the rise of smart contract-driven decentralized applications (DApps)[10]—spanning decentralized finance (DeFi) to innovative social applications[5]— ushers in an era of transparent, self-regulating digital ecosystems. As a multimedia community predicated upon vast online participation, advancements in blockchain may pave the way for a fair, transparent, and sustainable metaverse[13].

With the rapid development of the Internet of Things technology, the concept of smart cities that aims to help residents improve their quality of life has raised much attention in several application areas. In the context of smart cities, the provision of point of interest (POI) recommendations become an important requirement because a wide range of POIs are available for urban dwellers. Location-based social networks (LBSNs) such as Foursquare and Gowalla provide a massive volume of user check-in records that can assist users in choosing new POIs. However, user trajectories are mostly sparse in the real world. For example, users only check in a few POIs, and this makes it difficult to provide recommendations based on limited history trajectories. Though some attempts have adopted auxiliary geographical information to enhance POI recommendation, they still encounter the following problems: 1) the geographical trajectories of users are usually sparse in real-world datasets; 2) users may be more interested in the remote POIs; and 3) the previous models inherently perform transductive learning that cannot handle well the recommendation of unseen users and POIs. To address these problems, we propose an inductive representation learning model (IRLM) for location recommendation. IRLM contains two parts, namely geographic feature extraction and inductive representation learning. IRLM first captures global geographical influences among POIs through a standard Gaussian mixture model (GMM). Then IRLM adopts an attention neural network for the recommendation. Experimental results indicate that our proposed model can achieve superior performance over state-of-the-art models.

Surrogate-assisted evolutionary algorithms (SAEAs) have shown promising performance for solving expensive optimization problems (EOPs) whose true evaluations are computationally or physically expensive. However, most existing SAEAs only focus on the problems with low dimensionality and they rarely consider solving large-scale EOPs (LSEOPs). To fill this research gap, this article proposes an ensemble surrogate-based coevolutionary optimizer for tackling LSEOPs. First, some local surrogate models are trained with low-dimensional data subsets by using feature selection on the large-scale decision variables, a part of which are used to build a selective ensemble surrogate for better approximating the target LSEOP. Then, a coevolutionary optimizer guided by the ensemble surrogate is designed by running two populations to cooperatively solve the target LSEOP and the simplified auxiliary problem. The information of offspring from the two populations is shared to facilitate the coevolution process, which can exploit the searching experience from the simplified auxiliary problem to help solving the target LSEOP. Finally, an effective infill selection criterion is used to update the ensemble surrogate and enhance its approximate performance. To evaluate the performance of the proposed algorithm, a number of well-known benchmark problems are used and the experimental results validate our superior performance over nine state-of-the-art SAEAs on most cases.

Recently we have witnessed the rise of Artificial Intelligence of Things (AIoT) and the shift of sensing paradigm from cloud-centric to the edge-centric, which effectively improves the sensing capability of intelligence transportation systems. To improve the real-time sensing performance, in this work we propose an ensemble sensing based scheme to solve the time-constraint synchronized inference problem and achieve robust inference with heterogeneous IoT devices in intelligence transportation systems. We design and implement Ensen, which incorporates various novel techniques such as customized DNN model design, KD-based model training, and dynamic deep ensemble management, etc., to achieve improved accuracy and maximize the computational resource usage of the whole sensing group. Extensive evaluations on different types of common IoT devices have shown that Ensen achieves a robust performance and can be easily extended to different types of convolutional neural networks.

Blockchain technology is developing rapidly and has been widely applied in the field of Internet of Vehicles (IoV) to solve trust and security problems. However, due to the high security requirements in IoV scenarios, the security threats of blockchain itself become a big challenge for its applications in IoV. As the largest distributed platform supporting smart contract, Ethereum becomes one of the popular blockchain platforms that has been applied in IoV applications. In Ethereum, the local world state (stored on Road Side Units (RSUs) in IoV) is applied to facilitate account query and transaction verification. However, previous works showed that the local database can be easily tampered, so attackers may issue invalid transactions based on the modified world state, which is not acceptable for IoV applications. In this paper, the success probability and expected time for such an attack are first analyzed theoretically, including the effect of portion of tampered RSUs and the number of required confirmation blocks. Then experiment evaluation verifies the correctness of the theoretical analysis and shows that the attack would succeed with a higher probability within a shorter time when the local database on more RSUs are attacked. On the contrary, increasing of confirmation blocks can effectively reduce the success probability of a single attack and extend the confirmation time of the invalid transaction. Finally, efficient attack detection and recovery methods are proposed based on a novel hierarchical architecture with hybrid RSUs, and the effectiveness and complexity are verified by theoretical analysis and experiments.

The mobile edge computing (MEC) technology can simultaneously provide high-speed computing services for multiple vehicular users (VUs) in vehicular edge computing (VEC) networks. Nevertheless, due to the open feature of the wireless offloading channels and the high mobility of the vehicles, the security and stability of the offloading process would be seriously degraded. In this paper, by utilizing the physical layer security (PLS) technique and spectrum sharing architecture, we propose a deep reinforcement learning based joint secure offloading and resource allocation (SORA) scheme to improve the secrecy performance and resource efficiency of the multi-user VEC networks, where the VU offloading links share the frequency spectrum preoccupied with the vehicle-to-vehicle (V2V) communication links. We use Wyner’s wiretap coding scheme to obtain the achievable secrecy rate and guarantee that confidential information cannot be decoded by multiple mobile eavesdroppers. We aim at minimizing the system processing delay while securing the wireless offloading process, by jointly optimizing the transmit power, the frequency spectrum selection and the computation resource allocation. We formulate the optimization problem as a multi-agent collaborative optimal decision problem and solve it with a double deep Q-learning algorithm. Besides, we set a punishment mechanism for the rate degradation to guarantee the communication quality of each V2V link. Simulation results demonstrate that multiple VU agents adopting the SORA scheme can rapidly adapt to the highly dynamic VEC networks and cooperate to improve the system delay performance while increasing the secrecy probability.

With the large-scale deployment of the Internet of Vehicles (IoV) and 5G technologies, it is inevitable to share data frequently for superior in-vehicle services. However, due to the dynamically changing and widely distributed Vehicular Ad-hoc Networks (VANETs), data sharing still faces challenges in security, efficiency, and reliability. In this paper, we propose a secure and reliable data-sharing scheme (SDSS) for edge-enabled IoV networks. It assigns multiple attribute authorities to alleviate the management burden and support a large attribute universe catering to the various services in IoV. To enhance efficiency and flexibility, edge computing is introduced for quickly responding to vehicles’ requests and assisting resource-constrained vehicle computation. And an online/offline mechanism is designed to further alleviate the computational pressure of sharing data online. In addition, we put forward a cooperative key generation approach to guarantee the security of users’ private keys. The security analysis proves that SDSS ensures resistance to collusion attacks and indistinguishability under chosen-ciphertext attacks (IND-CCA). Moreover, it can avoid the single point of failure and resist denial of service (DoS) attacks with the help of multiple distributed edge nodes. The experiment demonstrates SDSS is practicable for IoV data sharing.

Air-to-ground (A2G) communication based on Unmanned aerial vehicle (UAV) is an important part of the future communication system. In this paper, an A2G channel model with UAV three-dimensional (3D) wobbles (pitch, roll, and yaw) based on the geometry-based stochastic model (GBSM) is proposed. On this basis, the UAV’s internal vibration is modeled as a sinusoidal random process, and the UAV wobble caused by the atmospheric flow is modeled as the uniform distribution random process. We derive the channel temporal correlation function (CF) with UAV 3D wobbles, analyze the variation of the temporal CF with different carrier frequencies, and amplitudes of the wobble angles. It is found that, even if the UAV wobbles slightly, the channel temporal correlation will be significantly affected. Numerical results show that the channel CF will decrease rapidly with the increase of the amplitudes of wobble angles and the carrier frequency. Therefore, the coherence time of millimeter wave (mmWave) band is significantly less than that of sub-6 GHz band. The consistency of simulation results and measurement results in published papers ensures the availability of the proposed model. For the MUAVs scenario, when the distance between different UAVs is much greater than the wavelength, the A2G channels between different UAVs and user equipment (UE) on the ground are not correlated to each other, and the temporal auto-correlation function (ACF) of each UAV is the same as that of the SUAV scenario. This work contributes to the theoretical exploration and system design of A2G communication based on UAV.

In the 5 G era, data traffic has been growing rapidly. A small number of popular data files may dominate the network traffic and lead to heavy network congestion. Device-to-Device (D2D) communication can be used for caching and offloading significant data traffic. D2D social networks are instantiated paradigms of D2D communication. Existing studies maximize the performances of caching and offloading in D2D social networks by predicting potential content propagation paths. However, predicting such paths still faces many challenges, such as limitation of user spatial-temporal features, fragility of D2D social networks, and uncertainty of participants. As a solution, we first measure users' multi-dimensional features and content propagation paths to explore the distributions of D2D activities. Then we propose a D2D-LSTM model to predict complete content propagation paths hierarchically and design a prototype-user model for new participants. Experimental results demonstrate the state-of-the-art performances of D2D-LSTM. D2D-LSTM achieves at most 95% and at least 84.6% average precision in predicting terminal prototype-user class. Tree generation tests show that the generated trees have at most 64% and at least 17% similarity with ground-truth trees.

Interference is a serious problem in Wireless Body Area Networks (WBANs) and heavily weakens system performance. In this paper, we propose an exchange-free resource scheduling scheme to overcome the interference of dynamic coexisting WBANs. For each data transmission period, we design a transmission channel/slot allocation scheme based on a Latin square, where each character denotes a specific combination of a channel and a time slot. For each data retransmission period, we design a retransmission time-slot selection scheme based on a hash function, in which the unique identity information of the collided node is used to calculate the retransmission slot. Compared with existing solutions, our work has two key advantages. First, all nodes can independently allocate and coordinate resources rather than exchange information with each other in traditional methods, and thus guaranteeing strong adaptability to the fast changes of WBANs. Second, the contention-free resource allocation pattern is implemented for both the data transmission period as well as the data retransmission period, and thus guaranteeing no intra-WBAN interference and extremely low probability of inter-WBAN interference. Our simulation results show that interferences can be well addressed based on the metrics of the packet loss rate, throughput, power dissipation, and data delivery delay.

In federated learning (FL), if the participating mobile devices have low computing power and poor wireless channel conditions and/or they do not have sufficient data for various classes, a long convergence time is required to achieve the desired model accuracy. To address this problem, we first formulate a constrained Markov decision process (CMDP) problem that aims to minimize the average time of rounds while maintaining the numbers of trained data and trained data classes above certain numbers. To obtain the optimal scheduling policy, the formulated CMDP problem is converted into an equivalent linear programming (LP). Additionally, to overcome the problem of the curse of dimensionality in CMDP, we develop a joint client selection and bandwidth allocation algorithm (J-CSBA) that jointly selects appropriate mobile devices and allocates suitable amount of bandwidth to them at each round by considering their data information, computing power, and channel gain. Evaluation results validate that J-CSBA can reduce the convergence time by up to$49\%$compared to a conventional random scheme.

This paper investigates the information freshness of two-way relay networks (TWRNs) operated with physical-layer network coding (PNC). Information freshness is quantified by age of information (AoI), defined as the time elapsed since the generation time of the latest received information update. PNC reduces the communication latency of TWRNs by turning superimposed electromagnetic waves into network-coded messages so that end users can send update packets to each other more frequently via the relay. While sending update packets more frequently has the potential to reduce AoI, how to handle packet corruption in TWRNs has not been investigated. Specifically, if an old packet is corrupted in any hop of a TWRN, one needs to decide whether to drop or to retransmit the old packet, e.g., a new packet has more recent information but may take more time to be delivered. Therefore, we study the average AoI with and without automatic repeat request (ARQ) in PNC-enabled TWRNs. Interestingly, our analysis shows that neither the non-ARQ scheme nor the pure ARQ scheme achieves a good average AoI. Hence, we put forth an uplink-lost-then-drop (ULTD) protocol that combines packet drop and ARQ. Experiments on software-defined radios indicate that ULTD significantly outperforms non-ARQ and pure ARQ schemes in terms of average AoI, especially when the two end users have imbalanced channel conditions. We believe the insight of ULTD on TWRNs generally applies to other two-hop networks: to achieve high information freshness, when packets are corrupted in the first hop, new packets should be generated and sent (i.e., old packets are discarded); when packets are corrupted in the second hop, old packets should be retransmitted until they are successfully received.

Applying peer-to-peer (P2P) architecture to online video games has already attracted both academic and industrial interests, since it removes the need for expensive server maintenance. However, there are two major issues preventing the use of a P2P architecture, namely how to provide an effective distributed data storage solution, and how to tackle potential cheating behaviors. Inspired by emerging blockchain techniques, we propose a novel consensus model called Proof-of-Play (PoP) to provide a decentralized data storage system that incorporates an anti-cheating mechanism for P2P games, by rewarding players that interact with the game as intended, along with consideration of security measures to address the Nothing-at-stake Problem and the Long-range Attack. To validate our design, we utilize a game-theory model to show that under certain assumptions, the integrity of the PoP system would not be undermined due to the best interests of any user. Then, as a proof-of-concept, we developed a P2P game ( Infinity Battle ) to demonstrate how a game can be integrated with PoP in practice. Finally, experiments were conducted to study PoP in comparison with Proof-of-Work (PoW) to show its advantages in various aspects.

Kubernetes (k8s) has the potential to coordinate distributed edge resources and centralized cloud resources, but currently lacks a specialized scheduling framework for edge-cloud networks. Besides, the hierarchical distribution of heterogeneous resources makes the modeling and scheduling of k8s-oriented edge-cloud network particularly challenging. In this paper, we introduce KaiS, a learning-based scheduling framework for such edge-cloud network to improve the long-term throughput rate of request processing. First, we design a coordinated multiagent actor-critic algorithm to cater to decentralized request dispatch and dynamic dispatch spaces within the edge cluster. Second, for diverse system scales and structures, we use graph neural networks to embed system state information, and combine the embedding results with multiple policy networks to reduce the orchestration dimensionality by stepwise scheduling. Finally, we adopt a two-time-scale scheduling mechanism to harmonize request dispatch and service orchestration, and present the implementation design of deploying the above algorithms compatible with native k8s components. Experiments using real workload traces show that KaiS can successfully learn appropriate scheduling policies, irrespective of request arrival patterns and system scales. Moreover, KaiS can enhance the average system throughput rate by 15.9% while reducing scheduling cost by 38.4% compared to baselines.

In this paper, the issue of user-centric clustering in cloud radio access networks is investigated. Specially, the outage probability of the typical user is derived by taking void cell and composite fading into account. The locations of remote radio heads and users working on the same resource block are modeled as the Poisson point process (PPP) and Mat$\acute {e}$rn hard-core point process of type II (MHCPP), respectively. Due to intractability of MHCPP, the PPP-based approximation is adopted. Then the closed expression of Laplace transform of the probability density function of the interfering power under composite fading channels is derived by Gauss-Hermite quadrature. Based on the approximated PPP, we obtain the outage probability of the typical user with user-centric clustering in the presence of void cell. Finally, the outage probability with or without considering void cell is verified and analyzed under different system parameters (i.g., the density of nodes, the radius of cluster, and the threshold of signal quality) and channel fading conditions (i.g., the pathloss exponent, shadowing standard deviation) through extensive simulations. Simulation results show that the effect of void cell on the system performance should be considered, especially when the density of nodes or the size of cluster is limited.

Nowadays, the multi-access interference problem in the ISAC systems can not be ignored. The study on interference management in ISAC has been envisioned as one of key technologies to support ubiquitous sensing functions. Different from the current work, a communications-sensing-intelligence converged network architecture is proposed to coordinate interference in this paper. Each base station equips with the individual deep neural networks to allocate power and beamforming. On this basis, the interference management is transformed into a functional optimization with stochastic constraints. An unsupervised learning algorithm is proposed to allocate power for interference management. Furthermore, a transfer learning method is presented to obtain the interference management in terms of transmit beamforming. Finally, the distributed management is obtained from the local channel state information in the multi-cell scenario. Simulation results verify the effectiveness of the proposed unsupervised learning interference management method in the ISAC systems.

With the rapid development of intelligent transportation systems, there is an increasingly strong demand for low-latency and high-bandwidth vehicular services. Unmanned aerial vehicles (UAVs) can be used as a supplement to the ground networks, to relieve the communication pressure on ground facilities, such as base stations. In this paper, we use multiple UAVs to provide services for vehicles and model the multi-UAV scenario as a collaborative multi-agent system. In addition, we take vehicle safety as the top priority and the delay requirement as the constraints. Then we exploit the Lagrange multiplier to combine the constraint function and cost function, so as to reduce the resource consumption as much as possible on the premise of ensuring the safety of the vehicles. The influence of spectrum efficiency and computing power should also be taken into account when allocating resources. We adopt the multi-agent reinforcement learning to train the UAVs, and meanwhile introduce the attention mechanism so that each UAV can optimize itself better with the information of other UAVs. Through extensive simulations, the effectiveness of our proposed method is verified. Particularly, the limited resources can allocated efficiently according to the vehicle’s needs under the premise of ensuring vehicle safety.

With the rapid development of mobile services and applications, the transmitting of massive data makes low-cost communication a challenge. Edge-based wireless communication technology is developed to be a promising approach to satisfy the communication requirements. Edge caching technology is one of effective methods to reduce the overhead of communication system and the pressure of backhauls. In this paper, the joint optimization problem of caching placement and power allocation in virtualized low earth orbit (LEO) satellite-terrestrial networks is proposed, which is based on cooperative caching, by considering cache size limits and power constraints. The optimization problem is solved using an algorithm inspired by the courtship movements and random flights of mayflies. Simulation results show the effectiveness of the proposed scheme in improving system performance and reducing power consumption.

Semantic communication is a newly emerged communication paradigm that exploits deep learning (DL) models to realize communication processes like source coding and channel coding. Recent advances have demonstrated that DL-based joint source-channel coding (DeepJSCC) can achieve exciting data compression and noise-resiliency performances for wireless image transmission tasks, especially in environments with low channel signal-to-noises (SNRs). However, existing DeepJSCC-based semantic communication frameworks still cannot achieve adaptive code rates for different channel SNRs and image contents, which reduces its flexibility and bandwidth efficiency. In this paper, we propose a predictive and adaptive deep coding (PADC) framework for realizing flexible code rate optimization with a given target transmission quality requirement. PADC is realized by a variable code length enabled DeepJSCC (DeepJSCC-V) model for realizing flexible code length adjustment, an Oracle Network (OraNet) model for predicting peak-signal-to-noise (PSNR) value for an image transmission task according to its contents, channel signal to noise ratio (SNR) and the compression ratio (CR) value, and a CR optimizer aims at finding the minimal data-level or instance-level CR with a PSNR quality constraint. By using the above three modules, PADC can transmit the image data with minimal CR, which greatly increases bandwidth efficiency. Simulation results demonstrate that the proposed DeepJSCC-V model can achieve similar PSNR performances compared with the state-of-the-art Attention-based DeepJSCC (ADJSCC) model, and the proposed OraNet model is able to predict high-quality PSNR values with an average error lower than 0.5dB. Results also demonstrate that the proposed PADC can use nearly minimal bandwidth consumption for wireless image transmission tasks with different channel SNR and image contents, at the same time guaranteeing the PSNR constraint for each image data.

Due to the weak security protection capabilities of the low-cost and low-complexity massive access of machine-type devices, massive machine-type communications (mMTC) networks are extremely vulnerable to the access jamming, which can affect the correctness of activity and data detection of legitimate devices and even leads to the paralysis of the mission-critical mMTC applications. This paper studies detection problem of the access jamming in the uplink of mMTC (AJ-UM), and we propose to exploit the characteristics of the joint low-rank factor and sparsity (JLFS) to detect the AJ-UM. Our detection method is motivated by the fact that the JLFS-based feature will be significantly impacted if the AJ-UM happens. We first extract the JLFS-based feature by solving a low-rank maximum likelihood factor analysis problem with sparsity constraint, and then perform the AJ-UM detection in a sequential manner. Moreover, the proposed JLFS-based method does not need to know the accurate prior information of the JLFS-based feature in the presence or absence of the AJ-UM, which can determine the AJ-UM exists as long as there is an abrupt change in the JLFS-based feature. Numerical results are finally presented to confirm the effectiveness of the proposed JLFS-based method.

Wireless systems are upgraded to use green energy (e.g., solar, wind, and tide energy) such that the greenhouse gas emission can be neutralized. This work incorporates the on-grid energy into a green coordinated multi-point (CoMP) system to handle the volatile arrival of green energy. In the green CoMP, the long-term weighted throughput maximization problem is investigated by expecting a non-positive consumption of the long-term on-grid energy. Motivated by the capacity-achieving property and simple implementation, an online zero-forcing dirty paper precoder is proposed to update the precoding matrices by combining statistical learning with the Lyapunov learning. A tradeoff relation is theoretically established to show that the long-term weighted throughput approaches the $\mathcal{O}(V)$ -neighbor of optimal value while the long-term consumed on-grid energy increases at a rate of $\mathcal{O}\left( {{{\log }^2}(V)/\sqrt V } \right)$, where V is an introduced control parameter. Numerical results are used to verify the performance of the online zero-forcing dirty paper precoder.

Due to the rapid growth of data transmissions in internet of vehicles (IoV), finding schemes that can effectively alleviate access congestion has become an important issue. Recently, many traffic control schemes have been studied. Nevertheless, the dynamics of traffic and the heterogeneous requirements of different IoV applications are not considered in most existing studies, which is significant for the random access resource allocation. In this paper, we consider a hybrid traffic control scheme and use proximal policy optimization (PPO) method to tackle it. Firstly, IoV devices are divided into various classes based on delay characteristics. The target of maximizing the successful transmission of packets with the success rate constraint is established. Then, the optimization objective is transformed into a markov decision process (MDP) model. Finally, the access class barring (ACB) factors are obtained based on the PPO method to maximize the number of successful access devices. The performance of the proposal algorithm in respect of successful events and delay compared to existing schemes is verified by simulations.

In Internet of Vehicles (IoV), authentication technology provides a basic security means to achieve trusted communication between legitimate vehicles. Revocation checking for vehicle certificates is an indispensable procedure in the process of authentication to protect vehicular networks from attacks by non-legitimate vehicles. However, revocation checking introduces procedures that require additional time to process which challenges latency-sensitive applications in vehicular networks. This challenge grows more evidently if taking into consideration the factor of privacy preservation. In this paper, we propose to offload partial revocation tasks to network edges to lighten the revocation process in vehicles. Particularly, we design a dual-certificates model for the revocation offloading process and employ blockchain to achieve decentralized Certificate Revocation List (CRL) management. Finally, we build a prototype of our proposed solution based on Hyperledger Fabric using permission blockchain, and compare it with Proof-of-Work scheme in terms of blockchain synchronization latency performance.

This paper considers the joint optimization of computation offloading, service caching, and resource allocation in the Digital Twin Edge Network (DTEN), and formulates the problem as Mixed-Integer Non-Linear Programming (MINLP), whose goal is to minimize the long-term energy consumption of the system. To solve the optimization problem, a Deep Deterministic Policy Gradient (DDPG) based algorithm is proposed for determining the strategies of computation offloading, service caching, and resource allocation. Simulation results demonstrate that the proposed DDPG based algorithm can reduce the long-term energy consumption of the system greatly, and outperform other benchmark algorithms under different scenarios.

The edge-cloud system has the potential to com-bine the advantages of heterogeneous devices and truly realize ubiquitous computing. However, for service providers to guar-antee the Service-Level-Agreement (SLA) priorities, the complex networked environment brings inherent challenges such as multi-resource heterogeneity, resource competition, and networked sys-tem dynamics. In this paper, we design a framework for the edge-cloud system, namely EdgeMatrix, to maximize the throughput while guaranteeing various SLA priorities. First, EdgeMatrix introduces Networked Multi-agent Actor-Critic (NMAC) algorithm to redefines physical resources as logically isolated resource combinations, i.e., resource cells. Then, we use a clustering algorithm to group the cells with similar characteristics into various sets, i.e., resource channels, for different channels can offer different SLA guarantees. Besides, we design a multi-task mechanism to solve the problem of joint service orchestration and request dispatch (JSORD) among edge-cloud clusters, significantly reducing the runtime than traditional methods. To ensure stability, EdgeMatrix adopts a two-time-scale framework, i.e., coordinating resources and services at the large time scale and dispatching requests at the small time scale. The real trace-based experimental results verify that EdgeMatrix can improve system throughput in complex networked environments, reduce SLA violations, and significantly reduce the runtime than traditional methods.

In Internet of Things (IoT) employing centralized machine learning, security is a major concern due to the heterogeneity of end devices. Decentralized machine learning (DML) with blockchain is a potential solution. However, blockchain with proof-of-work (PoW) consensus mechanism wastes computing resources and adds latency to DML. Computing resources can be utilized more efficiently with proof-of-useful-work (uPoW), which secures transactions by solving real-world problems. We propose a novel uPoW method that exploits PoW mining to accelerate DML through a task scheduling framework for multi-access edge computing (MEC) systems. To provide a good quality-of-service for the system, we minimize the latency by solving a multi-way number partitioning problem in the extended form. A novel uPoW-based mechanism is proposed to schedule DML tasks among MEC servers effectively. Simulation results show that our proposed blockchain strategies accelerate DML significantly compared with benchmarks.

With unmanned aerial vehicle (UAV) technologies advanced rapidly, many applications have emerged in cities. However, those applications do not widely spread as the safety consideration hinders the UAV from integrating into the civilian environment. This work focuses on investigating the UAV emergency landing problem which is a critical safety functionality of UAV. This work proposed a graph convolution network (GCN)-based decision network to learn by imitating the human pilots’ landing strategy. To alleviate the needs of a large amount of real-world data for model training, the proposed model allows to be trained in a simulated environment and then transferred to the real-world scenario due to the separation of domain-specific terrain classes and domain-independent topological structures among down-looking camera images. The GCN-based decision network can be coupled with a topological heuristic to improve the performance of action prediction in an emergency situation. To evaluate the proposed method, this work implemented a simulation environment for collecting data and testing the UAV emergency landing. The empirical results in both simulated and real-world scenarios show that the proposed methods can outperform the state-of-the-art counterparts in terms of predictive accuracy and success landing rate.

Industrial Internet of Things (IIoT) systems connect a plethora of smart devices, such as sensors, actuators, and controllers, to enable efficient industrial productions in manners observable and controllable by human beings. Plain model-based and data-driven diagnosis approaches can be used for fault detection and isolation of specific IIoT components. However, the physical models, signal patterns, and machine learning algorithms need to be carefully designed to describe system faults. Besides, the ever-increasing level of connectivity among devices can induce exponential complexity. Knowledge-based fault diagnosis approaches improve interoperability via ontologies so that high-level reasoning and inquiry response can be provided to nonexpert users. Therefore, knowledge-based fault diagnosis approaches are preferred over plain model-based and data-driven diagnosis approaches in recent IIoT systems. In the context of IIoT systems, this work reviews the recent progress on the construction of knowledge bases via ontologies and deductive/inductive reasoning for knowledge-based fault diagnosis. Besides, general inductive reasoning methods are discussed to shed light on their successful applications in knowledge-based fault diagnosis for IIoT systems. Following the trend of large-system decentralization, future fault diagnosis also requires decentralized implementations. Therefore, we conclude this survey by discussing several interesting open problems for decentralized knowledge-based fault diagnosis for IIoT systems.

In the last few decades, ciphertext-policy attribute-based encryption (CP-ABE) technology has attracted great interest, since it can provide fine-grained, flexible, and access control for sensitive data to implement a high secure and efficient data-sharing mechanism. In this article, based on the linear secret sharing scheme (LSSS), an efficient scheme is proposed to realize a collaborative decryption function. For any user group, when the user’s attribute set cannot access the ciphertext alone, the private key of other users in the same group can be used for collaborative decryption with the permission of the data owner. Our scheme uses the LSSS matrix that can significantly reduce the computation and storage overhead when comparing with the existing schemes. Then, a multiauthorization model is created based on the Bohen–Lynn–Shacham technology in order to solve the key-management issue. Finally, we implemented the specific functions of the framework through JAVA, and built a private chain to verify the feasibility of data transfer between users.

Video surveillance in intelligent transportation systems (ITSs) is in the rapid growth stage, where video analytics is a potential technology to improve the safety of the Internet of Autonomous Vehicles (IoAV). However, massive video data transmission and computation-intensive video analytics bring an overwhelming burden for vehicular networks. Moreover, owing to the unstable network connection, the video data are not always reliable, which makes data sharing a lack of security and scalability in IoAV. In this work, we first propose a video analytics framework, where the multiaccess edge computing (MEC) and blockchain technologies are integrated into IoAV to optimize the transaction throughput of the blockchain system as well as reducing the latency of the MEC system. Furthermore, based on deep reinforcement learning, the joint optimization problem is modeled as a Markov decision process (MDP), and the asynchronous advantage actor–critic (A3C) algorithm is adopted to solve this problem. Simulation results demonstrate that our approach can fast converge and significantly improve the performance of blockchain-enabled IoAV with MEC.

In this article, we consider wireless-powered two-way communication in an$N$-user interference channel with imperfect channel state information (CSI). In the system considered, the receivers harvest energy and receive information simultaneously from data signals sent by transmitters using a time switching (TS) policy, before transmitting response signals back to the transmitters in a subsequent phase using the harvested energy. We aim to find the resource allocation that allows the transmit power and TS ratio to be determined jointly to maximize the sum rate of the response links while guaranteeing a predetermined rate requirement for each data link, even in the presence of errors in the estimated CSI. To deal with the nonconvexity of our optimization problem, we first introduce a gradient algorithm with a barrier function that finds suboptimal solutions heuristically. Moreover, to overcome the limitations of the gradient algorithm, e.g., its high computational complexity and vulnerability to channel error, we devise a robust strategy for resource allocation based on deep learning, in which artificially distorted CSI is fed into the deep neural network (DNN) during training to compensate for the incompleteness of the derived solutions caused by channel error. The performances of the considered schemes are examined through simulations, in which the proposed DNN scheme achieves a near-optimal performance with respect to the sum rate of the response links and outage probability under imperfect CSI, which validates its usefulness and robustness.

With the transmission and sharing of data in the Internet of Things (IoT), while bringing development to life and the economy, it also inevitably threatens the data copyright protection and authentication. Digital watermarking technology can provide an effective solution for copyright protection by embedding the watermark in the data to prove the copyright attribution. The existing methods of digital watermarking in IoT mainly target multimedia, without considering the copyright authentication in database data. Unlike multimedia information, the database does not focus on the subjective visual perception when using the data, but rather on the potential values unlocked from the data through algorithms such as data mining. Therefore, we propose a new database watermarking algorithm based on decision tree shift correction (DTSC), considering the data copyright authentication and usability when applying for data mining algorithm. The algorithm adjusts the watermarked data by the DTSC method and makes the watermarked decision tree identical to the original in the iteration process. It solves the problem of database data copyright authentication in IoT and ensures the usability of the data when used for decision tree model construction. From the simulation results, it can be seen that the proposed method ensures the usability of the data for the classification and regression tree decision tree algorithm while embedding the watermark in the database data, and the data distortion of the proposed method does not differ from that of the traditional watermarking algorithm.

Traditional decision making in a vehicle network includes uploading vehicle sensing data to faraway cloud platforms and then returning correlated results to the vehicles. The data have features of large quantity and high redundancy, which causes high communication latency and vehicle applications to deteriorate. Vehicular fog computing (VFC) is a new network paradigm that uses local fog nodes for decision making. However, how to achieve distributed information exchange with low latency is a challenging issue because the connectivity of the vehicle network is low due to vehicle mobility. In this article, a distributed information exchange scheme with low latency in VFC is proposed. First, considering the frequent changes in vehicle positions and the randomness in driving routes, public transportation facilities with a wider driving range such as buses and taxis are used as fog nodes to increase the probability of uploading data. Then, the fog nodes should dynamically adjust the data sampling frequency according to the time-space correlation of the data to ensure that only nonredundant data are received. To minimize the interruption latency caused by accidents during an exchange, the fog nodes evaluate and predict connection states among them and their neighboring vehicles when establishing exchanges. If a fog node finds that a vehicle cannot complete information exchange because the vehicle may move outside its communication range in a future period, it will recalculate an optimized relay route for the vehicle by using mixed integer programming. Theoretical analysis and simulation results show that compared with the existing work, the proposed scheme can completely exchange all vehicle data with lower latency.

Cloud storage and edge computing provide the possibility to address the tremendous storage and computing pressure caused by the explosive growth of traffic at the edge of the networks. In this scene, as data is outsourced to the cloud or edge servers, data privacy can be leaked. For enhancing security and privacy, attribute-based searchable encryption (ABSE), as an effective technical approach, achieves controllable search of ciphertext. Aiming at addressing the issues of the low search efficiency in a single-keyword ABSE scheme and the large computing overhead of the existing multikeyword ABSE schemes, we propose a novel multikeyword ABSE scheme (EMK-ABSE) through cloud-edge coordination. The huge amounts of encrypted data is stored to cloud server (CS), while the corresponding encrypted index is uploaded to the nearest edge node (EN) to perform multikeyword search and assisted decryption. To further release the computational burden of clients, a hybrid online/offline mechanism is adopted in encryption. Security analysis indicates that the multikeyword index in EMK-ABSE has secure indistinguishability under chosen keyword attack (IND-CKA). The comprehensive evaluation proves that EMK-ABSE achieves not only encrypted multikeyword retrieval but also fine-grained access control, with lower computation complexity in the three stages of encryption, trapdoor generation, and decryption. We show that the proposed scheme has higher efficiency and practicability than the selected relative works.

Random access schemes in satellite Internet-of-Things (IoT) networks are being considered a key technology of new-type machine-to-machine (M2M) communications. However, the complicated situations and long-distance transmission can make the current random access schemes not suitable for the satellite IoT networks. The random access problem in the satellite IoT networks is studied in this article. A novel random access scheme for machine-type-communication devices (MTCDs) is proposed, to maximize the efficiency of random access for contention-based and contention-free random access. Under the set of random access opportunities (RAOs) and limited delay, the random access control model is designed via maximizing efficiency of random access. The model-free deep reinforcement learning (DRL) algorithm is proposed to tackle the problem based on the random access model. Subsequently, the deep Dyna-$Q$learning algorithm is introduced to deal with the proposed random access control model. In this proposed scheme, the random access model-free DRL algorithm is developed using simulated experience. The proposed algorithms’ performances are discussed, and simulation results show the desirable performance of the proposed DRL methods on different system parameters.

With the development of wireless communication and Internet of Things (IoT), there are massive wireless devices that need to share the limited spectrum resources. Dynamic spectrum access (DSA) is a promising paradigm to remedy the problem of inefficient spectrum utilization brought upon by the historical command-and-control approach to spectrum allocation. In this article, we investigate the distributed DSA problem for multiusers in a typical multichannel cognitive radio network. The problem is formulated as a decentralized partially observable Markov decision process (Dec-POMDP), and we propose a centralized off-line training and distributed online execution framework based on cooperative multi-agent reinforcement learning (MARL). We employ the deep recurrent$Q$-network (DRQN) to address the partial observability of the state for each cognitive user. The ultimate goal is to learn a cooperative strategy which maximizes the sum throughput of a cognitive radio network in a distributed fashion without information exchange between cognitive users. Finally, we validate the proposed algorithm in various settings through extensive experiments. The experimental results show that the proposed CoMARL-DSA algorithm outperforms the state-of-the-art deep$Q$-learning for spectrum access (DQSA) in terms of successful access rate and collision rate by at least 14% and 12%, respectively.

Based on the trustless feature of blockchain, this article designs a general configurable blockchain-enabled smart manufacturing system to achieve flexible manufacturing in response to large-scale manufacturing services. With a transaction pool containing all the pending manufacturing tasks but aligning with the logic flow, the complex manufacturing structure can be uniformly tackled. Furthermore, in virtue of the contradiction between large-scale manufacturing and limited blockchain throughput, we formulate a joint optimization of the block size, task scheduling, and the supply-demand configuration to maximize the customers’ net profit with the probabilistic delay requirements, which addresses the critical issue of efficiency and latency in the blockchain-based live manufacturing process. Meanwhile, the production quality and price preference are involved. For solution, a mixed online bipartite matching-based DQN algorithm is proposed, which circumvents the high dimensionality by separating the task-manufacturer matching from the time-correlated problem. Simulation results show that the proposed flexible framework can well adopt to dynamic customer population, and achieves better convergence.

Millimeter wave (Mmwave) communication can realize high rate service for the upcoming Internet of Things (IoT) networks. Although directional multiantenna gains can help enhance security, randomly distributed eavesdroppers can still intercept confidential messages by residing in both the main-lobe and side-lobe areas of the beam signal. Considering the unique propagation features of mmWave, this article explores the potential of physical layer security in mmWave multiple-input–multiple-output (MIMO) systems. We propose an artificial noise (AN)-aided capacity threshold on–off secure transmission scheme to resist the eavesdropping threat. Taking into account the influence of mmWave channel characteristics, random blockage, and multiantenna gains, we first derive the closed-form expressions of transmission probability (TP) and secrecy outage probability (SOP) in a noncolluding eavesdropping scenario. Then, the lower bound of SOP with AN and closed-form expression of SOP without AN is derived in a colluding eavesdropping scenario. Theoretical analysis evaluates the impacts of various system parameters on secrecy performance and verifies the effects of AN interference on inhibiting side-lobe eavesdropping. Simulation results validate the theoretical results and indicate that the combination of capacity threshold on–off transmission scheme, AN interference, and multiantenna directional gains can effectively reduce the security threats of mmWave MIMO systems. Besides, the optimal power allocation ratio of AN in noncolluding scenarios is demonstrated and its rule is summarized, which depends on whether legitimate communication links are in blockage.

Large-scale acyclic flow systems (LSAFSs) are models of pipeline networks that are used to transport important resources, such as water, oil, and natural gas in smart cities. LSAFSs have features of complex topology and deep-underground deployment, which would cause accidents, such as leakages and pollution that are difficult to be detected in time. Mobile sensors (MSs)-based monitoring schemes appear as an effective solution in recent years to handle this situation. These schemes drop MSs into an LSAFS from specified locations, and the MSs will move along with fluid inside the LSAFS to collect data. When the MSs pass through a predeployed and activated receiver node (RN), they will upload their data to the RN. However, how to decide the optimal locations and timings for dropping of the MSs and the best activation periods and deployment locations of the RNs, such that total length of monitored pipelines in the LSAFS is maximized, as well as energy consumption of the RNs is minimized, is a challenging problem. The problem is more challenging if potential uploading failures and undetermined movement of the MSs are considered. In this article, we first formalize the problem as a multiobjective optimization problem. Then, we decompose the problem into a submodular optimization problem and an union set optimization problem, and prove they are NP-hard. Next, an approximate algorithm based on the Pigeonhole principle is proposed to solve the first problem, and a heuristic algorithm based on the inclusion-exclusion principle is proposed to solve the second problem. Extensive theoretical analyses and simulations show that the proposed algorithms outperform state-of-the-art algorithms.

A novel paradigm that combines federated learning with blockchain to empower edge intelligence over vehicular networks (FBVN) can enable latency-sensitive deep neural network-based applications to be executed in a distributed pattern. However, the complex environments in FBVN make the system latency much harder to minimize by traditional methods. In this article, we model the training and transmission latency of each autonomous vehicle (AV) and consensus latency of the blockchain in-edge side in FBVN. Considering the dynamic and time-varying wireless channel conditions, unpredictable packet error rate, and unstable data sets quality, we adopt duel deep$Q$-learning (DDQL) as the solving approach. We propose a federated DDQL algorithm, in which the learning agent is deployed on each AV side, and the sensing states on each AV do not need to be shared so that it increases scalability and flexibility for practical implementation. Simulation results show that the proposed algorithm has better performance in reducing system latency compared with the other schemes.

Mobile-edge computing (MEC) has emerged as a promising computing paradigm in the 5G architecture, which can empower user equipments (UEs) with computation and energy resources offered by migrating workloads from UEs to the nearby MEC servers. Although the issues of computation offloading and resource allocation in MEC have been studied with different optimization objectives, they mainly focus on facilitating the performance in the quasistatic system, and seldomly consider time-varying system conditions in the time domain. In this article, we investigate the joint optimization of computation offloading and resource allocation in a dynamic multiuser MEC system. Our objective is to minimize the energy consumption of the entire MEC system, by considering the delay constraint as well as the uncertain resource requirements of heterogeneous computation tasks. We formulate the problem as a mixed-integer nonlinear programming (MINLP) problem, and propose a value iteration-based reinforcement learning (RL) method, named$Q$-Learning, to determine the joint policy of computation offloading and resource allocation. To avoid the curse of dimensionality, we further propose a double deep$Q$network (DDQN)-based method, which can efficiently approximate the value function of$Q$-learning. The simulation results demonstrate that the proposed methods significantly outperform other baseline methods in different scenarios, except the exhaustion method. Especially, the proposed DDQN-based method achieves very close performance with the exhaustion method, and can significantly reduce the average of 20%, 35%, and 53% energy consumption compared with offloading decision, local first method, and offloading first method, respectively, when the number of UEs is 5.

Future heterogeneous services and applications require the provisioning of unprecedented massive user access, heterogeneous data traffic, high bandwidth efficiency, and low latency services in next generation multiple access. In response to the requests from these services and applications, a large number of workers with scattered computing power need to be managed uniformly and scheduled in an efficient manner to perform various tasks. Therefore, task allocation has become a crucial issue to determining whether next generation multiple access can support future heterogeneous services and applications. In this paper, we propose a novel Two-stage Multi-task Allocation method based on Discrete Particle Swarm Optimization (TMA-DPSO). TMA-DPSO is easy to implement and has good search efficiency, which is suitable for large-scale task allocation in next generation networks. Under TMA-DPSO, we redefine the particles in discrete coding form, iteratively update the position and velocity based on the individual optimal particles and the global optimal particle, and finally obtain a corrected optimal solution. Unlike previous methods that only focused on the first-stage task allocation, we make full use of workers’ remaining time to perform second-stage redundant task allocation, which can not only increase workers’ income, but also potentially improve fault tolerance and security. As far as we know, this is the first attempt to utilize the remaining time after first-stage allocation. Finally, we evaluate TMA-DPSO extensively using the synthetic and real-life datasets. The results demonstrate that whether in a compactly or uniformly distributed scene, TMA-DPSO outperforms three benchmark methods by increasing 2.15%-42.24% platform revenue and 6.1%-46.63% workers income.

Due to its inherent ability in reducing hardware cost and power consumption while maintaining high system capacity, hybrid precoding is deemed as one of the key technologies in the upcoming 5G/6G millimeter-wave (mmWave) massive multiple-input multiple-output (MIMO) systems. However, it is challenging to design high performance hybrid precoders/combiners with low computational complexity. In this paper, based on the singular value decomposition (SVD) technique and the concept of equivalent channel, joint hybrid precoding strategies with high spectral-efficiency and low complexity are proposed for both single-user and multi-user massive MIMO systems. Specifically, for single-user massive MIMO scenarios, after transforming the design of hybrid beamforming into the problem of maximizing the square of sum eigenvalues for an equivalent channel, a two-stage successive method is conceived to design the analog precoder and combiner jointly, and the corresponding equivalent channel is constructed. Then, the digital precoding and combining operations are realized directly by applying the SVD technique to the matrix of equivalent channel. Meanwhile, the hybrid precoding strategy is extended to the multi-user scenario for achieving high performance resultant from multi-user diversity. Extensive simulations are conducted to verify the effectiveness of the precoding/combing schemes. The results show that our proposed schemes can achieve superior performance with lower complexity compared to the existing ones.

Advances in communications and networking technologies are driving the computing paradigm toward the end-edge-cloud collaborative architecture to leverage ubiquitous data and resources. Opposite to centralized intelligence, Hierarchical Federated Learning (HFL) relieves overwhelmed communication overhead and enjoys the advantages of high bandwidth as well as abundant computing resources while retaining privacy-preserving benefits of Federated Learning (FL). It is difficult to balance system overhead and model performance in the HFL framework, while it could be solved by introducing an incentive mechanism. Although the incentive mechanism can alleviate the above anxiety by compensating relevant participants, some limitations (multi-dimensional properties, incomplete information and unreliable participants) will significantly degrade the performance and efficiency of the designed mechanism. To address the challenges caused by the above limitations, we propose InFEDge, a blockchain-based incentive mechanism in the HFL. The InFEDge considers 1) multi-dimensional individual properties to model system participants and proves the uniqueness of Nash equilibrium with the closed-form solution. Meanwhile, 2) we transform the problem under incomplete information into a contract game where we obtain the optimal solution. Moreover, 3) we also leverage the blockchain to provide economic incentives, prevent unreliable participants’ disturbance and further ensure data privacy by implementing the mechanism in the smart contract to offer a credible, faster, and transparent resource trading system. Experimental evaluations on a proof-of-concept testbed along with real traces demonstrate the superiority of our mechanism. Further, our method solves a real-world user allocation problem for future communications and networking.

With the explosive proliferation of connected devices and mobile users in the Internet-of-things, multiple access techniques are urged to be developed for the next generation wireless communications. Recently, rate-splitting multiple access (RSMA) has been a promising communication technology that holds advantages of strong robustness, low complexity, and high spectral efficiency, which can be integrated with the indoor visible light communication (VLC) broadcast system to compensate for the shortcomings of limited modulation bandwidth of LEDs. However, the research on the RSMA-based VLC systems is still in its infancy and there exist various problems to be explored. To benefit from the RSMA technique, this paper investigates the energy efficiency optimizations for both single-cell and multi-cell RSMA-based VLC broadcast systems. Specifically, these two systems are modeled, where the VLC broadcast channel follows Lambertian radiation model, and the splitting design and successive interference cancellation of RSMA are employed to mitigate the multi-user interference. Especially for multi-cell networks, the zero-forcing approach is adopted to eliminate the inter-cell interference. To maximize the energy efficiency, the precoding and power allocation problems are formulated for single-cell and multi-cell networks while accommodating multiple constraints including dynamic operation ranges of LEDs, QoS requirements, and interference elimination. For solving these non-convex fractional problems, two pieces of successive convex approximation (SCA)-based algorithms are proposed, in which the variable transformation and linear approximation are adopted. Simulation results indicate that the proposed schemes can achieve superior energy efficiency with fast convergence for various network loads and user deployments.

The studies of Unmanned Air/Ground Vehicle (UAV/UGV) cooperative detection systems have received much attention due to their wide applications in the disaster rescue, target tracking, intelligent surveillance, and automatical package delivery missions. UAVs provide a broad view and have a fast speed in the air, while UGVs have sufficient load capacity and can serve as repeater stations on the ground. The path planning of a UAV/UGV cooperative system is an important but difficult issue, which aims to plan paths for both the UAVs and the UGVs in the system to cooperatively complete a mission. In this article, we consider the path planning problem of the UAV/UGV cooperative system for illegal urban building detection, by taking the limits of UGV speed, UAV load power, and UAV/UGV communication restriction into consideration. To solve this problem, we first model the path planning problem as a constraint optimization problem which tries to minimize an overall execution time for completing the illegal urban building detection tasks, and then propose a two-level memetic algorithm (called Two-MA) to solve the path planning problems of both the UAV and the UGV. Experiments on both synthetic and real-world data sets show the superiority of the proposed Two-MA over several states-of-the-art algorithms in solving the path planning problems of the UAV and UGV for illegal urban building detection tasks. Note to Practitioners—This article was motivated by the task of detecting illegal buildings in cities by unmanned vehicles. Previous works mainly focus on path planning of either UAVs or UGVs in this task. This article proposes a new approach using an Unmanned Air/Ground Vehicle (UAV/UGV) cooperative system for detecting illegal buildings in parks, by taking the limits of UGV speed, UAV load power, and UAV/UGV communication restriction into consideration. This cooperative system consists of a UAV, UGV, and control center. The UAV equipped with cameras takes aerial photography in the air, and can transmit collected photos to the control center. The UGV executes loading and transportation on the ground, and can serve as takeoff and landing platforms for the UAV. The control center executes computationally intensive tasks such as data transmission and processing, task scheduling, and vehicle coordination. To quickly complete all detection tasks, a memetic algorithm is proposed for path planning of both the UAV and the UGV. The simulated results show that the proposed algorithm enables the UAV/UGV cooperative system to visit all buildings in cities with a minimum task execution time.

Cloud gaming is a novel service provisioning paradigm, which hosts video games in the cloud and transmits interactive game streams to game players via the Internet. In such cloud gaming scenarios, the cloud is required to consume tremendous resources for video rendering and streaming, especially when the number of concurrent players reaches a certain level. On the other hand, different game players may have distinct requirements on Quality-of-Experience, such as high video quality, low delay, etc. Under this circumstance, how to satisfy players of different interests by efficiently leveraging cloud resources becomes a major challenge to existing cloud gaming services. In order to meet the overall requirements of players in a cost-effective manner, this article applies game theory to cloud gaming scenarios. It proposes a distributed algorithm to optimize virtual machine (VM) placement in mobile cloud gaming through resource competition. Further, by constructing a potential function, we prove that the resource competition game is a potential game, and the proposed algorithm scales well as the player population increases. We prove theoretically and verify experimentally that, with the proposed distributed VM placement algorithm, players can achieve a mutually satisfying state within a finite number of iterations.

Inappropriate service migrations can lead to undesirable situations, such as high traffic overhead, long service latency, and service disruption. In this article, we propose an application-aware migration algorithm (AMA) with prefetching. In AMA, a mobile device sends a service offloading request to the controller. After receiving this request, the controller determines the initial service cloud where virtual machine (VM) of the service initially operates by considering the application type. In addition, it periodically decides where to migrate VM and prefetch its core part considering the mobility of the mobile device and application type. To minimize the generated traffic volume while satisfying the requirements of the application, a constrained Markov decision process (CMDP) is formulated and its optimal policy is obtained via linear programming. Evaluation results demonstrate that AMA with the optimal policy can reduce the generated traffic volume while satisfying the requirements of the application (i.e., service latency and probability of service disruption).

Multicast is a promising solution to address spectrum scarcity in wireless video streaming, while facing tough challenge in provisioning quality of service (QoS) to heterogeneous users. This article presents an adaptive modulation and coding (AMC) scheme to accommodate both spatial diversity and temporal variation on users’ channel conditions for QoS provisioning in wireless scalable video multicast. The QoS-guaranteed AMC policy optimization is formulated as constrained stochastic optimization based on Markov decision processes. An adaptive policy iteration algorithm is developed to find the optimal AMC policy online without any prior knowledge of users’ channel statistics or intensive calculations. This algorithm is attractive due to adaptability to unknown environments and less run-time computation expenditure. Simulations results demonstrate the effectiveness of the proposed scheme.

With the rise of the processing power of networked agents in the last decade, second-order methods for machine learning have received increasing attention. To solve the distributed optimization problems over multiagent systems, Newton's method has the benefits of fast convergence and high estimation accuracy. In this article, we propose a reinforced network Newton method with K -order control flexibility (RNN-K) in a distributed manner by integrating the consensus strategy and the latest knowledge across the network into local descent direction. The key component of our method is to make the best of intermediate results from the local neighborhood to learn global knowledge, not just for the consensus effect like most existing works, including the gradient descent and Newton methods as well as their refinements. Such a reinforcement enables revitalizing the traditional iterative consensus strategy to accelerate the descent of the Newton direction. The biggest difficulty to design the approximated Newton descent in distributed settings is addressed by using a special Taylor expansion that follows the matrix splitting technique. Based on the truncation on the Taylor series, our method also presents a tradeoff effect between estimation accuracy and computation/communication cost, which provides the control flexibility as a practical consideration. We derive theoretically the sufficient conditions for the convergence of the proposed RNN-K method of at least a linear rate. The simulation results illustrate the performance effectiveness by being applied to three types of distributed optimization problems that arise frequently in machine-learning scenarios.

The papers in this special section focus on the use of artificial intelligence (AI)-enabled technologies to address human wellness. As the COVID-19 pandemic took hold over the last several years, there was an urgent demand to pay more attention to psychological health for human wellness by providing methods and means of sensing psychological parameters, emotional care and mental disorder patient monitoring, especially during these difficult times. With the aid of wearable computing technology and artificial intelligence, emotion and mental disorder detections are available through sensing and analyzing psychological parameters. Discusses the use of AI-based patient monitoring and the ability to monitor human wellness via remote sensing technologies. The papers in this issue provide a snapshot of some of the latest research advances on the research and application of Small Things and Big Data, knowledge discovery and knowledge representation for the combination towards biomedical and health informatics.

With the rapid development of intelligent transportation systems, there is an increasing demand for a variety of vehicular services, such as automated driving assistance, emergency alert, infotainment, etc. However, in some situations (e.g., remote areas or maritime scenarios), the terrestrial networks alone cannot serve the vehicular applications very well due to the infrastructure deployment and maintenance issues. Satellite networks have become an effective supplement to terrestrial networks, which complement well in terms of coverage, flexibility, reliability, and availability. In this paper, we consider the low orbit multi-beam satellite-terrestrial networks to serve for vehicles. We model this problem as a cooperative multi-agent reinforcement learning process, where each beam acts as an agent, and the global bandwidth is cooperatively shared among all the agents. A multi-agent actor-critic method with attention mechanism is proposed to allocate resources for vehicles with strict delay requirements and minimum bandwidth consumption. When allocating bandwidth, the channel efficiency, the angle of the beams and the priorities of requests in different regions are also considered. Centralized training and distributed execution is performed in the training of the agents. Extensive simulation results verify the effectiveness of our proposed method, where all the agents can well cooperative to achieve efficient resource allocation on-demand for the vehicles under strictly limited bandwidth resources.

In intelligent transportation systems (ITS), the vehicular ad-hoc network (VANET) is an enabling technology that can provide information exchange services among connected and autonomous vehicles (CAVs). Video streaming over VANETs is a potential application to ensure the safety of drivers and passengers and improve infotainment services. However, owing to the dynamic network topology, video transmission in VANETs is very challenging in terms of latency, reliability, and security. Therefore, a comprehensive summary of the state-of-art video streaming over VANETs is surveyed in this work. Firstly, related works and background knowledge are introduced. Then, a systematic survey on resource allocation (RA) scheme for video streaming in VANETs is provided, and some prevailing and feasible optimization tools are elaborated. Furthermore, enabling technologies of video streaming over VANETs are summarized with a special focus on the integration of video communication, caching, and computing. Finally, we give some challenges and future research directions.

In battery swapping environments, electric vehicles (EVs) can play roles as battery providers as well as consumers. In this paper, we propose an optimal battery charging algorithm (OBCA) where a battery swapping station (BSS) charges batteries in its storage with the consideration of the profile of the electricity price and the arrival rates of EVs. To maximize the net profit of BSS while maintaining the battery changing probability above a certain level (i.e., maintaining high quality of service (QoS) of BSS), we formulate a constraint Markov decision process (CMDP) problem and the optimal charging schedule for batteries in BSS is obtained by a linear programming (LP). Evaluation results demonstrate that OBCA with the optimal policy can improve the net profit of BSS up to 418% compared to an electric price-aware scheme while maintaining high QoS of BSS.

Due to its flexibility and high maneuverability, Unmanned Aerial Vehicle (UAV) is able to quickly provide wireless connections to the ground vehicles in mobile environment. In this paper, a multi-UAV enabled mobile Internet of Vehicles (IoV) model is proposed, where the UAVs track to serve the mobile vehicles and send downlink information to the vehicles during the flight time. Considering the constraints of anti-collision and communication interference between the UAVs, the system throughput is maximized by jointly optimizing vehicle communication scheduling, UAV power allocation and UAV trajectory. The formulated non-convex optimization problem is separated into three subproblems, including communication scheduling optimization, power allocation optimization and UAV trajectory optimization, which can be solved by successive convex approximation (SCA). A joint iterative optimization algorithm of the three subproblems is put forward to get the optimal solution. Then, a fairness optimization problem is proposed to guarantee the fair communications for each vehicle. The numerical results reveal the excellent performance of the multi-UAV enabled mobile IoV by joint communication and trajectory optimization.

Connected and autonomous vehicles (CAVs) are recently envisioned to provide a tremendous social impact, while they put forward a much higher requirement for both vehicular communication and computation capacities to process resource-intensive applications. In this paper, we study unmanned aerial vehicle (UAV)-assisted mobile edge computing (MEC) for a platoon of wireless power transmission (WPT)-enabled vehicles. Our objective is to maximize the system-wide computation capacity under both communication and computation resource constraints. We incorporate the coupled effects of the platooning vehicles and the flying UAV, air-to-ground (A2G) and ground-to-air (G2A) communications, onboard computing and energy harvesting into a joint scheduling optimization model of communication and computation resources. To tackle the resulting optimization problem, we propose a successive convex programming method based on a second-order convex approximation, in which feasible search directions are obtained by solving a sequence of quadratic programming subproblems and used to generate feasible points that can approach a local optimum. We also theoretically prove the feasibility and convergence of the proposed method. Moreover, simulation results are provided to validate the effectiveness of our proposed method and demonstrate its superior performance over other conventional schemes.

Digital mymargin Twin (DT) and Intelligent Reflective Surface (IRS), the most two promising technologies of 6G make the Internet of Vehicles (IoV) more adaptive. However, future autonomous driving needs powerful networking resources and high-quality wireless communications to guarantee the Quality of Service (QoS). Especially considering the time-varying physical operating environments of IoV, it is extremely urgent to improve resource utilization and wireless channel quality. In this work, we propose a Digital Twin-Driven Vehicular Task Offloading and IRS Configuration Framework (DTVIF) to efficiently monitor, learn, and manage the IoV. Specifically, we adopt Mobile Edge Computing (MEC) and IRS to provide augmented computing capacities for vehicles and improve transmission performance when vehicles communicate to MEC servers. DT is employed to achieve real-time data collection and digital representation of physical operating environments of IoV to better support decisions making. In order to reduce the overall delay and energy consumption of DTVIF, we propose a Two-Stage Optimization for Jointly Optimizing Task Offloading and IRS Configuration (TSJTI) algorithm based on Deep Reinforcement Learning (DRL) and Transfer Learning (TFL). In the first stage, we introduce Double Deep$Q$-learning Networks (DDQN) to find the optimal offloading decision. In the second stage, based on the parameters learned from the first stage, we migrate the parameters from the first stage to find the optimal IRS configuration based on the Deep Deterministic Policy Gradient (DDPG) method. The simulations demonstrate that the proposed algorithm can effectively reduce the processing latency of task offloading and reduce the average energy consumption in DTVIF.

Content caching at femto base stations (F-BSs) enhances user experience. In practice, the storage size of F-BSs is often minuscule compared to the size of the content library, which calls for effective content placement strategy aligned with user association (UA), networking issues, and possible content retransmissions. The common assumption is to associate user equipments with the closes F-BS that holds the requested content—content-centric user association (CC-UA). We argue that CC-UA could deteriorate hit rate and energy efficiency (EE), and then propose three cache-agnostic UA schemes to tackle this issue: baseline (CA-B), Macro-to-femto (CA-M2F), and femto-to-femto (CA-F2F). Under CA-B if the requested content is not found at the cache, it is retrieved via backhaul. The CA-M2F scheme uses the communication between Macro-BSs and F-BSs to improve the performance. Finally, the CA-F2F scheme uses the direct F2F communication paradigm allowing F-BSs to share contents between themselves on-demand. By the aid of stochastic geometry we model and analyze all these UA schemes and derive associated hit rate and EE performances based on main system parameters. We then utilize the analysis to study the performance of the developed UA-C schemes under several (heuristic) probabilistic content placement strategies. For a chosen choice of the content placement strategy, the numerical results confirm that CA-F2F and CA-M2F outperform CC-UA and CA-B by large margins. For example, we observe that via CA-F2F one can achieve 1200 percent growth of EE compared to CC-UA.

A variety of novel mobile applications are developed to attract the interests of potential users in the emerging 5G-enabled vehicular networks. Although computation offloading and task scheduling have been widely investigated, it is rather challenging to decide the optimal offloading ratio and perform adaptive task scheduling in high-dynamic networks. Furthermore, the scheduling policy made by the network operator may be violated, since vehicular users are rational and selfish to maximize their own profits. By considering the incentive compatibility and individual rationality of vehicular users, we present POETS, an efficient partial computation offloading and adaptive task scheduling algorithm to maximize the overall system-wide profit. Specially, a two-sided matching algorithm is first proposed to derive the optimal transmission scheduling discipline. After that, the offloading ratio of vehicular users can be obtained through convex optimization, without any information of other users. Furthermore, a non-cooperative game is constructed to derive the payoff of vehicular users that can reach the equilibrium between users and the network operator. Theoretical analyses and performance evaluations based on real-world traces of taxies demonstrate the effectiveness of our proposed solution.

Traditional routing technologies based on a single IP address domain faces the challenge to meet the increasing demand for network services and security. Packet classification is a technique to differentiate multi-domain network traffic in a fine-grained manner using packet header fields. Packet classification requires to operate efficiently to avoid it becoming a bottleneck in the packet routing process. Tuple space search (TSS) used in SDN supports fast rule updates but low-speed packet classification. In this paper, we propose a learned Bloom filter (LBF)-based packet classification algorithm that combines LBF and TSS to promote classification speed by avoiding invalid hash table accesses. Specifically, LBF consists of multiple RNN models and one support Bloom filter (SBF), in which the learned models are trained with the positive and negative sets, and used as a pre-filter to identify the two sets. For the filter outcomes with a negative result from learned models, SBF is constructed to perform the second filtration. To ensure efficiency of RNN and SBF, we carefully select key features to be used in RNN and SBF, which can also maintain efficient search in the final stage of hash checking. Our experimental results show that the proposed algorithm saves more memory space than Tuple space pruning (TSP) given the same false positive rate. The proposed algorithm is competitive in terms of the number of memory accesses, while achieving almost one order of magnitude improvement on pre-processing time over NeuroCuts which is an advanced decision tree classifier.

The rapid increase of data traffic has brought great challenges to the maintenance and optimization of 5G and beyond, and some smart critical infrastructures, e.g., small base stations (SBSs) in cellular cells, are facing serious security and failure threats, causing resiliency degradation concerns. Among special smart critical infrastructure failures, the sleeping cell failure is hard to address since no alarm is generally triggered. Sleeping cells can remain undetected for a long time and can severely affect the quality of service/quality of experience to users. To enhance the resiliency of the SBSs in sleeping cells, we design a mobile edge-cloud computing system and propose a semi-supervised learning-based framework to dynamically detect the sleeping cells. Particularly, we consider two indicators, recovery proportion and recovery speed, to measure the resiliency of the SBSs. Moreover, in the proposed scheme, experts’ optimization experience and each period’s detection results can be utilized to iteratively improve the performance. Then we adopt a dataset from real-world networks for performance evaluation. Trace-driven evaluation results demonstrate that the proposed scheme outperforms existing sleeping cell detection schemes, and can also reduce the communication and runtime costs and enhance the resiliency of the SBSs.

Medium access control (MAC) plays a crucial role in ensuring proper operation in vehicular ad hoc networks (VANETs). However, existing solutions cannot meet the strict requirements of high throughput and low latency in high-density scenarios. In this paper, we propose a novel MAC protocol to meet such demands for VANETs. The roadside unit (RSU) pattern and the dual-transceiver manner are adopted to assign channel resources for all packets. The striking features of our approach are twofold: the time slot allocation based on global vehicle information and the consideration of different delay requirements of different applications. First, we design a time slot exchange mechanism, which avoids any transmission conflict between two adjacent RSUs, to reduce channel resource waste. Then, we design a packet weight allocation mechanism, by which the packets of any network edge area are assigned higher priorities to further reduce channel resource waste. Moreover, we devise a packet quality evaluation mechanism, by which our multi-objective problem is transformed into a single-objective problem. In addition, we devise a greedy branch-and-bound algorithm to address the multiple-knapsack problem, which is transformed into a single-knapsack problem. Extensive simulation results show the advantages of our approach in terms of throughput and latency.

Following the roadmap of carbon neutrality, wireless communication systems are upgrading to use green energy that comes from renewable sources, e.g., sun, tide, and wind. Due to the volatile arrival of green energy, the on-grid energy is used as a backup for a green coordinated multiple point system. In this work, a weighted sum-rate maximization problem in thegreencoordinated multiple point system is investigated by expecting non-positive consumption of the on-grid energy in the long term. Motivated by the capacity-achieving property and simple implementation, an online zero-forcing dirty paper precoder is proposed to update the precoding matrices by combining statistical learning with the Lyapunov learning technique. A tradeoff relation is theoretically established to show that the long-term weighted sum rate approaches the${\mathcal{ O}}(V)$-neighbor of optimal value while the long-term on-grid energy increases at a rate of${\mathcal{ O}}({\scriptstyle {}^{\scriptstyle \log ^{2}(V)}}\hspace {-0.224em}/\hspace {-0.112em}{\scriptstyle \sqrt {V}})$, where$V$is an introduced control parameter. Numerical results are used to verify the performance of the proposed online adaptive precoder.

Fault-Prone Mobile Edge Cloud (FP-MEC) is a new type of distributed network composed of mobile edge computing and network function virtualization, where virtual network services can be provided in the form of service function chains (SFCs) that are a sequence of virtual network functions (VNFs) on-demand deployed on resource-limited edge servers. FP-MEC has a characteristic that the fault probability of each VNF is dynamic and fluctuates with time and workloads, making SFCs temporarily unreliable. To increase the reliabilities, redundant Backup VNFs (BVNFs) need to be deployed near the VNFs and activated when they experience faults. Different mobile users would request different SFCs with reliability and service time demands to process their data. However, workloads of VNFs are dynamic and unpredictable in FP-MEC due to random arrival of user requests. How to optimally deploy VNFs and corresponding BVNFs on a set of edge servers to form expected SFCs that have higher reliabilities than user demand values, meanwhile throughput of receiving requests is maximized while receiving cost is minimized in real-time, is a challenging problem. The receiving cost is composed of deployment cost of instantiating VNFs and BVNFs, and communication cost of routing data among users, VNFs and BVNFs. In this paper, the long-term provisioning problem is first formulated as an integer linear program and proved to be NP-hard. Then, it is discretized into a sequence of one-slot optimization problems to handle practical time-varying fault probability, where a set of SFC requests are given at each time slot, and receiving or rejecting decisions are executed immediately without any future information. Finally, an online approximation scheme with a constant approximation ratio is proposed to solve the one-slot problems in polynomial time. Theoretical analyses and experiments based on real network topology of CERNET in China demonstrate that the scheme is promising compared to existing works.

With innovative applications of unmanned aerial vehicle (UAV) ad hoc networks in various areas, their demands on broad bandwidth, large capacity and low latency become prominent. The combination of millimeter wave, directional antenna and time division multiple access techniques, which enables concurrent transmissions, is promising to deal with it. In this paper, we study the resource allocation problem in UAV ad hoc networks. Specifically, the slot assignment, antenna boresight and transmit power are jointly optimized to promote the network capacity. First, we formulate the optimization problem as the maximization of the fairness-weighted network capacity, subject to the constraint on priority guarantee. Then, because the formulated problem is a mixed integer non-linear programming problem (MINLP), which is NP-hard, two algorithms called dual-based iterative search algorithm (DISA) and sequential exhausted allocation algorithm (SEAA) are respectively proposed to efficiently solve it with acceptable complexity. DISA slacks the MINLP into a continuous-variable optimization problem and solves it with the Lagrangian dual method in an iterative manner. As a heuristic method, SEAA schedules links sequentially, i.e., from high-priority to low-priority ones. Numerical results demonstrate that both DISA and SEAA can efficiently allocate resources for UAVs, while guaranteeing the fairness and priority of links.

The integration of blockchain and mobile edge computing (MEC), as a secure, efficient, and reliable edge computing paradigm, has been widely applied in many applications, such as large-scale Internet of Things (IoT), Internet of Vehicles (IoV), and smart grid. However, due to the restricted transaction throughput of blockchain, the combination of blockchain and MEC in most existing works cannot support applications with frequent transaction requirements. In this paper, we propose an integrated blockchain and MEC (IBM) framework based on a space-structured ledger to meet the transaction demands for IoT applications. In the framework, a collaborative mining process is designed, where we consider the cooperation between mobile devices (MDs) and MEC servers. To promote mining efficiency, we further develop a high-performance consensus mechanism called reputation-based proof of work (Re-PoW), in which differentiated mining targets are assigned according to the reputation of MDs. In the Re-PoW consensus mechanism, heterogeneous capabilities and historical behaviors of MDs are all considered for accurately evaluating their reputation. In addition, we present an alternating optimization algorithm by jointly optimizing bandwidth allocation and computation resource allocation to further enhance the performance of the proposed scheme. Simulation results show that the proposed approach can achieve significant throughput improvement.

The arrival of 5G networks has extensively promoted the growth of content delivery services (CDSs). Understanding and predicting the spatio-temporal distribution of CDSs are beneficial to mobile users, Internet Content Providers and carriers. Conventional methods for predicting the spatio-temporal distribution of CDSs are mostly base-stations (BSs) centric, leading to weak generalization and spatio coarse-grained. To improve the spatio accuracy and generalization of modeling, we propose user-centric methods for CDSs spatio-temporal analysis. With geocoding and spatio-temporal graphs modeling algorithms, CDSs records collected from mobile devices are modeled as dynamic graphs with spatio-temporal attributes. Moreover, we propose a spatio-temporal-social multi-feature extraction framework for spatio fine-grained CDSs hot spots prediction. Specifically, an edge-enhanced graph convolutional block is designed to encode CDSs information based on the social relations and the spatio dependence features. Besides, we introduce the Long Short Term Memory (LSTM) to further capture the temporal dependence. Experiments on two real-world CDSs datasets verified the effectiveness of the proposed framework, and ablation studies are taken to evaluate the importance of each feature.

As a compelling collaborative machine learning framework in the big data era, federated learning allows multiple participants to jointly train a model without revealing their private data. To further leverage the ubiquitous resources in end-edge-cloud systems, hierarchical federated learning (HFL) focuses on the layered feature to relieve the excessive communication overhead and the risk of data leakage. For end devices are often considered as self-interested and reluctant to join in model training, encouraging them to participate becomes an emerging and challenging issue, which deeply impacts training performance and has not been well considered yet. This paper proposes an incentive mechanism for HFL in end-edge-cloud systems, which motivates end devices to contribute data for model training. The hierarchical training process in end-edge-cloud systems is modeled as a multi-layer Stackelberg game where sub-games are interconnected through the utility functions. We derive the Nash equilibrium strategies and closed-form solutions to guide players. Due to fully grasping the inner interest relationship among players, the proposed mechanism could exchange the low costs for the high model performance. Simulations demonstrate the effectiveness of the proposed mechanism and reveal stakeholder's dependencies on the allocation of data resources.

Mobile edge computing (MEC) provides a new ecosystem that enables cloud computing capabilities at the edge of mobile networks, which is characterized by ultra-low latency and high bandwidth as well as real-time access to radio network information leveraged by applications. Nevertheless, various challenges, especially the decision-making issues for task offloading, are yet to be properly addressed. In this paper, leveraging the insight from the relative evaluation method, we propose a metric to quantify the benefit on users’ service experience enhancement by task offloading. Meanwhile, by comprehensively considering the energy cost, time cost and users’ service experience enhancement throughout the task offloading process, we formulate the task offloading decision-making problem as a two-dimensional knapsack loading problem to maximize the cost efficiency of task offloading. To solve the optimization problem more efficiently, we propose a suboptimal heuristic algorithm with polynomial-time complexity. Compared with four baseline algorithms, simulation results demonstrate the cost efficiency improvement of our proposed scheme.

With the development of network technology and the surge in demand, the speed and throughput of data and applications are leading to the skyrocketing increase in traffic. The communication and collaboration between heterogeneous edge servers are indispensable. In this scenario with heterogeneous edges, there is a common understanding on the fact that an effective edge caching algorithm could play the role of enabler to reduce the network resource consumption and content fetch delay. However, most of the existing studies on multi-agent caching methods focus more on the overall situation, while ignoring the mutual influence between different agents. In this context, we model the edge caching content replacement problem as a Markov process and deploy attention mechanism based on the Actor-Attention-Critic algorithm to realize a neighboring-aware edge caching (NAEC) strategy. The proposed method makes full use of the communication between base stations to exchange neighboring information, so that we can reduce the pressure on the backbone and further improve user satisfaction. The simulation results have verified the feasibility and effectiveness of the proposed algorithm.

With the rapid development of vehicular networks, there is an increasing demand for extensive networking, computing and caching resources. In fact, vehicular networks are nonstationary, and how to allocate multiple resources effectively and efficiently for dynamic vehicular networks is extremely important, however, really challenging. In this paper, we propose a general framework that can enable fast-adaptive edge resource allocation for dynamic vehicular environment. Specifically, we model the dynamics of the vehicular environment as a series of related Markov Decision Processes (MDPs). We combine hierarchical reinforcement learning with meta learning, which makes our proposed framework available to quickly adapt to a new environment by only fine-tuning the top-level master network, and meanwhile the low-level sub-networks can make the right resource allocation policy. The extensive simulation results show the effectiveness of our proposed framework, which can quickly adapt to different scenarios. This is consistent with the real-world situations and can significantly improve the performance of resource allocation in dynamic vehicular networks.

With the rapid increase of data in mobile edge computing (MEC) networks, mobile devices (MDs) have been generating many computation-latency-sensitive tasks. As the MDs are limited by resources in terms of storage, computation, and bandwidth, part of tasks have to be offloaded to the edge of mobile networks or the remote cloud for more efficient processing. Hence, task offloading plays a vital role in this scene. Existing works about task offloading mainly aim at one-shot task offloading and rarely consider the dependencies of tasks. In this paper, we focus on minimizing the maximum delay of processing a series of tasks with dependencies in MEC networks, which supports device-to-device communications. Specifically, we consider task offloading under a hybrid scenario with a small base station (SBS) deployed with an edge server (ES) and several MDs which generate several tasks with dependencies. Then we model the tasks to a weighted directed acyclic graph (DAG) and formulate the optimization problem as minimizing the critical path of the weighted DAG. To tackle this NP-hard problem, we propose a heuristic scheme to iteratively optimize the delay of paths of the weighted DAG under the constraints of the ES. To evaluate the proposed scheme, we perform numerical experiments with different numbers of tasks. Simulation results demonstrate that the proposed scheme outperforms other schemes in terms of reducing the system delay and saving the energy consumption of the MDs.

Kubernetes (k8s) has the potential to merge the distributed edge and the cloud but lacks a scheduling framework specifically for edge-cloud systems. Besides, the hierarchical distribution of heterogeneous resources and the complex dependencies among requests and resources make the modeling and scheduling of k8s-oriented edge-cloud systems particularly sophisticated. In this paper, we introduce KaiS, a learning-based scheduling framework for such edge-cloud systems to improve the long-term throughput rate of request processing. First, we design a coordinated multi-agent actor-critic algorithm to cater to decentralized request dispatch and dynamic dispatch spaces within the edge cluster. Second, for diverse system scales and structures, we use graph neural networks to embed system state information, and combine the embedding results with multiple policy networks to reduce the orchestration dimensionality by stepwise scheduling. Finally, we adopt a two-time-scale scheduling mechanism to harmonize request dispatch and service orchestration, and present the implementation design of deploying the above algorithms compatible with native k8s components. Experiments using real workload traces show that KaiS can successfully learn appropriate scheduling policies, irrespective of request arrival patterns and system scales. Moreover, KaiS can enhance the average system throughput rate by 14.3% while reducing scheduling cost by 34.7% compared to baselines.

In recent years, with the rapid development of the Internet of Things (IoT), various applications based on IoT have become more and more popular in industrial and living sectors. However, the hypertext transfer protocol (HTTP) as a popular application protocol used in various IoT applications faces a variety of security vulnerabilities. This article proposes a novel HTTP anomaly detection framework based on edge intelligence (EI) for IoT. In this framework, both clustering and classification methods are used to quickly and accurately detect anomalies in the HTTP traffic for IoT. Unlike the existing works relying on a centralized server to perform anomaly detection, with the recent advances in EI, the proposed framework distributes the entire detection process to different nodes. Moreover, a data processing method is proposed to divide the detection fields of HTTP data, which can eliminate redundant data and extract features from the fields of an HTTP header. Simulation results show that the proposed framework can significantly improve the speed and accuracy of HTTP anomaly detection, especially for unknown anomalies.

As an information carrier, the Internet of Things (IoT) based on the Internet and sensing equipment makes all physical objects form an interconnected network. The 5th generation mobile networks (5G) technology has many advantages, such as high data rates, reduced latency, energy savings, reduced costs, increased system capacity and large-scale device connectivity, realize the real-time data collection, transmission, analysis, management, and application in the era of global Internet of Everything. In order to quickly respond to people’s daily requirements and provide the smart application based on artificial intelligence technology in various scenarios, the number of IoT devices will further increase. The integration of mobile-edge computing (MEC) and IoT is imperative, especially in industries needing real-time data computing, such as smart home, public security, automobile transportation, smart health, emotion care, etc. As a new form of IoT terminal combining 5G and MEC, wearable device based on intelligent fabrics plays an important role in smart health and emotion care, which is one of the potential development directions of the next generation of intelligent medical and rehabilitation systems.

Nowadays, many disruptive Internet-of-Things (IoT) applications emerge, such as augmented/virtual reality online games, autonomous driving, and smart everything, which are massive in number, data intensive, computation intensive, and delay sensitive. Due to the mismatch between the fifth generation (5G) and the requirements of such massive IoT-enabled applications, there is a need for technological advancements and evolutions for wireless communications and networking toward the sixth-generation (6G) networks. 6G is expected to deliver extended 5G capabilities at a very high level, such as Tbps data rate, sub-ms latency, cm-level localization, and so on, which will play a significant role in supporting massive IoT devices to operate seamlessly with highly diverse service requirements. Motivated by the aforementioned facts, in this article, we present a comprehensive survey on 6G-enabled massive IoT. First, we present the drivers and requirements by summarizing the emerging IoT-enabled applications and the corresponding requirements, along with the limitations of 5G. Second, visions of 6G are provided in terms of core technical requirements, use cases, and trends. Third, a new network architecture provided by 6G to enable massive IoT is introduced, i.e., space-air-ground-underwater/sea networks enhanced by edge computing. Fourth, some breakthrough technologies, such as machine learning and blockchain, in 6G are introduced, where the motivations, applications, and open issues of these technologies for massive IoT are summarized. Finally, a use case of fully autonomous driving is presented to show 6G supports massive IoT.

With the emergence of 5G, wireless sensor networks, and related technologies, Internet of Things (IoT) has gained prominence as an emerging paradigm to meet the demands of flexible, agile, and ubiquitous accessibility of cyberspace from physical systems. However, the current centralized IoT architecture is heavily restricted by the problems of single points of failure, data privacy, security, and robustness. Recently, blockchains have been found attractive as potential solutions to some of these problems, due to their ability to maintain immutable open ledgers that are accessible to everyone but are tamper-proof. In addition, rapid development of edge computing has enabled a large range of new IoT applications. Edge computing pushes cloud services from the network core to the network edges in closer proximity to IoT devices. Thus, blockchain and edge computing are attractive technologies to meet new and existing challenges by enabling new IoT applications and services through secure, reliable, flexible, and powerful devices and systems while motivating new business models in the growing digital economies. They can provide attractive solutions, such as schemes for decentralized services, service virtualization, rapid resource optimization, and flexible and reliable management and maintenance.

In smart cities, data monitoring for basic infrastructures, such as an urban water supply pipeline system or an oil/gas supply pipeline system, has become one of the most important tasks. An urban pipeline system that can be called a large-scale acyclic directed pipeline network (LSADPN), which has some characteristics, such as wide geographical distribution, complex connection, and deep underground. Therefore, it is difficult to be monitored comprehensively and accurately in real time. In recent years, some studies have proposed methods that use mobile sensors that are put into a pipeline network to obtain accurate monitoring results from the interior of the network. However, the mobile sensors have no motion devices and can only flow with the liquid in the pipelines. When a pipeline connection is encountered, it is uncertain whether all branches of the connection can be covered. Therefore, the maximum monitoring capacity, i.e., liquid capacity in the network monitored by the mobile sensors, is difficult to be maximized. In this article, the problem of maximizing the monitoring capacity of LSADPN is first proved to be NP-hard. Then, two new mobile sensors deployment algorithms based on the submodular function optimization method are proposed. Theoretical analyses and experimental results show that the two algorithms can monitor a whole network with high probability and achieve near maximum monitoring capacity with a specified number of mobile sensors and a given time.

Distributed deep learning deployed in an edge computing environment is a promising approach for extracting accurate information from raw sensor data from Internet of Things (IoT). But the distributed training suffers from heavy communication overheads between a master node and multiple compute nodes due to frequent transmission of gradients, which limits the training efficiency of the distributed deep learning. In this article, we propose a novel algorithm named ProbComp-LPAC (ProbComp: probability compression and LPAC: layer parameters adaptive compression), which can reduce the communication overhead and improve the training efficiency of the distributed deep learning. ProbComp-LPAC adopts a probability equation to select the gradients and uses different compression rates in different layers of deep neural networks. Comparing with other methods, such as adaptive compression (AdaComp) and lazily aggregated quantized compression (LAQ), the performance of ProbComp-LPAC is not only faster in the training speed but also higher in the accuracy of the test.

In this article, we investigate control-aware energy-efficient transmission strategies for wireless control systems with short packets (WCSs), in which remote state estimation error, system stability, transmission energy consumption, and communication packets with finite-length coding are all taken into account. Specifically, we formulate the transmission strategy design problem as a multiobjective optimization problem, which minimizes the remote state estimation error and transmission energy consumption simultaneously under the constraints of system stability and short packet communications. To solve the multiobjective optimization problem, we first introduce a novel objective function that encapsulates two different objective functions into a single one by using weight parameters, and further prove that the solution of the new stochastic optimization problem is a nondominated solution of the original one. Moreover, to solve the new stochastic optimization, we propose a dynamic control-aware energy-efficient transmission (DCET) algorithm that pushes the objective cost close to the optimal with a tradeoff in virtual queue backlogs for constraints. In particular, to tackle the nonconvexity constraint due to short packet communications, we introduce an additional constraint, with which the optimization problem is convex. Finally, simulation results verified the superiority of our proposed transmission strategy as compared with schemes of TDMA and Aloha-RAM multi access.

This article puts forth a new channel coding paradigm for multi-source information streams with Age of Information (AoI) requirements. The recently introduced AoI metric characterizes the freshness of information, defined as the time elapsed since the generation of the last successfully received update. We study a setup in which a large number of sensors want to send update information to a common monitor with the help of aggregators. Specifically, an aggregator collects update packets from sensors and forwards them to the monitor. Conventional block codes (such as LDPC codes) that encode and decode each update packet separately do not perform well in such an information aggregation and update scenario. When update packets suffer from packet loss, we show that block codes lead to high instantaneous AoI because a sensor waits for a long time for the next update opportunity. This article investigates stream-based codes to tackle this problem. A distinguishing feature of stream-based codes is the joint encoding of update packets from different sensors, and a series of coded packets are sent continuously like a stream. Different update packets are then jointly decoded using multiple coded packets from the stream. A key challenge with AoI requirements is the joint design of error corrections of old packets and fast decodings of new packets. We design a practical encoding-decoding scheme and a sliding decoding window mechanism to control the decoding complexity. We evaluate two AoI metrics, average AoI and bounded AoI. In particular, bounded AoI corresponds to an AoI threshold that the instantaneous AoI is below a large percentage of the time. Experimental results on software-defined radio show that stream-based codes significantly outperform block codes in both average AoI and bounded AoI under varying channel conditions. Overall, stream-based codes provide a viable channel coding solution to multi-source information streams with timely update requirements.

In order to meet the growing demands for multimedia service access and release the pressure of the core network, edge caching and device-to-device (D2D) communication have been regarded as two promising techniques in next generation mobile networks and beyond. However, most existing related studies lack consideration of effective cooperation and adaptability to the dynamic network environments. In this article, based on the flexible trilateral cooperation among user equipment, edge base stations and a cloud server, we propose a D2D-assisted heterogeneous collaborative edge caching framework by jointly optimizing the node selection and cache replacement in mobile networks. We formulate the joint optimization problem as a Markov decision process, and use a deep Q-learning network to solve the long-term mixed integer linear programming problem. We further design an attention-weighted federated deep reinforcement learning (AWFDRL) model that uses federated learning to improve the training efficiency of the Q-learning network by considering the limited computing and storage capacity, and incorporates an attention mechanism to optimize the aggregation weights to avoid the imbalance of local model quality. We prove the convergence of the corresponding algorithm, and present simulation results to show the effectiveness of the proposed AWFDRL framework in reducing average delay of content access, improving hit rate and offloading traffic.

The pilot scheme currently used in 5th generation (5G) cellular networks assigns the same set of orthogonal pilot signals to all cells. This results in inter-cell interference, also known as pilot contamination, which can significantly degrade performance, especially in massive multi-input multi-output (MIMO) systems. To mitigate this interference, we propose a novel Dual Pilot Scheme (DPS) that assigns a slightly modified set of nearly-orthogonal pilot signals. DPS is a general scheme that can be implemented in any wireless communication system, including 5G and beyond. We demonstrate the integration of DPS in a massive MIMO system in both microscopic and macroscopic levels and analytically prove that DPS enables more accurate estimates of the channel state information in the minimum mean-squared error sense, under the independent identically distributed (i.i.d.) and the correlated Rayleigh fading wireless communication channel models. We further validate and demonstrate the advantages of DPS over various channel models of massive MIMO 5G technology by extensive simulations.

This paper investigates the security problem of a multi-eavesdrop multiple-input-single-output (MISO) wiretap channel, where an N-antenna transmitter communicates with a single-antenna legitimate user in the presence of multiple single-antenna smart eavesdroppers. To overcome the security risk of the traditional secure constructive interference-based (CI-based) scheme when facing the smart eavesdroppers, we propose a novel deception scheme (DS) via a random transmission strategy, where the eavesdroppers are expected to decode the deception symbols correctly but unable to distinguish the authenticity of the decoded symbol. Then, an efficient algorithm is proposed for the deception signal-to interference-plus-noise (SINR)-balancing problem when perfect channel state information (CSI) is assumed. Furthermore, we consider a practical scenario where only imperfect CSI is available, and explore two different methods for the deception optimization problem, i.e., convexification relaxation approach (CRA) and Lagrangian relaxation approach (LRA), respectively. For both CSI cases, a closed-form solution to the considered CI-based deception scheme is obtained. Simulation results validate the superiority of the proposed approach over traditional secure precoding schemes, and also demonstrate the significant computation efficiency improvements for the proposed algorithms.

The combination of non-orthogonal multiple access (NOMA) and multi-access edge computing (MEC) can significantly improve the system performance including communication coverage, spectrum efficiency, etc. In this article, we focus on energy-efficient resource allocation for a multi-user multi-BS NOMA-MEC network with imperfect channel state information (CSI), where each user can upload its tasks to multiple base stations (BSs) for remote executions. We propose an optimization scheme, including task assignment, power allocation and user association, to minimize energy consumption. Specifically, we transform the probabilistic problem into a non-probabilistic one. To efficiently solve this nonconvex energy minimization problem, we first investigate the one-user two-BS case and derive the optimal closed-form expressions of task assignment and power allocation via the bilevel programming method. Subsequently, based on the derived optimal solution, we propose a low complexity algorithm for the user association in the multi-user multi-BS scenario. Simulations demonstrate that the proposed algorithm can yield much better performance than the conventional OMA scheme and the identical results with lower complexity from the exhaustive search with the small number of BSs.

Edge nodes (ENs) in Internet of Things commonly serve as gateways to cache sensing data while providing accessing services for data consumers. This paper considers multiple ENs that cache sensing data under the coordination of the cloud. Particularly, each EN can fetch content generated by sensors within its coverage, which can be uploaded to the cloud via fronthaul and then be delivered to other ENs beyond the communication range. However, sensing data are usually transient with time whereas frequent cache updates could lead to considerable energy consumption at sensors and fronthaul traffic loads. Therefore, we adopt Age of Information to evaluate data freshness and investigate intelligent caching policies to preserve data freshness while reducing cache update costs. Specifically, we model the cache update problem as a cooperative multi-agent Markov decision process with the goal of minimizing the long-term average weighted cost. To efficiently handle the exponentially large number of actions, we devise a novel reinforcement learning approach, which is a discrete multi-agent variant of soft actor-critic (SAC). Furthermore, we generalize the proposed approach into a decentralized control, where each EN can make decisions based on local observations only. Simulation results demonstrate the superior performance of the proposed SAC-based caching schemes.

Terahertz (THz) band has attracted considerable interest recently due to its superior high frequency and large available bandwidth. THz could act a vital part in the sixth generation (6G) mobile communication networks. In this paper, we introduce the downlink non-orthogonal multiple access (NOMA) technology into THz band small cell networks, where the total performance is optimized considering the two key enabling technologies. In order to decrease the energy consumption triggered by increasing of wireless services, we pay great attention to energy efficiency (EE) optimization and resource allocation in the THz-NOMA downlink systems by solving the subchannel assignment and power optimization. We first exploit a channel model for the THz-NOMA downlink system by using the key features of THz-NOMA networks. Then we utilize Dinkelbach-style algorithm to solve the resource allocation problem and decompose it into two subproblems. A subchannel assignment algorithm and a power optimization based on alternative direction method of multipliers (ADMM) algorithm are developed to get the solution. Finally, to embody the strengths of THz-NOMA performance, we compare our proposed schemes against the conventional schemes. Simulation results yield substantially higher EE and further prove the availability of our proposed schemes.

In this paper, we focus on the physical layer security for a $K$ -user multiple-input-single-output (MISO) wiretap channel in the presence of a malicious eavesdropper, where we propose several interference exploitation (IE) precoding schemes for different types of the eavesdropper. Specifically, in the case where a common eavesdropper decodes the signal directly and Eve's full channel state information (CSI) is available at the transmitter, we show that the required transmit power can be further reduced by re-designing the `destructive region' of the constellations for symbol-level precoding and re-formulating the power minimization problem. We further study the SINR balancing problems with the derived `complete destructive region' with full, statistical and no Eve's CSI, respectively, and show that the SINR balancing problem becomes non-convex with statistical or no Eve's CSI. On the other hand, in the presence of a smart eavesdropper using maximal likelihood (ML) detection, the security cannot be guaranteed with all the existing approaches. To this end, we further propose a random jamming scheme (RJS) and a random precoding scheme (RPS), respectively. To solve the introduced convex/non-convex problems in an efficient manner, we propose an iterative algorithm for the convex ones based on the Karush-Kuhn-Tucker (KKT) conditions, and deal with the non-convex ones by resorting to Taylor expansions. Simulation results show that all proposed schemes outperform the existing works in secrecy performance, and that the proposed algorithm improves the computation efficiency significantly.

In this paper, we investigate secure content delivery in a two-tier cache-enabled millimeter wave (mmWave) heterogeneous network composed of a macro base station (MBS) and K small base stations (SBSs) with caching capabilities. We allocate finite cache units at the SBSs and MBS to pre-store files with high popularities, where the SBSs store the most popular files, and the MBS stores the less popular ones. To deliver the file requested by a legitimate user securely, two secure transmission schemes, namely, distributed beamforming and direct transmission, are employed at the SBSs and MBS, respectively. Moreover, artificial noise (AN) is combined with the above two transmission schemes to further improve transmission security. The connection outage probability, secrecy outage probability, and secrecy throughput for the proposed mmWave transmission schemes are obtained. Based on these results, we jointly design the transmission rates and the cache resource allocation between the SBSs and MBS to maximize the overall secrecy throughput. We also provide insights into how the overall secrecy throughput is influenced by various parameters, including transmission rates, power allocation ratio of the AN scheme, and cache allocation factor. Numerical results are eventually presented to validate our theoretical analysis and demonstrate the effectiveness of the proposed transmission schemes and cache resource allocation strategy.

Motivated by the prospects of 5G communications and industrial Internet of Things (IoT), recent years have seen the rise of a new computing paradigm, edge computing, which shifts data analytics to network edges that are at the proximity of big data sources. Although deep neural networks (DNNs) have been extensively used in many platforms and scenarios, they are usually both compute and memory intensive, thus, difficult to be deployed on resource-limited edge devices and in performance-demanding edge applications. Hence, there is an urgent need for techniques that enable DNN models to fit into edge devices, while ensuring acceptable execution costs and inference accuracy. This article proposes an on-demand DNN model inference system for industrial edge devices, called knowledge distillation and early exit on edge (EdgeKE). It focuses on the following two design knobs: first, DNN compression based on knowledge distillation, which trains the compact edge models under the supervision of large complex models for improving accuracy and speed; second, DNN acceleration based on early exit, which provides flexible choices for satisfying distinct latency or accuracy requirements from edge applications. By extensive evaluations on the CIFAR100 dataset and across three state-of-art edge devices, experimental results demonstrate that EdgeKE significantly outperforms the baseline models in terms of inference latency and memory footprint, while maintaining competitive classification accuracy. Furthermore, EdgeKE is verified to be efficiently adaptive to the application requirements on the inference performance. The accuracy loss is within 4.84% under various latency constraints, and the speedup ratio is up to 3.30× under various accuracy requirements.

In this article, we investigate the jointly optimized resource allocation with hybrid multiple access in energy-efficient industrial Internet of Things (IIoT), where some devices (e.g., those for critical control devices) have higher transmission priority and stable energy supply while some devices (e.g., those for comprehensive sensors) may not. We consider a system model supporting wireless powered IIoT devices, with certain user terminal as a potential relay for the transmission between a hybrid access point and another user terminal. Constrained by the limited energy storage, the user needs to harvest energy before relaying and only the harvested energy is utilized for the following transmission. We propose a collaborative orthogonal and nonorthogonal multiple access protocol where two cooperation schemes with and without decoding the relay message are applied. Jointly considering time sharing in the transmission process, power splitting for simultaneous wireless information and power transfer, and transmit power allocation at the cooperative user, the achievable rate regions under the Rayleigh fading channel model are derived. Based on which, an optimization problem on resource allocation strategies is formulated and discussed. Both analytical and numerical results are provided, illustrating the impact of user geometry on the achievable rates as well as the optimal resource allocation with different cooperative strategies applied in different use cases. Aiming to enhance resource utilization, energy-efficient cooperation enables the combination of various transmission modes and networking classes in large scale networks, as well as a better use of ambient radio frequency signals for wireless powered transmissions.

Wireless virtual reality (VR) is increasingly used in industrial Internet of Things (IIoTs). However, ultra-high viewport rendering demands and excessive terminal energy consumption restrict the application of wireless VR. Pervasive edge computing emerges as a promising method for wireless VR. In this article, we propose an energy-aware resource management scheme for wireless-VR-supported IIoTs. To reduce the energy consumption of VR equipments (VEs) while ensuring a smooth immersive VR experience, we formulate the viewport rendering offloading, computing, and spectrum resource allocation to be a joint optimization problem, considering content correlation between VEs, fluctuating channel conditions, and VR quality of experience. By applying dual approximation, the original problem is transformed to be a Markov decision process and an reinforcement learning (RL)-based online learning algorithm is designed to find the optimal policy. To improve the learning efficiency, the quantum parallelism is integrated into the RL to overcome “curse of dimensionality”. In the simulations, the convergence rate and the performance in terms of energy consumption and stalling rate are evaluated. Simulation results demonstrate the effectiveness of the proposed scheme.

This article studies information freshness in information update systems with nonorthogonal multiple access (NOMA). Information freshness is characterized by age of information (AoI), defined as the time elapsed since the generation of the last successfully received update. Conventional orthogonal multiple access (OMA) systems, say time-division multiple access (TDMA) systems, lead to high average AoI when a large number of users take turns to transmit their latest samples to a common receiver over a wireless medium. In contrast to OMA, NOMA allows multiple users to transmit simultaneously. Although NOMA could lead to higher packet error rates (PER) due to the wireless interference among users, we show that higher PERs do not always lead to a higher average AoI. Specifically, our experiments on software-defined radio indicate that NOMA with conventional multiuser decoding (MUD) techniques leads to higher PERs but lower average AoI than OMA does in the high SNR regime. Furthermore, to improve the AoI performance in the medium SNR regime, we combine MUD with physical-layer network coding (PNC), a technique that turns wireless interference into useful network-coding information. PNC works well even when the SNRs of different NOMA users do not differ much. This article is the first attempt to apply PNC to information update systems. Experiments show that the combined use of PNC and MUD reduces the average AoI significantly in a practical network setting. Overall, PNC-enabled NOMA is a promising solution to information update systems.

This paper comprehensively discusses the cooperative communication and computation of vehicular system. Based on the cooperative transmission, an stochastic model of vehicle-to-vehicle (V2V) communication reliability is established using probability theory. Furthermore, the computation reliability is defined as a new metric for computation offloading, and a vehicle computational performance evaluation model is also established. In order to effectively compute the required data, we combine V2V communication and vehicle computing to further characterize the coupling reliability of cooperative communications and computation systems. In addition, we propose a virtual queue model that combines queue length and vehicle privacy entropy to optimize partitioning. Finally, considering the amount of processing data and cut-off time of vehicle applications, we establish the optimal partition model of vehicle computing with the goal of maximizing the coupling reliability, and propose the coupling-oriented reliability calculation for vehicle collaboration using dynamic programming methods. Simulations show that the proposed scheme outperforms traditional approaches in terms of coupling reliability and completion rate. In addition, the allocation between local computing and data offloading is controlled by the server’s privacy perception of collaboration events.

Collaborative beamforming (CB) in wireless sensor networks (WSNs) based on a virtual node antenna array (VNAA) can increase the transmission distance and enhance the energy efficiency of sensor nodes. However, a VNAA cannot be pre-designed like the conventional antenna arrays due to the randomly deployed sensor nodes, thereby causing a high sidelobe level (SLL) which increases the interferences. In this article, we formulate a hybrid discrete and continuous optimization problem (HDCOP) for reducing the maximum SLL. HDCOP requires to solve both the discrete and the continuous problems simultaneously, and we propose both centralized and consensus-based distributed CB strategies for solving HDCOP. For the centralized strategy, we convert HDCOP into two sub-optimization problems, and propose a discrete cuckoo search (CS) algorithm for the node location selection optimization and a continuous CS algorithm to optimize the excitation current weights of the selected nodes. For the distributed strategy, we propose a parallel distributed CS algorithm to solve the discrete and continuous parts of HDCOP simultaneously. Moreover, we propose two operating mechanisms based on these two algorithms. Simulation results verify the effectiveness of the proposed strategies for reducing the maximum SLL of CB in WSNs. Moreover, the proposed CB strategies have better performance in terms of the energy efficiency compared with other approaches such as the cross-entropy optimization-based method.

In recent years, the rapid growth of traffic has become a serious problem of mobile network operators. For effectively mitigating this traffic explosion problem, there have been many efforts to research on offloading the traffic from cellular links to direct communications among users. In this paper, we are motivated by users' sharing activities, and hence propose the framework of Traffic Offloading assisted by Social network services (SNS) via opportunistic Sharing in mobile social networks (MSNs), TOSS, to offload SNS-based cellular traffic by user-to-user sharing. First, a subset of users who are to receive the same content was selected as initial population depending on their content spreading impacts in the online SNSs and their mobility patterns in the offline MSNs. Then users move, encounter and share the content via opportunistic local connectivity with each other, the content via opportunistic local connectivity with each other, e.g., Bluetooth, Wi-Fi Direct, Device-to-Device in LTE. Individual users have distinct access patterns, which potentially allow TOSS to exploit the user-dependent access delay between the content generation time and each user's access time for content sharing purposes. The traffic offloading and content spreading among users are analyzed by taking into account various options in linking SNS and MSN traces. Four mobility traces and online SNS trace for evaluation are analyzed. An extended evaluation over a large-scale data set are further carried out, and the effectiveness of TOSS is further proved.

In this paper, we consider the nonlinear least squares (NLLSs) problems in adaptive networks, where a collection of nodes with adaptation ability by learning are required to estimate a global vector parameter by minimizing the specified convex cost function. Although the global Gauss-Newton (GN) method is an excellent candidate for solving such problems, many challenges need to be addressed for practical realization due to its natures of centralization and noncooperation. Without specialized design for routing, we motivate and propose new diffusion GN methods with cooperative strategy among local neighborhoods. The good performances of diffusion cooperation schemes have been proved in different literatures, such as distribution, robustness, and easy implementation. The proposed cooperative diffusion strategies are named as aggregation-then-update (ATU) and update-then-aggregation (UTA), which reach fully information diffusion across network and consist of two steps in a reversible way including aggregation of local estimates and local GN update. Although all implementations are local, the cooperation between nodes is network wide. Based on the steady-state equilibria theory in the nonlinear discrete dynamical system, the convergence analysis of proposed algorithms is provided. The results show that the global convergence can be achieved when the sufficient conditions are satisfied. We also provide performance comparisons and analysis together with simulation to confirm the applicability and effectiveness of proposed diffusion GN algorithms.

Multi-objective resource allocation is studied for edge-caching enabled fog-radio access network. Notably, joint maximization of the energy-efficiency (EE) and spectrum-efficiency (SE) and interference management are investigated for distributing contents from the cache-enabled fog access points (F-APs) and cloud base station (CBS) to the user devices (UDs). In our envisioned system, the UDs are grouped into multiple non-overlapping device-clusters based on their locations. A rate-splitting with common message decoding based transmission strategy is applied to enable UDs of each device-cluster to receive data from a suitably selected F-AP and CBS over the same radio resource blocks. To maximize system EE and SE jointly, a multi-objective optimization problem (MOOP) is formulated and it is solved in three stages. At first, by employing the$\epsilon $-constraint method, the MOOP is converted to an EE-SE trade-off optimization problem. Then, by leveraging iterative function evaluation based power control and generalized 3D-resource matching, the EE-SE trade-off optimization problem is solved and a novel resource allocation algorithm is proposed to obtain near-optimal Pareto-front for the proposed MOOP. To reduce the complexity of obtaining near-optimal Pareto-front, a sub-optimal resource allocation algorithm is proposed as well. Finally, a low-complexity algorithm is devised to select a suitable operating EE-SE pair from the obtained Pareto-front. The conducted simulations demonstrate that the proposed resource allocation schemes achieve substantial improvement of system EE and SE over the benchmark schemes.

In this paper, we consider a wireless-powered two-way communication, calledtransmit-harvest-respond, with co-channel interference. The two-way communication considered here comprises three steps: i) transmitters send data signals, ii) receivers decode information and harvest energy simultaneously from the received signals using a policy of time switching (TS) or power splitting (PS), and iii) receivers transmit responses back to transmitters using this harvested energy. We aim to find the transmit power and energy harvesting ratios that maximize the sum rate of the forward links while ensuring a minimum rate requirement for each backward link. Due to the non-convexity and NP hardness of the optimization problem considered here, we first derive suboptimal solutions using an iterative algorithm (IA) on the basis of asymptotic strong duality. In view of the high computation time of the IA, we then design an efficient deep neural network (DNN) framework and novel training strategy as a means of combining supervised and unsupervised training. Specifically, DNNs are pre-trained using the suboptimal solutions obtained by the IA in a supervised manner, as a means of initialization; further training is then applied to DNNs using a well-designed loss function in an unsupervised manner to enhance performance. Simulation results reveal that the pre-training technique using IA solutions is beneficial for improving the performance of the DNN. The proposed hybrid scheme thus achieves near-optimal performances with a lower computation time, compared with the use of IA or DNN alone.

Media access control (MAC) plays a pivotal role in ensuring proper operation in wireless body area networks (WBANs). However, current solutions still cannot satisfy the stringent requirements of low power and low delay for emergency data reporting. In this paper, we propose an energy-efficient and emergency-aware MAC (EEEA-MAC) protocol for meeting such a rigorous demand. First, we design a node-different channel access scheme, in which source nodes use the CSMA/CA pattern while relay nodes adopt the hybrid CSMA/CA-TDMA pattern. Second, we devise an emergency-first time-slot allocation scheme, in which channel sensing is performed and the emergency data is handled by relay nodes according to different cases. EEEA-MAC has two striking features. One is that, source nodes adopt the CSMA/CA scheme instead of the conventional CSMA/CA-TDMA scheme, ensuring the requirement because there are almost no collisions and no confirmation messages in this scheme. The other is that, relay nodes use a sensing-based emergency data handling mechanism instead of the traditional empty-slot occupying mechanism, further guaranteeing the requirement owing to the immediate handling of emergency data and the short time of channel sensing. Extensive simulations demonstrate the advantages of EEEA-MAC in terms of energy dissipation and latency.

Non-orthogonal multiple access (NOMA) has been extensively studied to improve the performance of space-terrestrial satellite networks on account of the shortage of frequency band resources. In this paper, terrestrial network and satellite network synergistically provide complete coverage for ground users. A user association scheme on account of the channel gain and distance between the ground users and the BSs is proposed to identify the users to be associated by the BSs, and there is an upper limit for the number of users associated with each BS. Then calculate the channel condition ratio to select the users served by the satellite. The all BSs provide service for those unselected users, and the NOMA technology is applied to terrestrial network. Then, a user pairing scheme which maximize the minimum the ground user channel correlation coefficient is formulated to match the terrestrial users in a NOMA group. On account of multiple antennas equipped by the BSs and satellite, beamforming is performed among groups of BSs and among satellite users so as to reduce multi-user interference. In the power allocation scheme, we introduce the alternative direction method of multipliers (ADMM) algotithm so as to optimize system energy efficiency. In addition, the objective function is a non-convex function, so the Dinkelbach-style scheme is presented to convert non-convex function into the convex-form function. Eventually, the performance of the presented algorithm is simulated and compared with the existing NOMA-FTPA algorithm. The results indicate that the presented algorithm has high superiority in system energy efficiency and it can be applied to this network.

Coordinated direct and relay transmission (CDRT) is a promising strategy to extend cell coverage. However, higher spectral efficiency (SE) cannot be guaranteed in CDRT due to the cooperative process. Thus, non-orthogonal multiple access (NOMA) based CDRT is investigated, where a relaying user assists a base station (BS) in communicating with a cell-edge user (CEU) while the BS directly communicates with a cell-center user (CCU). Specifically, a novel joint downlink-uplink adaptive scheme is proposed for NOMA-based CDRT to improve the SE further. The proposed scheme jointly designs uplink and downlink via NOMA and adaptive transmission to implement bidirectional communication. First, we study the performance of the proposed scheme under both perfect and imperfect successive interference cancellation (SIC), and closed-form expressions are derived for the outage probability, diversity order, outage throughput (OT), ergodic sum rate (ESR), and energy efficiency (EE). Then, an optimal power allocation algorithm using the segment optimization and a modified particle swarm optimization algorithm are proposed to maximize the ESR under perfect and imperfect SIC, respectively. Numerical results verify the superiority of the proposed scheme in terms of the ESR, OT, EE, and the outage performance of CEU. The effectiveness of the proposed power allocation algorithms is also validated.

Network slicing is capable of satisfying differentiated service demands of vertical industries by tailoring a common infrastructure to multiple logical networks which are isolated. Considering that the dynamic of service demands makes it difficult to maintain high quality of user experience and high revenue of tenants, slice reconfiguration is necessary to avoid performance degradation. Hence, this paper proposes an optimal and fast slice reconfiguration (OFSR) solution by leveraging advanced deep reinforcement Learning. To deal with the uncertain changes in resources requirement, a demand prediction model based on Markov renewal process is introduced in decision-making. Taking into account the operation costs of reconfiguring diversified slices and the constraints of available resources, the proposed OFSR scheme aims at obtaining high long-term revenue with low operation cost. Given that the convergence of the conventional reinforcement learning approach is slow to learn the optimal reconfiguration policy for different classes of slices, deep dueling neural network combined with Q-learning is applied to improve the speed of convergence. Simulation results validate that the proposed framework is effective in achieving long-term revenue for tenants and the dueling deep Q-learning approach performs better than other current approaches.

With the tremendous growth of mobile data traffic generated by various devices such as smartphones, smartpads and wearable devices, it is necessary for mobile network operators to introduce revolutionary networking techniques, thereby satisfying service requirements of mobile users. Recently, mobile edge computing (MEC) has been regarded as an effective technique to alleviate the traffic burden on backhaul networks. In this paper, we investigate the issue of mobility-aware content caching and user association for ultra-dense MEC networks by minimizing the system costs. The problem is formulated as a complex pure integer nonlinear programming, which is NP-hard. To address the original long-term optimization problem, we decompose it into a series of one-slot subproblems, and then optimize the short-term subproblem in two phases (i.e., content caching and user association). We further propose a mobility-aware online caching algorithm to achieve content caching, and a lazy re-association algorithm to determine user association based on matching theory. Trace-driven evaluation results demonstrate that the proposed framework has superior performance on reducing system costs.

The revolutions of computing and communication have opened up demands for the high quality of service (QoS), such as high data transmission, high reliability, and low latency. These new opportunities have spawned numerous studies on edge computing and artificial intelligence (AI), even the cooperation between them, referred to as edge intelligence. However, there are a number of handicaps that prevent edge intelligence from being used as a generic platform. The most intractable one is the heterogeneity and un-credibility among edges, hindering the way of sharing the learning results reliably, flexibly, and efficiently. In this paper, we propose a blockchain-assisted edge intelligence (B-EI) approach to solve the problem. The edge learning nodes train their local intelligence, followed by the improved blockchain to share the local intelligence, constructing edge intelligence among the heterogeneous and uncredible edges. Specifically, the improved blockchain employs a novel learning-measured consensus protocol, named Proof of Learning. The edges, also acted as the blockchain nodes, compete to have more superior local intelligence, instead of solving a hashed result. The superior local intelligence is then shared and distributed with other edges. It is not only beneficial to achieve edge intelligence, but also efficient to employ the computation resource, by replacing the hashing as the intelligence training. In order to show the potential benefits, we then use the proposed B-EI approach to solve a joint resource assignment problem. Simulation results show that our scheme outperforms the other state-of-art solutions, in terms of training episodes, and resource utility.

Unmanned aerial vehicles (UAVs) can be utilized as aerial base stations to provide communication service for remote mobile users due to their high mobility and flexible deployment. However, the line-of-sight (LoS) wireless links are vulnerable to be intercepted by the eavesdropper (Eve), which presents a major challenge for UAV-aided communications. In this paper, we propose a latency-minimized transmission scheme for satisfying legitimate users' (LUs') content requests securely against Eve. By leveraging physical-layer security (PLS) techniques, we formulate a transmission latency minimization problem by jointly optimizing the UAV trajectory and user association. The resulting problem is a mixed-integer nonlinear program (MINLP), which is known to be NP hard. Furthermore, the dimension of optimization variables is indeterminate, which again makes our problem very challenging. To efficiently address this, we utilize bisection to search for the minimum transmission delay and introduce a variational penalty method to address the associated subproblem via an inexact block coordinate descent approach. Moreover, we present a characterization for the optimal solution. Simulation results are provided to demonstrate the superior performance of the proposed design.

Unmanned aerial vehicles (UAVs) are developing rapidly owing to flexible deployment and access services as air base stations. However, the energy efficiency of the UAVs cells using non-orthogonal multiple access (NOMA) with imperfect channel state information (CSI) hasnt been well studied yet. Therefore, we maximize energy efficiency in the downlink NOMA UAV network considering imperfect CSI between the UAV and users. Resource allocation schemes including user scheduling as well as power allocation are designed for system energy efficiency optimization. Because of the non-convexity of optimization function with an probability constraint for imperfect CSI, the original problem is converted into a nonprobability problem and then decoupled into two convex subproblems by successive convex approximation method. First, a user scheduling method is applied in the two-side matching of users and subchannels by the difference of convex programming. Then based on user scheduling, the energy efficiency in UAV cells is optimized through a suboptimal power allocation algorithm. The simulation results prove that our proposed algorithm is more effective compared with existing resource allocation schemes.

Secure message dissemination is an important requirement of intelligent transportation systems (ITS). Existing solutions, such as broadcasting, are effective in flooding a message to a wider area, however, they are inherently unreliable and bandwidth inefficient. Furthermore, it is difficult to both assess the authenticity of a message and maintain the privacy of sender in a single solution. Moreover, as a practical solution, there is a need of economic modeling to incentivise vehicles for safe driving and cooperation. This paper proposes a blockchain based message dissemination approach which utilises incentive distribution and reputation management to overcome these challenges. Specifically, with the proposed voting based consensus algorithm, it can assess the authenticity of a message and select the most suitable relay node for its dissemination in a completely decentralised fashion. Meanwhile, the blockchain based integrated incentive and reputation scheme encourages the cooperation among vehicles and strengthens its ability to deliver authentic messages. The security capacity of the proposed solution is demonstrated by a game theoretic analysis. Simulation results show that the proposed approach can save average consensus time by 11% and improve success rate of authentic message dissemination by 17% with less number of hops as compared to the existing solutions.

The problem of security and privacy in vehicular networks is a vital issue and it attracts increasing attention to address the security vulnerability of vehicular networks. Authentication solutions are introduced in vehicular networks to ensure that network access only comes from authorized users. Particularly, group signature not only offers authentication services in vehicular networks, but also provides conditional privacy preservation. However, the current group signature solution for authentication in vehicular networks exhibits time-consuming signature verification, which is attributed to the centralized certificate revocation list (CRL) management. To overcome this shortcoming, we propose utilizing edge computing approach and design a flexible and efficient decentralized authentication scheme (FEDAS). In the proposed architecture, a decentralized CRL management method is developed to reduce verification delay in the authentication process. In addition, transition zone is proposed to solve reliable authentication problem in border area of the group caused by decentralized architecture. We also conduct extensive simulations to show the effectiveness of our proposed scheme.

Terahertz (THz) band communication has been widely studied to meet the future demand for ultra-high capacity. In addition, multi-input multi-output (MIMO) technique and non-orthogonal multiple access (NOMA) technique with multiantenna also enable the network to serve more users. In this paper, we study the maximization of energy efficiency (EE) problem in THz-NOMA-MIMO systems for the first time. And the original optimization problem is divided into user clustering and hybrid precoding. Based on channel correlation characteristics, a fast convergence scheme for user clustering using enhanced K-means machine learning algorithm is proposed. Considering the power consumption and complexity, the hybrid precoding scheme based on the sub-connection structure is adopted. The simulation results show that the proposed scheme can achieve faster convergence and higher EE.

Explosively increasing multimedia services and applications, e.g., automatic speech recognition (ASR), have aggravated the burden on the cloud server in mobile networks. To address the challenge, mobile edge computing has emerged for partially alleviating the workload of the cloud server and enhancing the quality of service of mobile users. In this paper, we aim to employ the technique of edge-cloud computing to accelerate the processing of ASR tasks generated by users in mobile networks. Particularly, we deploy a convolutional neural network based encoder in each edge server to extract features of the audio data. Based on certain network constraints (i.e., user association and edge servers’ storage/computing capacity), we propose a low-complexity and distributed iterative greedy method to address the formulated nonlinear mixed-integer nonconvex optimization problem. Simulation results demonstrate the effectiveness of the proposed scheme on reducing the total delay in the network.

Sleeping cell problem refers to the degradation or unavailability of network services without triggered alarm, which is one of the most critical issues in current mobile networks. This problem is generally not detectable by the operators but only revealed after users’ complaints occur. Therefore, it leads to the degradations of network performance in the service provision in the long run. To address this problem, we introduce a cloud-based sleeping cell detection platform into radio access networks (RANs) to detect the sleeping cells and deal with them automatically. In the cloud RANs (C-RANs), we combine and improve different methods employed in the pioneering studies in this field, and creatively use labeled training data and ensemble learning method for improving the accuracy. Particularly, we utilize expert optimization experience for further improving the detection framework. To evaluate the proposed ensemble learning based sleeping cell detection framework, we use a time-series dataset of Key Performance Indicator (KPI) in a real-world network. Trace-driven evaluation results show that the proposed framework can achieve up to 14.38% and 20.50% improvements compared with two existing schemes, respectively.

The blockchain technology provides a data authentication and permanent storage solution to the data volatility issue in peer-to-peer games. In this work, we present the Infinity Battle, a serverless turn-based strategy game supported by a novel Proof-of-Play consensus model. Comprising three major phases: matchmaking, gaming session and global synchronization, the proposed demo game generates a blockchain through distributed storage and processing.

Fog-computing radio access network (F-RAN) and non-orthogonal multiple access (NOMA) have been recognized as the promising technologies with high mobility and low delay support. In this paper, we propose a new network architecture of the NOMA based F-RAN, and investigate the noncooperative radio resource optimization for time-varying wireless network environment. The subchannel assignment is modeled as the two-side matching issue, and deal with by the matching theory. Then, the dynamic power allocation is deal with the Lyapunov theory, which is decoupled into there subproblems. Simulations results illustrates that the dynamic resource management scheme can obtain the high utility performance gain of communication systems.

To utilize the potential commutating resources of parked vehicles (PVs) in the large parking lot, we design a large-scale parked vehicular computing system via software defined blockchain. However, the parking time for PVs is uncertain and some computational services have delay requirements. Therefore, in this paper, we propose a delay-sensitive joint blockchain parameters and resource optimization framework including block size and block generation time, as well as the offloading strategy and computing frequency adjustment. Such a design causes the problem to be highly coupled and non-convex, for which we use an alternating optimization (AO) strategy and perform multiple transformations to ensure convexity. Finally, the simulation results show the effectiveness of the proposed scheme.

Duplicated download has been a big problem that affects the users' quality of service/experience (QoS/QoE) of current mobile networks. Edge caching and Device-to-Device communication are two promising technologies to release the pressure of repeated traffic downloading from the cloud. There are many researches about the edge caching policy. However, these researches have some limitations in the real scenarios. Traditional methods are lacking the self-adaptive ability in the dynamic environment and privacy issues will occur in centralized learning methods. In this paper, based on the virtue of Deep Q-Network (DQN), we propose a weighted distributed DQN model (WDDQN) to solve the cache replacement problem. Our model enables collaboratively to learn a shared predictive model. Trace-driven simulation results show that our proposed model outperforms some classical and state-of-the-art schemes.

Recently, mobile edge computing has received widespread attention, which provides computing infrastructure via pushing cloud computing, network control, and storage to the network edges. To improve the resource utilization and Quality of Service, we investigate the issue of task offloading for End-EdgeCloud orchestrated computing in mobile networks. Particularly, we jointly optimize the server selection and resource allocation to minimize the weighted sum of the average cost. A cost minimization problem is formulated underjoint the constraints of cache resource and communication/computation resource of edge servers. The resultant problem is a Mixed-Integer Non-linear Programming, which is NP-hard. To tackle this problem, we decompose it into simpler subproblems for server selection and resource allocation, respectively. We propose a low-complexity hierarchical heuristic approach to achieve server selection, and a Cauchy-Schwards Inequality based closed-form approach to efficiently determine resource allocation. Finally, simulation results demonstrate the superior performance of the proposed scheme on reducing the weighted sum of the average cost in the network.

Bandwidth limitations in wireless networks may be prohibitive for transmitting High Dynamic Range (HDR) video content to end users to take advantage of the capabilities of HDR displays. Instead, the Standard Dynamic Range (SDR) version of the content may be transmitted, which is inverse tone mapped to the visually rich HDR format at the receiver end. One of the challenges in this approach is that the mapping process causes color shifts. Failing to address this color change, degrades the overall visual quality of the generated HDR video. In this paper, we propose a perception-based color adjustment method that is capable of preserving the hue of colors and produces HDR colors that closely follow their SDR counterparts, while causing negligible luminance change. Performance evaluations show that our method outperforms existing state-of-the-art color adjustment methods.

Traditional centralized token exchange (CEX) has been suffering from hacking due to the centralized management of users’ tokens. In contrast, decentralized token exchange (DEX) maintains users’ assets by smart contracts in a decentralized manner, but introduces additional overhead in terms of gas fee and transaction confirmation latency. Hybrid decentralized token exchange (HEX) has been proposed to combine the benefits of CEX and DEX. However, existing HEX is criticized for two issues. First, trading transactions are time-consuming and expensive for frequent token traders. Second, excessive simultaneous transactions might cause the pending transaction congestion in the Ethereum network. In this paper, we propose a payment channel based HEX, which extends existing solutions by adding a new payment channel layer to benefit frequent traders and alleviate the pending transaction congestion. Besides, we propose the very first gas-price vs. transaction-confirmation-latency function to guide Ethereum transaction issuers to choose an optimal gas price that minimizes the overall cost. Extensive simulations are conducted to compare the cost in the proposed HEX with that in the conventional HEX. The results demonstrate the effectiveness of our proposed mechanism in terms of reducing gas fees and transaction confirmation latency for frequent traders as well as the pending transaction congestion in Ethereum.

Edge caching is an emerging technology for addressing massive content access in mobile networks to support rapidly growing Internet-of-Things (IoT) services and applications. However, most current optimization-based methods lack a self-adaptive ability in dynamic environments. To tackle these challenges, current learning-based approaches are generally proposed in a centralized way. However, network resources may be overconsumed during the training and data transmission process. To address the complex and dynamic control issues, we propose a federated deep-reinforcement-learning-based cooperative edge caching (FADE) framework. FADE enables base stations (BSs) to cooperatively learn a shared predictive model by considering the first-round training parameters of the BSs as the initial input of the local training, and then uploads near-optimal local parameters to the BSs to participate in the next round of global training. Furthermore, we prove the expectation convergence of FADE. Trace-driven simulation results demonstrate the effectiveness of the proposed FADE framework on reducing the performance loss and average delay, offloading backhaul traffic, and improving the hit rate.

Social sensor cloud (SSC) is combined with social network, wireless sensor network, cloud computing, and fog computing, which is currently a new type of Internet of Things (IoT). In order to provide a convenient, open, and highly reliable SSC services, the devices of fog computing are distributed at the edge of cloud computing. The devices of fog computing can independently process and store data, and feedback more quickly in SSC. The sensing layer of SSC faces different types of physical attacks and communication attacks, such as message forgery, message tampering, reply attacks, hidden data attacks, etc., lead to the lack of trust between social sensors and cloud data centers in SSC. Therefore, the trust evaluation between the sensing layer and the network layer is necessary. However, computing the reliability of the social sensor data in cloud data centers will generate a large amount of trust computing overhead, communication overhead, and communication delay, which hinder the widespread application of SSC services. To combat this issue, a reliable trust computing mechanism (RTCM) based on multisource feedback and fog computing fusion is proposed. First, a new metric is designed for the trust of social sensor nodes, and multisource feedback trust value collection is performed at the sensing layer to improve the detection of malicious feedback nodes. Second, the trust feedback information of the sensing layer is collected by the devices of fog computing, and the recommendation trust calculation is performed, which reduces the communication delay and computing overhead. Third, a fusion algorithm is designed to aggregate different types of feedback trust values, which overcomes the limitation of trust weights in artificial weighting and subjective weighting in traditional trust mechanisms. Theoretical analyses and simulation results show that the proposed trust computing mechanism has better computational efficiency and higher reliability compared with existing methods.

Mobile wireless sensor networks (MWSNs) are resource constrained, and have limited energy and transmission range. Distributed collaborative beamforming (DCB) in MWSNs based on a virtual node antenna array (VNAA) can increase the transmission distance and enhance the energy efficiency of a single sensor node. To achieve a lower maximum sidelobe level (SLL), sensor nodes can move to optimal locations with optimal excitation current weights for DCB. However, this leads to an extra motion energy consumption. In this article, we construct a multiobjective optimization framework (MOF) to jointly optimize the maximum SLL, transmission power, and motion energy consumption of the DCB nodes in MWSNs. Moreover, an improved nondominated sorting genetic algorithm-II (INSGA-II) and a distributed parallel INSGA-II (DPINSGA-II) are proposed for solving the formulated MOF. In addition, a simple but practical DCB scheduling mechanism is proposed. The simulation results show that the maximum SLL, transmission power, and motion energy consumption of the VNAA can be effectively optimized by the proposed algorithms.

Multiuser multirelay network is a potential scenario to fulfill the transmission requirements of various sources and high-volume traffic for the Internet of Underwater Things. To efficiently complete concurrent transmissions for multiple users, this article investigates the joint relay assignment and power allocation problem for multiuser multirelay networks based on the underwater optical wireless communication (UOWC). Specifically, the multiuser multirelay network for UOWC based on decode-and-forward relaying is modeled, where the absorption, scattering, solar radiation noise, and oceanic turbulence of UOWC are all considered. The joint optimization problem of relay assignment and power allocation is formulated as a mixed-integer programming problem, where the average outage probability is minimized with the constraint of total transmitted power. To solve this joint problem, an alternating optimization method is employed, which alternately optimizes the relay assignment and power allocation subproblems. The relay assignment subproblem is modeled as a weighted bipartite matching problem and solved by an improved Kuhn-Munkres algorithm, whereas the power allocation subproblem is proved to be quasiconvex and solved by an iterative bisection algorithm. The simulation results indicate that the proposed schemes significantly reduce the average outage probability with fast convergence.

General traffic analysis based on deep packet inspection (DPI) techniques at switches cannot grasp the detailed knowledge of network applications going into internal switches, and the statistics-based reports of switches lack flow-level recognition of the traffic. Besides, DPI is generally expensive and has limited performance. Therefore, network-wise accurate flow-awareness by packet sampling is highly desirable for fine-grained quality of service guarantee, internal network management, traffic engineering, security analysis, and so on. In this paper, we propose a Spatial-Temporal Collaborative Sampling (STCS) framework in the flow-aware software-defined networks (SDNs). Particularly, considering the spatial-temporal factors and limits of network resources, the formulated STCS problem aims to maximize the network-wise sampling accuracy of flows including mice flows and elephant flows by characterizing both of the comprehensive influences of switches and the effects on sampling accuracy imposed by the collaborative strategy among switches in the spatial-temporal dimension. We propose a suboptimal approach to address the complex STCS problem in two steps: 1) Top-K switch selection based on the iterative comprehensive influence, and 2) sampling time slot allocation based on the local value maximization. Trace-driven evaluation results demonstrate the effectiveness of the proposed framework on improving the sampling accuracy and reducing redundant packets.

Terahertz (THz) band communication has been widely studied to meet the future demand for ultra-high capacity. In addition, multi-input multi-output (MIMO) technique and non-orthogonal multiple access (NOMA) technique with multi-antenna also enable the network to carry more users and provide multiplexing gain. In this paper, we study the maximization of energy efficiency (EE) problem in THz-NOMA-MIMO systems for the first time. And the original optimization problem is divided into user clustering, hybrid precoding and power optimization. Based on channel correlation characteristics, a fast convergence scheme for user clustering in THz-NOMA-MIMO system using enhanced K-means machine learning algorithm is proposed. Considering the power consumption and implementation complexity, the hybrid precoding scheme based on the sub-connection structure is adopted. Considering the fronthaul link capacity constraint, we design a distributed alternating direction method of multipliers (ADMM) algorithm for power allocation to maximize the EE of THz-NOMA cache-enabled system with imperfect successive interference cancellation (SIC). The simulation results show that the proposed user clustering scheme can achieve faster convergence and higher EE, the design of the hybrid precoding of the sub-connection structure can achieve lower power consumption and power optimization can achieve a higher EE for the THz cache-enabled network.

Energy efficiency is one of the most important concerns in cloud/edge computing systems. A major benefit of the Dynamic Voltage and Frequency Scaling (DVFS) technique is that a Virtual Machine (VM) can dynamically scale its computation frequency on an on-demand basis, which is helpful in reducing the energy cost of computation when dealing with stochastic workloads. In this paper, we study the joint workload allocation and computation resource configuration problem in distributed cloud/edge computing. We propose a new energy consumption model that considers the stochastic workloads for computation capacity reconfiguration-enabled VMs. We define Service Risk Probability (SRP) as the probability a VM fails to process the incoming workloads in the current time slot, and we study the energy-SRP tradeoff problem in single VM. Without specifying any distribution of the workloads, we prove that, theoretically there exists an optimal SRP that achieves minimal energy cost, and we derive the closed form of the condition to achieve this minimal energy point. We also derive the closed form for computing the optimal SRP when the workloads follow a Gaussian distribution. We then study the joint workload allocation and computation frequency configuration problem for multiple distributed VMs scenario, and we propose solutions to solve the problem for both Gaussian and unspecified distributions. Our performance evaluation results on both synthetic and real-world workload trace data demonstrate the effectiveness of the proposed model. The closeness between the simulation results and the analytical results prove that our proposed method can achieve lower energy consumption compared with fixed computation capacity configuration methods.

Summary In recent years, fog computing has emerged as a new distributed system model for a large class of applications that are data‐intensive or delay‐sensitive. By exploiting widely distributed computing infrastructure that is located closer to the network edge, communication cost and service response time can be significantly reduced. However, developing this class of applications is not straightforward and requires addressing three key challenges, ie, supporting the dynamic nature of the edge network, managing the context‐dependent characteristics of application logic, and dealing with the large scale of the system. In this paper, we present a case study in building fog computing applications using our open source platform Distributed Node‐RED (DNR). In particular, we show how applications can be decomposed and deployed to a geographically distributed infrastructure using DNR, and how existing software components can be adapted and reused to participate in fog applications. We present a lab‐based implementation of a fog application built using DNR that addresses the first two of the issues highlighted earlier. To validate that our approach also deals with large scale, we augment our live trial with a large scale simulation of the application model, conducted in Omnet++, which shows the scalability of the model and how it supports the dynamic nature of fog applications.

Data center benefits cloud applications in providing high scalability and ensuring service availability. However, virtual machine (VM) placement in data center poses new challenges for service provisioning. For many cloud services such as storage and video streaming, present placement approaches are unable to support network-demanding services due to overwhelming communication traffic and time. Therefore VM placement concerning link capacity is vital to cloud data centers. In this paper, we define the network-aware VM placement optimization (NAVMPO) problem based on integer linear programming. The objective function of NAVMPO problem aims to minimize communication time for VMs of the same service type. Then we propose the service-oriented physical machine (PM) selection (SOPMS) algorithm and link-aware VM placement (LAVMP) algorithm. The SOPMS algorithm selects the most appropriate PM based on service-oriented architecture, and then the LAVMP algorithm deploys the most suitable VM to target PM regarding to the link capacity between them. Simulation results show that the proposed placement approach significantly decreases communication time compared to existing non-service-oriented and service-oriented VM placement algorithms, and also improves the average utility rate of PMs with lower power consumption.

Motivated by complementing the ubiquitous wireless sensor networks (WSNs) and powerful cloud computing (CC), a lot of attention from both industry and academia has been drawn to Sensor-Cloud (SC). However, SC pricing is barely investigated. Towards pricing for SC, this paper 1) introduces five SC Pricing Models (SCPMs) first. Specifically, to charge a SC user, each SCPM considers one of the following factors respectively: i) the lease period of the SC user; ii) the required working time of SC; iii) the SC resources utilized by the SC user; iv) the volume of sensory data obtained by the SC user; v) the SC path that transmits sensory data from the WSN to the SC user. Further, this paper 2) performs analysis to discuss and exhibit the characteristics of the proposed SCPMs. With that, this paper 3) presents the case studies regarding the application of SCPMs. Eventually, this paper 4) conducts a review about the user behavior study. This paper aims to serve as a very favorable guidance for future research about pricing in SC.

User scheduling, beamforming and energy coordination are investigated in smart-grid powered cellular networks (SGPCNs), where the base stations are powered by a smart grid and natural renewable energy sources. Heterogeneous energy coordination is considered in SGPCNs, namely energy merchandizing with the smart grid and energy exchanging among the base stations. A long-term grid-energy expenditure minimization problem with proportional-rate constraints is formulated for SGPCNs. Since user scheduling is coupled with the beamforming vectors, the formulated problem is challenging to handle via standard convex optimization methods. In practice, the beamforming vectors need to be updated over each slot according to the channel variations. User scheduling needs to be updated over several slots (frame) since the frequent scheduling of user equipment can cause reliability issues. Therefore, the Lyapunov optimization method is used to decouple the problem. A practical two-scale algorithm is proposed to schedule users at each frame, and obtain the beamforming vectors and amount of exchanged natural renewable energy at each slot. We prove that the proposed two-scale algorithm can asymptotically achieve the optimal solutions via tuning a control parameter. Numerical results verify the performance of the proposed two-scale algorithm.

The boom of video streaming industry has resulted in the increasing demands for transcoding services from heterogeneous users. Recent advances of blockchain technology allow some startups to realize decentralized collaborative transcoding through device-to-device (D2D) networks, where a group of transcoders are selected to perform transcoding cooperatively. For the blockchain-enabled D2D transcoding systems, it's imperative to jointly design transcoder selection, task scheduling and resource allocation schemes in order to provide efficient and trustworthy transcoding services. In this paper, viewing the involved multi-dimensional complex factors and channel fluctuation, we propose a novel deep reinforcement learning (DRL) based transcoder selection framework for blockchain enabled D2D transcoding systems where both the platform dynamics and channel statistics are captured. To reduce the action space size, we adopt a two-stage decision approach to first select the transcoders through a normal DRL based framework and then obtain the optimal task scheduling, power control, and resource allocation scheme by solving a stochastic optimization problem with the constrained stochastic successive convex approximation (CSSCA) approach. Simulation results show that our proposed framework can achieve high transcoding revenue while meeting the quality of service (QoS) requirements, and it can well handle dynamic cases.

Explosive growth of mobile data demand may impose a heavy traffic burden on fronthaul links of cloud-based small cell networks (C-SCNs), which deteriorates users' quality of service (QoS) and requires substantial power consumption. This paper proposes an efficient maximum distance separable (MDS) coded caching framework for a cache-enabled C-SCNs, aiming at reducing long-term power consumption while satisfying users' QoS requirements in short-term transmissions. To achieve this goal, the cache resource in small-cell base stations (SBSs) needs to be reasonably updated by taking into account users' content preferences, SBS collaboration, and characteristics of wireless links. Specifically, without assuming any prior knowledge of content popularity, we formulate a mixed timescale problem to jointly optimize cache updating, multicast beamformers in fronthaul and edge links, and SBS clustering. Nevertheless, this problem is anti-causal because an optimal cache updating policy depends on future content requests and channel state information. To handle it, by properly leveraging historical observations, we propose a two-stage updating scheme by using Frobenius-Norm penalty and inexact block coordinate descent method. Furthermore, we derive a learning-based design, which can obtain effective trade-off between accuracy and computational complexity. Simulation results demonstrate the effectiveness of the proposed two-stage framework.

The studies on signed networks have received a great attention due to their capabilities on presenting conflicting relationships, which reflect the potential conflicts and tensions of complex systems. To further understand those conflicts and tensions, many methods have been proposed for computing the global structural balance (GSB) of signed networks, which aim to discover the most balanced state of the networks with the least number of unbalanced links. However, most of them request full access to all information (structures, signs, and balance states) of links, which are usually sensitive and private. In this article, we propose a privacy-preserving GSB computation (PGSBC) framework, which aims to compute the GSB while preserving the privacy of the networks. The PGSBC first protects the sensitive information (structures, signs, and balance states) of links by using encryption techniques (the homomorphic cryptosystem and the random disturbances) and then computes the GSB of the signed networks on the encrypted structures. In the PGSBC, a balance-aware energy function is adopted to evaluate the balance degree of a clustering, while a fast two-level greedy algorithm (called as HM-Louvain) is presented to discover the most balanced clustering of signed networks. Simulation results on 11 LFR benchmark networks and 10 real signed networks show that the proposed framework can effectively compute the GSB of the networks while preserving the privacy of links’ sensitive information.