Multi-agent multi-objective systems (MAMOS) have emerged as powerful frameworks for modelling complex decision-making problems across various real-world domains, such as robotic exploration, autonomous traffic management, and sensor network optimisation. MAMOS enhances scalability and robustness through decentralised control and more accurately captures inherent trade-offs between conflicting objectives. In MAMOS, each agent uses utility functions that map return vectors to scalar values. Existing MAMOS optimisation methods face significant challenges in handling heterogeneous objective and utility function settings, where training non-stationarity is intensified due to private utility functions and the associated policies. In this paper, we first theoretically prove that direct access to, or structured modeling of, global utility functions is necessary to achieve the Bayesian Nash Equilibrium under decentralised execution constraints. To access the global utility functions while preserving the decentralised execution, we propose an Agent-Attention Multi-Agent Multi-Objective Reinforcement Learning (AA-MAMORL) framework. Our approach implicitly learns a joint belief over other agents’ utility functions and their associated policies during centralised training, effectively mapping global states and utilities to each agent's policy. During execution, each agent independently selects actions based on local observations and its private utility function to approximate a BNE, without relying on inter-agent communication. We evaluate our framework through extensive experiments in a custom-designed MAMO Particle environment and the standard MOMALand benchmark. The results demonstrate that accessibility to global preferences and our proposed AA-MAMORL significantly improves performance and consistently outperforms state-of-the-art methods.

Discrete event network simulator (DES) is a fundamental service for the design, validation and optimization of various networked systems, including traditional computer networks and the recent LLM training/inference systems. Efficient DES is strongly demanded by the community yet not delivered. The reason is: while DES allows for node-level parallelism, its concurrency potential has been significantly under-utilized (usually <5%) due to the limited number of CPU cores. Meanwhile, GPUs, with thousands of cores, have long been overlooked in the design of DES systems due to the incompatibility between GPUs' SIMT architecture and DES's sequential model. In this paper, we aim to achieve ground-breaking performance improvement for DES by designing a novel GPU-driven simulation engine. By carefully manipulating the life cycles of network events and orchestrating them with long- and short-term alignments, we overcome the incompatibility barriers and established GeDES, a high-level parallel and cost-effective DES system. Extensive simulation experiments show that GeDES significantly boosts DES by 33-2400X speedups compared to the SOTA works Unison and DONS. The code is available at https://github.com/mobinets/GeDES.

Fake news detection has been a long-standing research focus in social networks. Recent studies suggest that incorporating sentiment information from both news content and user comments can enhance detection performance. However, existing approaches typically treat sentiment features as auxiliary signals, overlooking role differentiation, that is, the same sentiment polarity may originate from users with distinct roles, thereby limiting their ability to capture nuanced patterns for effective detection. To address this issue, we propose SARC, a Sentiment-Augmented Role Clustering framework which utilizes sentiment-enhanced deep clustering to identify user roles for improved fake news detection. The framework first generates user features through joint comment text representation (with BiGRU and Attention mechanism) and sentiment encoding. It then constructs a differentiable deep clustering module to automatically categorize user roles. Finally, unlike existing approaches which take fake news label as the unique supervision signal, we propose a joint optimization objective integrating role clustering and fake news detection to further improve the model performance. Experimental results on two benchmark datasets, RumourEval-19 and Weibo-comp, demonstrate that SARC achieves superior performance across all metrics compared to baseline models. The code is available at: https://github.com/jxshang/SARC.

Signed Graph Neural Networks (SGNNs) have achieved outstanding performance in Link Sign Prediction (LSP), which involves predicting the existence and polarity of edges, by effectively modeling positive and negative interactions in signed graphs. However, their black-box nature raises transparency concerns, necessitating faithful explanations of model behavior to ensure trustworthiness and accountability. Existing eXplainable GNN (XGNN) methods, primarily designed for unsigned graphs, struggle to provide meaningful and human-understandable explanations for SGNN-based LSP, often generating disconnected subgraph explanations or neglecting the unique sign interactions. To address the gap, we propose SGExplainer, a novel method that leverages balanced paths, a concept rooted in signed graph theory, to provide clear and faithful explanations for LSP. SGExplainer employs a path-enforcing mask learning framework that ensures interpretable balanced path generation while maintaining explanation fidelity. Extensive experiments on real-world signed graphs demonstrate that SGExplainer consistently provides faithful and intuitive explanations for various SGNNs, outperforming state-of-the-art baselines in explanation quality, interpretability, and efficiency.

High-quality GPS trajectories are essential for location-based web services and smart city applications, including navigation, ride-sharing and delivery. However, due to low sampling rates and limited infrastructure coverage during data collection, real-world trajectories are often sparse and feature unevenly distributed location points. Recovering these trajectories into dense and continuous forms is essential but challenging, given their complex and irregular spatio-temporal patterns. In this paper, we introduce a novel diffusion model for TRA jectory rEC overy named TRACE, which reconstruct dense and continuous trajectories from sparse and incomplete inputs. At the core of TRACE, we propose a State Propagation Diffusion Model (SPDM), which integrates a novel memory mechanism, so that during the denoising process, TRACE can retain and leverage intermediate results from previous steps to effectively reconstruct those hard-to-recover trajectory segments. Extensive experiments on multiple real-world datasets show that TRACE outperforms the state-of-the-art, offering >26% accuracy improvement without significant inference overhead. Our work strengthens the foundation for mobile and web-connected location services, advancing the quality and fairness of data-driven urban applications. Code is available at:~ https://github.com/JinmingWang/TRACE

Graph-structured data effectively captures complex relationships in diverse domains such as social networks, financial transactions, citation networks, and recommendation systems. Graph Neural Networks (GNNs) excel in learning intricate topological patterns, yielding strong performance on tasks like node classification and link prediction. However, real-world graphs often scale to millions of nodes and billions of directed edges, posing significant computational and storage challenges for GNN training that frequently exceed available hardware limits. Although graph sampling and distillation techniques alleviate these issues by subsampling or creating surrogate graphs, they primarily handle undirected graphs, neglecting directional semantics that are crucial for applications like fraud detection and causal analysis. To address these limitations, we introduce the Directed Graph Distillation (Dir-GD) framework, which combines distributed learning with community detection to divide large directed graphs into independent subgraphs for distributed directed GNN training. This process culminates in parameter aggregation to produce a compact global synthetic graph that preserves essential topology and directionality. Extensive experiments on large-scale datasets, such as the million-node soc-pokec-relationships, demonstrate over 91% accuracy at 0.001 distillation ratios, accompanied by substantial memory and runtime savings. This work pioneers directed graph distillation as a key paradigm for analyzing ultra-large directed graphs, offering a scalable solution that maintains high fidelity in compressed representations.

Adaptive traffic signal control (ATSC) is essential for mitigating urban congestion in modern smart cities, where traffic infrastructure is evolving into interconnected Web-of-Things (WoT) environments with thousands of sensing-and-control nodes. However, existing methods face a critical scalability-coordination tradeoff: centralized approaches optimize global objectives but become computationally intractable at city scale, while decentralized multi-agent methods scale efficiently yet lack network-level coherence, resulting in suboptimal performance. In this paper, we present HALO, a hierarchical reinforcement learning framework that addresses this tradeoff for large-scale ATSC. HALO decouples decision-making into two levels: a high-level global guidance policy employs Transformer-LSTM encoders to model spatio-temporal dependencies across the entire network and broadcast compact guidance signals, while low-level local intersection policies execute decentralized control conditioned on both local observations and global context. To ensure better alignment of global-local objectives, we introduce an adversarial goal-setting mechanism where the global policy proposes challenging-yet-feasible network-level targets that local policies are trained to surpass, fostering robust coordination. We evaluate HALO extensively on multiple standard benchmarks, and a newly constructed large-scale Manhattan-like network with 2,668 intersections under real-world traffic patterns, including peak transitions, adverse weather and holiday surges. Results demonstrate HALO shows competitive performance and becomes increasingly dominant as network complexity grows across small-scale benchmarks, while delivering the strongest performance in all large-scale regimes, offering up to 6.8% lower average travel time and 5.0% lower average delay than the best state-of-the-art.

Simultaneous wireless information and power transfer (SWIPT) has emerged as a cornerstone technology for sustainable connectivity in sixth-generation (6G) space–air–ground integrated networks (SAGIN). This paper proposes a unified signal design framework that jointly supports radio-frequency (RF) coherent reception and noncoherent energy detection with colocated or separated deployments of information/energy receivers (IR/ER), thereby bridging RF and intensity-modulation/direct-detection (IM/DD) optical links. Guided by reliability, spectral efficiency, and harvested power metrics, we develop a generalized signal design framework based on a refined sphere-packing aimed at constructing high-dimensional symbols across space-time-frequency resources subject to symbol-level wireless power transfer constraints and an average power budget. The resulting nonconvex quadratically constrained quadratic program (QCQP) is efficiently solved using an alternating semidefinite programming–linear programming (ASDP–LP) method and an augmented Lagrangian dual-ascent (ALDA) algorithm. Analytical and simulation results confirm that the proposed approach achieves significant gains in communication-power trade-offs compared with conventional schemes, providing a foundation for sustainable RF–optical SWIPT in future 6G integrated networks.

With the proliferation of cloud computing, the exponential growth of data amount requires continuous expansion of storage capacity to meet the storage demand, consequently resulting in higher energy consumption in data centers. However, many of the conventional data placement strategies strive to save energy by optimizing the distribution of data requests, while overlooking the impact of heat recirculation among data nodes. To bridge this gap, we propose a heat-recirculation-aware data placement approach, termed HRADP, designed to optimize data placement in data centers while reducing energy consumption. First, based on the extent of heat recirculation, HRADP places data to the upper limit of the disk allowance for each data node. Second, during energy allocation, HRADP further eliminates disks with high current workloads to prevent localized hotspots. Finally, during request scheduling, HRADP selects dormant data nodes according to the request size, minimizing the startup energy consumption caused by data nodes waking up with small requests. We implement the HRADP approach on a data center simulation platform, CloudSim, and its performance with state-of-the-art, including the Energy-efficient and Thermal-aware Data Placement (ETDP) algorithm, Thermal-aware file assignment technique (TIGER), Storage and rack-sensitive replica placement algorithm (SRS), and Hadoop Distributed File System (HDFS). The experimental results reveal that HRADP revamps the cooling supply temperature, total energy, and data throughput by averages of 0.08%-0.6%, 8.22%-53.03%, and 9.58%-64.59%, respectively.

Pre-trained Language Models (PLMs) have demonstrated their superiority and versatility in modern Natural Language Processing (NLP), effectively adapting to various downstream tasks through further fine-tuning. Federated Parameter-Efficient Fine-Tuning (FedPEFT) has emerged as a promising solution to address privacy and efficiency challenges in distributed training for PLMs on resource-constrained local devices. However, our measurements reveal two key limitations of FedPEFT: heterogeneous data across devices exacerbates performance degradation of low-rank adaptation, and a fixed parameter configuration results in communication inefficiency. To overcome these limitations, we propose FedARA, a novel Adaptive Rank Allocation framework for federated parameter-efficient fine-tuning of language models. Specifically, FedARA employs truncated Singular Value Decomposition (SVD) adaptation to enhance similar feature representation across clients, significantly mitigating the adverse effects of data heterogeneity. Subsequently, it utilizes dynamic rank allocation to progressively identify critical ranks, effectively improving communication efficiency. Lastly, it leverages rank-based module pruning to automatically remove inactive modules, steadily reducing local computational cost and memory usage in each federated learning round. Extensive experiments show that FedARA consistently outperforms baselines by an average of 6.95% to 8.49% across various datasets and models under heterogeneous data while significantly improving communication efficiency by 2.40×. Moreover, experiments on various edge devices demonstrate substantial decreases in total training time and energy consumption by up to 48.90% and 46.95%, respectively.

Communication overhead is a critical challenge in federated learning, particularly in bandwidth-constrained networks. Although many methods have been proposed to reduce communication overhead, most focus solely on compressing individual gradients, overlooking the temporal correlations among them. Prior studies have shown that gradients exhibit spatial correlations, typically reflected in low-rank structures. Through empirical analysis, we further observe a strong temporal correlation between client gradients across adjacent rounds. Based on these observations, we propose GradESTC, a compression technique that exploits both spatial and temporal gradient correlations. GradESTC exploits spatial correlations to decompose each full gradient into a compact set of basis vectors and corresponding combination coefficients. By exploiting temporal correlations, only a small portion of the basis vectorsneed to be dynamically updated in each round. GradESTC significantly reduces communication overhead by transmitting lightweight combination coefficients and a limited number of updated basis vectors instead of the full gradients. Extensive experiments show that, upon reaching a target accuracy level near convergence, GradESTC reduces uplink communication by an average of 39.79% compared to the strongest baseline, while maintaining comparable convergence speed and final accuracy to uncompressed FedAvg. By effectively leveraging spatio-temporal gradient structures, GradESTC offers a practical and scalable solution for communication-efficient federated learning.

Memristor-based Hopfield neural networks (MHNNs) exhibit rich chaotic dynamics and bear closer hardware resemblance to the biological brain, making them well suited for emulating neural dynamical behaviors. However, most existing MHNNs are constructed with first-order memristors. This paper proposes a novel second-order memristor (SOM) approach for constructing MHNNs with enriched chaotic dynamics. Specifically, a second-order memristor is incorporated into a three-neuron Hopfield neural network to emulate the magnetic coupling mechanism between neurons, thereby forming a second-order memristor-based neural network (SOM-HNN). Comprehensive dynamical analyses, including bifurcation diagrams, Lyapunov exponent spectra, and numerical simulations, confirm that the proposed SOM-HNN exhibits richer and more intricate chaos behaviors than its first-order counterparts. Remarkably, the proposed SOM-HNN can simultaneously generate butterfly and scroll attractors, multi-butterfly and multi-scroll attractors, as well as initial-boosed coexisting multi-butterfly and multi-scroll attractors, thereby substantially enhancing its dynamical diversity. To the best of our knowledge, this is the first report of both multi-butterfly and multi-scroll dynamics in a neural network. Furthermore, the SOM-HNN is implemented in hardware using analog circuits and a digital field-programmable gate array (FPGA) platform. Experimental results demonstrate the network’s abundant dynamical features and its feasibility for efficient hardware realization in neuromorphic engineering applications.

Unmanned aerial vehicle (UAV) aided Mobile Edge Computing (MEC) has emerged as a promising technique to offer computing support for high-mobility and high-demand mobile devices (MDs). However, due to the dynamic scale of UAVs and MDs as well as their changeable resource availability and demands, it is very challenging to quickly make suitable UAV deployment plans for satisfying the real-time requirements. Existing solutions commonly adopt the centralized decision-making manner based on the global information, which leads to poor scalability, excessive search time, and repeated training costs. To address these important challenges, we propose a novel Federated deep Reinforcement learning based UAV Deployment optimization method (FRUD) for multi-UAV-aided MEC systems, aiming to minimize the average task response time via optimizing the real-time deployment locations of large-scale UAVs. In FRUD, each UAV independently conducts the deployment decision-making based on the local information of runtime environments rather than using the global information. Next, through feedback control and multi-UAV cooperation, an effective UAV deployment plan can be gradually formed. Simulation results show that the proposed FRUD well handles the UAV deployment problem in large-scale and dynamic multi-UAV-aided MEC systems and outperforms the state-of-art methods.

Owing to the on-demand deployment, low cost, and flexibility, unmanned aerial vehicles (UAVs) are capable of performing tasks such as data monitoring, collection, and sharing. However, the openness of UAV wireless networks makes data susceptible to security threats such as theft, tampering, and forgery during collaborative data sharing and mission execution. Additionally, the limited resources and high mobility of UAVs further exacerbate challenges related to data security and reliability. To address these issues, this paper proposes a blockchain-based secure data sharing scheme for cloud-assisted multi-UAV networks. Specifically, we leverage cloud-based infrastructure to undertake the storage of massive data, significantly offloading the computational and storage burdens on the UAVs. Simultaneously, blockchain is integrated to establish immutable and traceable trust for the shared data, ensuring strong security, integrity, and retrievability under the constraints of UAV resources. On this basis, a certificateless searchable encryption algorithm is employed to eliminates traditional certificates management overhead and enables lightweight, distributed, and efficient search based on predefined keywords. Furthermore, we introduce an access control list based on geofencing to specify the data sharing permissions of UAVs, strictly limiting the data access permissions within specific area, thereby reducing the misuse or abuse of data. This scheme is proven to achieve ciphertext and trapdoor indistinguishability against keyword guessing attacks. The performance analysis indicates that the efficiency advantages of the proposed scheme become increasingly prominent as the number of UAVs increases.

Vehicle-to-everything (V2X) communication plays an essential role in the Internet-of-Vehicles (IoV) systems. However, in practice the diverse decision objectives of different users and the highly dynamic nature of IoV cause great challenges in realizing efficient data transmission. This paper investigates a sequential power control problem in a typical V2X communication network formed by multiple data delivery links, and proposes a novel decision framework from the perspective of dynamic multi-objective optimization (DMO). The framework is developed based on the dynamic multi-objective optimization evolutionary algorithm (DMOEA). When the variation of channel fading state is detected, an innovative environment change response mechanism is implemented to predict the centroid change of the Pareto optimal set (PS) in the new environment. This allows to properly generate the initial population for the subsequent evolutionary search process, and rapidly track the time-varying Pareto optimal front (PF). The effectiveness and advantages of the proposed framework over conventional solutions are validated by simulation results.

The core function of quantum networks is to establish high-fidelity quantum entanglement for long-distance communication. However, the main challenge is to efficiently allocate resources under limited conditions, maximize throughput, satisfy end-to-end (E2E) fidelity requirements, and prevent quantum decoherence caused by inefficient routing algorithms. Current research focuses on optimizing either throughput or fidelity, with a lack of approaches that optimize both simultaneously; furthermore, existing algorithms suffer from high computational complexity. To tackle these challenges, this study proposes a Satisfying Fidelity Threshold Routing and Adaptive Purification Strategy (SFTRAP). SFTRAP maximizes throughput for each request by selecting multiple paths and dynamically choosing links for entanglement purification based on the current state of link resources, thus minimizing throughput loss while satisfying fidelity threshold. The strategy also adaptively adjusts the number of purification rounds according to the fidelity threshold, thereby optimizing the time required for deep purification and enhancing algorithmic efficiency. For multi-request scenarios, SFTRAP employs a priority sorting mechanism that takes into account both path cost and path freedom, which refines request scheduling and path selection to create more efficient request combinations, thus further boosting the overall network throughput. Simulation results indicate that SFTRAP surpasses state-of-the-art methods in terms of both throughput and algorithmic efficiency, highlighting its potential for optimizing resources in quantum networks.

The increasing demand for autonomous and open peer-to-peer (P2P) data sharing has driven the widespread adoption of decentralized file systems, such as the InterPlanetary File System (IPFS). However, decentralized data sharing inherently requires distributed access control mechanisms due to the absence of centralized authorities. Although blockchain-based access control has become a primary solution, the public nature of blockchain can unintentionally reveal user attributes, posing significant privacy risks. To address the leakage of attribute sets in blockchain, we propose zk-Guard, a decentralized access control framework integrating blockchain and zero-knowledge Succinct Non-interactive Arguments of Knowledge (zk-SNARKs) tailored for IPFS. To further improve the efficiency of zero-knowledge policy checking and reduce the delay of policy updating, we employ a universal constraint circuit and encode policies into sparse configuration matrices, achieving fine-grained, rapid policy updates without regenerating proving keys while guaranteeing constant-time verification regardless of policy complexity. Additionally, to prevent repeated permission checks for large f iles and improve system responsiveness, zk-Guard integrates Merkle Tree Proof (MTP) mechanisms to securely link sub-data blocks to their root block. Comprehensive theoretical complexity analysis and extensive experiments demonstrate that zk-Guard achieves substantial performance improvements over existing schemes, with constant-time proof verification under 2.5 ms enabling efficient data retrieval, and policy deployment and updates completed within 0.2 seconds even for 1,000 attributes. The source code is available at https://github.com/ningboliucug/zk-Guard.

LoRa networks have become a key enabling technology for the Industrial Internet of Things (IIoT) due to the low cost, wide coverage, and easy deployment. However, the lifetime of Industrial LoRa Networks (ILNs) leaves much to be desired due to the star topology used, i.e., the energy consumption of nodes at network edges is much higher than those near the gateway. Existing works deploy additional gateways to improve network lifetime, however, this is often limited by hardware cost and geographical constraints. In this article, we propose to trade the long communication range for better network performance by introducing intranetwork relays into ILNs. The fine-grained global views and strict time synchronization in ILNs allow us to establish multihop relays within a network, thus supporting more energy-efficient parameters at edge nodes for enhancing network lifetime. We investigate the unique challenges of LoRa relays in ILNs, and then propose HybLoRa, a novel hybrid framework which adaptively assign relays and configure nodes based on a gain-driven minimum spanning tree (MST). We conduct real-world experiments and large-scale simulations. The results show that compared with single-hop EXPLoRa, HybLoRa can reduce total network energy consumption by 36.1% and improve network lifetime by 67.2% .

Modern navigation systems and logistics services rely heavily on digital road networks, which can be accurately constructed from crowd-sourced GPS trajectories. Yet, most existing trajectory-based road network generators project GPS coordinates to 2D grid, followed by semantic segmentation to obtain road heatmap, and further processed to road network graph via heuristic processing. The data through this pipeline involve multiple cross-modal heuristic conversions, which cause serious information loss and harm overall robustness. In this paper, we propose a novel end-to-end learnable deep learning approach, named GraphWalker, to generate accurate road network graphs directly from raw trajectories with minimal information loss. In particular, GraphWalker is a latent diffusion model (LDM) consisting of two key components: theTrajectory-to-Walks Diffusion Transformer(T2W-DiT) generateswalkswith trajectories as conditions, and theWalks-to-Graph Variational Auto-Encoder(W2G-VAE) reconstructs road network graphs from walks. GraphWalker keeps the data in geographical space throughout the pipeline to retain all information within raw trajectories. Additionally, the end-to-end learnable design removes the heuristic processing and enhances the robustness and generalizability. Extensive experiments on multiple datasets demonstrate that the proposed GraphWalker can effectively generate high-quality road networks from noisy and sparse trajectories, showcasing significant improvements of up to 55.43% over state-of-the-art.

Quasi-clique is one of the most fundamental models for characterizing cohesive subgraphs in network analysis. However, existing quasi-clique definitions and identification algorithms are designed for unsigned graphs, while many real-world networks are modeled as signed graphs with positive and negative edges representing cooperative and adversarial interactions between entities. Therefore, it remains an open problem to define a quasi-clique model tailored for signed graphs. Motivated by this, we propose the maximal balanced \( (\gamma_{1},\gamma_{2}) \) -quasi-clique (MBQC) model, which not only preserves the essence of quasi-completeness but also aligns with the foremost structural balance theory for signed graphs. Specifically, we formulate the problem of MBQCs enumeration in a given signed graph and prove its NP-hardness. To address this problem, we devise a novel branch-and-bound algorithm to efficiently enumerate all MBQCs in a signed graph, which is further optimized with several carefully-crafted techniques to prune unpromising search spaces and enhance enumeration efficiency. Extensive experiments on real-world datasets demonstrate the efficiency, scalability, and effectiveness of our MBQC model and algorithms.

Fake news detection is a hot topic in the social media mining research community. Recent studies have shown that sentiment signals could significantly benefit the detection performance. However, most existing methods treat sentiment merely as auxiliary features, while the more sophisticated social sentiment interactions were rarely explored. In this paper, we propose a novel framework named ReFEND, which leverages the sentiment resonances among the social users (i.e., social sentiment resonances) and the sentiment relationship between news content and user comments to improve the detection performance. Specifically, we first utilize sentiment scorers to assess the sentiment of comments and identify users' emotional tendencies. Then we creatively construct a sentiment-aware multi-relational graph to capture social sentiment resonances evoked by the content and the interactions between comments and news. Next, we leverage the relational graph convolutional network (RGCN), which specializes in handling multi-relational graph data, to learn the interactions on sentiment-aware graph. To our best knowledge, this is the first effort to leverage social sentiment resonances for fake news detection. Experimental results on three datasets indicate that ReFEND significantly outperforms the state-of-the-art sentiment-based methods in terms of F1 and accuracy. Besides, ablation studies demonstrate the effectiveness of components designed in ReFEND.

Nowadays, social media platforms have become primary channels for dissemination of fake news. On these platforms, user comments provide direct reactions and insights into the content being shared, offering valuable clues for effective fake news detection. However, existing approaches predominantly analyze comments from an isolated, single-comment perspective, overlooking the broader insights from the entire comment section. To address this limitation, this paper comprehensively considers three key factors within the comment section: emotional evolution, semantic evolution, and diversity of user attention, based on which a novel fake news detection model MESE is proposed by mining the emotional and semantic evolution from user comments. Specifically, to capture the diversity of user attention toward different news segments, we first propose a news-conditioned comment attention mechanism to obtain news-enhanced comment representations. Next, a gating mechanism is introduced to deeply integrate emotional and semantic features. Additionally, we develop a comment emotional and semantic evolution module to capture shifts in public reactions over time. Finally, these diverse representations are fused to generate prediction results. Extensive experiments on two public datasets demonstrate the superior performance of MESE. Further case studies and ablation experiments validate the rationality of our design and the effectiveness of the model components.

The integration of satellite communications with mobile edge computing (MEC) into space-air-ground integrated networks, known as satellite edge computing (SEC), has become a crucial research field for future communication systems to provide extensive global coverage services. This paper investigates the joint dependent task offloading and resource allocation problem for remote Internet-of-Things (IoT) applications within the SEC architecture. The proposed system leverages unmanned aerial vehicles (UAVs) as mobile access points and edge servers and utilizes low- earth orbit (LEO) satellites and ground stations as cloud computing resources. Multiple applications with dependent tasks from IoT devices (IoTDs) are modeled as directed acyclic graphs (DAGs). To address the challenges of reducing the system cost in UAV-assisted SEC, we first propose a one-to-many matching algorithm to associate IoTDs with UAVs. Then, a multi-application task sequence algorithm is devoted to merging the multiple DAGs and sorting the task order. Finally, a graph-aware asynchronous multi-agent reinforcement learning approach empowers the agents to autonomously discover optimal offloading and resource allocation strategies. Extensive simulations based on real-world datasets demonstrate the effectiveness of the proposed approach in minimizing the system costs while meeting application latency requirements, outperforming other benchmark algorithms.

Automotive Ethernet as an in-vehicle networking paradigm has gradually become the main automotive backbone network. However, with the ever-increasing time-critical in-vehicle traffic, it is being confronted with enormous challenges to realize deterministic-latency communications, due to the inherent limitations of its distributed network architecture and the adopted MAC protocols, including limited-computing power, low-speed and unreliable traffic transmission. Furthermore, it is often incompatible with emerging vehicular functions and protocols, which can provide tremendous potential for better vehicular Quality-of-Service (QoS). Therefore, in this paper, we first design a Future Automotive Ethernet (FAE) architecture and then, built on the representative Time-Sensitive Networking (TSN) and industrial summation frame, propose a Deterministic-Latency MAC (DLM) protocol running in FAE to tackle these issues. The FAE architecture includes three functional domains, three in-vehicle computing units, and no fewer than three intelligent network processing modules, which can integrate with the emerging LAN protocols to realize cross-domain and intra-domain Ethernet-based communications. Under the umbrella of this architecture, DLM classifies the driving situations into driving, reversing, left turn, right turn and parking states, following the real-world vehicle behaviors, and assigns all traffic associated with driving safety in five states different recommended priorities to be delivered. Furthermore, an optimized deterministic-latency mechanism integrated with TSN and the industrial summation frame is developed to realize the timely and accurate transmission of high-priority and medium/low-priority traffic. Simulation results obtained from diversified scenarios demonstrate that the proposed DLM running in FAE can significantly improve transmission latency determinacy and reliability compared with the existing technical strategies.

The deployment of multimodal large language models (MLLMs) in edge-cloud networks faces critical challenges, including computational resource heterogeneity, memory bottlenecks, and bandwidth constraints. To address these issues, we propose EdgeSD, a novel framework that accelerates MLLM inference by integrating speculative decoding (SD) with edge-cloud collaboration. First, EdgeSD decouples the vision encoding and decoding processes of the draft MLLM across heterogeneous edge servers (ESs). This disaggregation architecture overcomes single-node memory constraints, enabling optimized resource utilization and high-resolution input processing. Second, to resolve the communication bottleneck and computational burden inherent in this distributed architecture, EdgeSD integrates a bandwidth-aware dynamic image token merging (ITM) method. Unlike general pruning techniques, this EdgeSD-specific ITM method focuses on minimizing inter-ES transmission latency for vision-decoding disaggregation while maintaining draft quality. Third, to optimize SD efficiency on consumer-grade ESs, EdgeSD employs an adaptive and scalable token tree structure solved using a parallel delta-stepping algorithm. This structure maximizes the number of accepted tokens under strict edge latency constraints. Extensive experiments on six multimodal datasets and five benchmarks with various MLLM pairs demonstrate that EdgeSD achieves substantial acceleration and throughput gains in edge-cloud collaboration scenarios using a lightweight draft MLLM, achieving 3.04-5.12x speedup compared to baseline methods.

Mobile Crowdsensing (MCS) is a new data acquisition method that has emerged with the proliferation of smart mobile devices. With the expanding scale of urban sensing, the locations of tasks and users become critical information, which plays a significant role in crowd-sensing and task scheduling areas. Tasks in areas with a high concentration of users can be completed quickly, whereas tasks in sparsely populated areas are challenging to accomplish. To address this issue, existing research has primarily focused on task assignment to designated users, assuming that users' motivations are rational, while neglecting the impact of psychological factors on their motivations. Therefore, we propose an incentive mechanism based on prospect theory, analyzing the decisions users might make under irrationality and then adjusting corresponding rewards to influence user decisions. This paper transforms the problem of maximizing the data value in crowdsensing into an ordered submodular function model. Our proposed incentive mechanism consists of three components: User Decision-Making, User Selection, and Payment Determination. In the User Decision-Making phase, users calculate the prospect value based on the auction results from the previous round to make decisions. In the User Selection phase, users are chosen based on marginal value. In the Payment Determination phase, rewards for winning users are designed based on the ordered submodular model. The platform provides auction results as a reference for the next round. In the experimental section, we demonstrate that the incentive mechanism can enhance the platform's value.

In vehicular edge computing (VEC) networks, by implementing content caching and V2X connectivity, road side unit (RSU) and nearby vehicles can serve as platforms for rapid data retrieval to address mobile traffic explosion. However, due to the dynamic and multi-constrained environment consisting of heterogeneous vehicles and RSU, it is challenging to meticulously plan cooperative caching policies. Additionally, due to the diversity of contents and the mobility of vehicles, the caching policy space is massive, which can be fatal for vehicles with limited computing and energy. In this paper, we formulate cooperative content caching in VEC networks as Markov decision process (MDP), configuring caching policies for vehicles and RSU. Our aim is to minimize Lyapunov drift and long-term delay. To address the massive caching policies, we propose a two-stage deep reinforcement learning (TS-DRL) algorithm. In the first stage, an improved ant colony algorithm is used to generate unilateral suggestions and construct action space to avoid the curse of dimensionality. In the second stage, we combine the Noisy Net and Double Deep Q-Learning Network to avoid overestimating value and efficient exploration problem. Simulation results show that TS-DRL outperforms advanced algorithms in terms of delay and cache hit rate.

The convergence of edge computing and Artificial Intelligence (AI) gives rise to Edge-AI, which enables the deployment of real-time AI applications at the network edge. A key research challenge in Edge-AI is edge inference acceleration, which aims to realize low-latency high-accuracy Deep Neural Network (DNN) inference by offloading partitioned inference tasks from end devices to edge servers. However, existing research has yet to adopt a practical Edge-AI market perspective, which would explore the personalized inference needs of AI users (e.g., inference accuracy, latency, and task complexity), the revenue incentives for AI service providers that offer edge inference services, and multi-stakeholder governance within a market-oriented context. To bridge this gap, we propose anAuction-basedEdge Inference Pricing Mechanism (AERIA) for revenue maximization to tackle the multi-dimensional optimization problem of DNN model partition, edge inference pricing, and resource allocation. We develop a multi-exit device-edge synergistic inference scheme for on-demand DNN inference acceleration, and theoretically analyze the auction dynamics amongst the AI service providers, AI users and edge infrastructure provider. Owing to the strategic mechanism design via randomized consensus estimate and cost sharing techniques, the Edge-AI market attains several desirable properties. These include competitiveness in revenue maximization, incentive compatibility, and envy-freeness, which are crucial to maintain the effectiveness, truthfulness, and fairness in auction outcomes. Extensive simulations based on four representative DNN inference workloads demonstrate that AERIA significantly outperforms several state-of-the-art approaches in revenue maximization. This validates the efficacy of AERIA for on-demand DNN inference in the Edge-AI market.

The advent of 6G networks necessitates fundamental advancements in Radio Access Network (RAN) slicing to accommodate unprecedented service demands with highly dynamic traffic patterns. Existing AI-driven approaches for RAN slicing face critical limitations: they typically require model retraining when slice configurations change, lack scalability for concurrent slice management, or overlook the significant computational overhead from frequent resource reconfigurations. This paper addresses these significant challenges by introducing a novel RAN Partially Observable Stochastic Game (RAN-POSG) framework that enables parallel decision-making while effectively incorporating global resource constraints. Firstly, we propose an Adaptive Retention Framework (ARF) that strategically balances stability and adaptability through an innovative Conditional Accumulative Reward mechanism, significantly reducing reconfiguration overhead while maintaining high Service Level Agreement (SLA) compliance. Our proposed Statistic-Field Deep Truncated Monte Carlo (SF-DTMC) algorithm leverages multi-agent reinforcement learning where agents make independent yet coordinated decisions, ensuring both flexibility with varying slice counts and scalability under large-scale networks. Lastly, a custom-built high-fidelity RAN slicing simulator based on NS-3 simulator with PettingZoo interfaces is developed for comprehensive evaluations across multiple test scenarios. The simulation results demonstrate the significant advantages of the proposed framework, including superior user satisfaction, resource utilization, and lower resource reconfiguration overhead compared to state-of-the-art methods, representing a crucial advancement toward Native-AI in 6G networks.

Integrating Generative AI (Gen-AI) into vehicular computing can significantly enhance road safety and driving experience. The performance of Gen-AI inference in vehicular computing is highly sensitive to the number of inference steps, where even minor adjustments can disrupt the balance between delay and inference quality. This raises a critical question: how can inference steps be optimally determined for diverse tasks, given the inherent delay-quality trade-offs? Existing approaches fail to offer an optimal solution due to the lack of flexible inference services and efficient memory bandwidth allocation strategies. To address these challenges, we develop aCriticality-awareResource-efficientInference (CARIN) framework, where inference steps are dynamically adjusted to balance delay and quality for multi-criticality tasks. Leveraging an accurate inference model, CARIN fully exploits in-vehicle resources to accelerate both parameter loading and task computing during inference. The joint optimization problem of step control, memory bandwidth allocation, and compute resource scheduling is formulated as a mixed-integer nonlinear programming (MINLP) problem, and solved by a novel learning-to-optimize (L2O) algorithm efficiently. Experimental results demonstrate that, for high-criticality tasks, the proposed approach achieves$28.4\%$latency reduction and$36\%$quality improvement over baseline methods.

Through conducting equivalent model training within the paradigm of edge intelligence, the Digital Twin Edge Networks (DITEN) have been widely employed in the Industrial Internet-of-Things (IIoT) to facilitate the cost-effective execution without the operational disruption. However, due to the insufficient consideration of heterogeneity in computing and communication capabilities of distinct industrial terminals in the Digital Twin (DT) model training, the existing approaches of DT construction/update have unbalanced model training cost and loss in the whole life cycle of DT model, hindering the abilities of quick responding to complex and dynamic productions and ensuring the data consistency of virtual-real space. To address this issue, we define a global loss minimization problem with constraint, and propose an original approach of semi-asynchronous federated learning, named EDT-SaFL, as a promising solution. Considering the collaborative utilization of heterogeneous resources, and the contribution of local data quantity and quality to the global model update, the EDT-SaFL consists of three important operations,Terminal Selection for Model Training,Self-Adaptation of Local Training Iterations, andSemi-asynchronous Global Aggregation. With the analysis of convergence, complexity and communication overhead, the experiments have evidently demonstrated the superiority of EDT-SaFL on the datasets of CIFAR-10 and Industrial-Equipment.

In the realm of Mobile Edge Computing (MEC) networks, mobile interactive applications, such as multiplayer online games, federated learning, and interactive multi-view video, are becoming increasingly popular. The embedding of Bidirectional Service Function Chains (BSFCs) for these applications has been studied. However, existing BSFC embedding research only considers static users, and the prevailing Virtual Network Functions (VNFs) placement methods do not account for the impact of individual node resources on the path, thus failing to maximize node resource utilization at the network level. Considering the aforementioned issues, we introduce a framework for BSFC embedding tailored for mobile users, named Path as a Point (PAAP). This framework integrates the resources of the paths and then globally considers the impact of the computing resources of edge nodes on the paths connecting them, maximizing edge node resource utilization across the entire network. We propose a three-phase algorithm within the PAAP framework. In the first phase, we introduce a singleuser algorithm for VNFs deployment during BSFC embedding. In the second phase, this optimization is extended to multiple users by establishing inter-user association rules. In the third phase, candidate application placement positions are evaluated across the entire network, culminating in the determination of optimal placement strategies. Empirical evaluations confirm the effectiveness of the proposed algorithm, demonstrating significant performance improvements over baseline methods.

Personalized Federated Learning (PFL) has been widely adopted in Mobile Edge Computing (MEC) to enable tailored services without private user data ever leaving the devices. Previous efforts have illustrated that the weighted aggregation determined by the number of samples on clients will hurt the convergence of PFL. Furthermore, the over-personalization of PFL may result in model overfitting and lack of generalization capabilities. Therefore, in this paper, we propose novel quality/discrepancy-aware Multi-task Personalized Federated Learning (MPFL) for MEC to tackle these issues. Specifically, a number of personalized learning objectives of different clients in PFL are considered as multiple tasks. Both local private Batch Normalization (BN) and global shared BN layers are introduced into PFL as the specialized experts to better balance the personalization and generalization capabilities of the local models. Furthermore, the statistical discrepancies between such two BN layers and the model quality of clients are jointly taken into account to design aggregation weights for quick model aggregation with better performance gains. Extensive experiments conducted on three well-known datasets demonstrate that the proposed framework outperforms the state-of-the-art benchmarks in terms of convergence speed and learning accuracy.

With the rapid development of Artificial Intelligence Generated Content (AIGC), single data centers are increasingly unable to meet the growing demands for data and computational resources in distributed large-scale language model (LLM) training. In this context, distributed training across heterogeneous data centers has become a necessary choice to enhance computational power and flexibility. However, the networks in heterogeneous data centers are polymorphic, with diverse communication protocols and network architectures. This heterogeneity renders traditional routing devices ineffective in recognizing and processing gradient data. Moreover, frequent copying and excessive parsing of gradient data by routing devices across heterogeneous data centers significantly increase model training time. To address these challenges, we propose XAForward, a method for accelerating distributed LLM in heterogeneous data centers using eXpress Data Path (XDP). Specifically, XAForward introduces a polymorphic-compatible protocol that reconstructs the header of gradient data packets to enable efficient data forwarding across different communication protocols in heterogeneous data centers. Additionally, to accelerate distributed LLM computing and reduce gradient data copying and excessive parsing during training, XAForward leverages kernel-bypass techniques based on XDP for packet processing and kernel-level data forwarding using network index identifiers. Experimental results show that, compared to state-of-the-art methods, XAForward reduces the distributed LLM training time by approximately 35% to 40%.

Network Function Virtualization (NFV) often suffers from unexpected failures in some mission-critical applications due to the reliability-agnostic deployment of Virtual Network Functions (VNFs), thus achieving suboptimal service performance. To cope with this issue, we propose a Reliability-aware VNF service Provisioning (RVFP) approach for NFV-based networks via Multi-Agent Deep Reinforcement Learning (MADRL), where each VNF is hosted and backed up in appropriate hardware with reliability guarantees. Specifically, a novel MADRL-based framework for VNF placement is designed with two alternating optimization objectives, namely maximizing reliability and minimizing VNF instance failure probability, to incorporate diverse objective landscapes and encourage broader exploration within the solution space. Furthermore, two agent allocation strategies are developed to alternately arrange the tasks of collaborative agents for reliability-aware placement of VNFs in a parallel and cooperative manner. Besides, the newly-designed prioritized experience sampling, built on reward and sampling frequency, is used to better exploit valuable experiences for faster model training. Extensive simulation results obtained from various scenarios show that RVFP can significantly improve placement reliability and service acceptance ratios for VNF deployment compared with the state-of-the-art approaches.

The prediction of network latency with partial measurements is of importance for ever-increasing personal devices to ensure their Quality of Service (QoS). However, the current matrix-factorization-based efforts, as a promising paradigm, for network latency prediction have failed to intelligently exploit inherent factors hidden in networks to accurately infer the unknown network latency. Furthermore, it is more complicated to execute extensive network measurements on pervasive personal devices due to unstable communication environments. To alleviate these problems, in this paper, a novel accurate network latency prediction (DALP) solution via Deep Reinforcement Learning (DRL) is proposed for personal devices under cost-aware sampling. Specifically, we first alternately implement cost-aware latency measurement based on temporal correlation, and model it as a network latency matrix, in which unmeasured and missing elements need to be inferred. In order to achieve accurate prediction performance, the DRL-based Matrix Factorization with Double Weights (DWMF) is designed to exploit the potential network factors and multiple rules of matrix factorization, which can be alternatively executed, to minimize the prediction errors. Furthermore, an angle-loss-based reward strategy is designed to enhance the quality of model training. Simulation results on real-world datasets illustrate that DALP outperforms the previous approaches with quicker convergence and lower prediction errors.

Federated Learning (FL) is a popular privacy-preserving machine learning paradigm, enabling collaborative training among distributed devices coordinated by a central server, without gathering the devices’ local data. Recent studies indicate that device-to-device (D2D) communication technology has the potential to reduce reliance on the central server and enhance the scalability of FL. However, complex heterogeneities in wireless D2D network environments lead to degradation in learning efficiency and hamper global convergence of D2D-assisted FL. To address this important problem, we propose FedAHC, an Asynchronous Hierarchical Clustered FL method based on Graph Convolutional Networks (GCN). To effectively mitigate the impact of computational and communicational heterogeneities on D2D-assisted FL, we utilize a clustering approach for FL devices within the D2D network, formulate it as a graph problem, and design an unsupervised learning strategy powered by GCN to obtain effective cluster assignments adhering to D2D link connectivity. Meanwhile, a global optimizer state is introduced into FedAHC to reduce the training model drift caused by heterogeneous data across devices. We theoretically prove the convergence of this new method by deriving an upper bound on the global loss function. We conduct extensive experiments with various network scenarios and datasets to demonstrate the performance of FedAHC. In comparison to key baselines, FedAHC converges to a higher model accuracy, while exhibiting up to 80% improvement in time efficiency and up to 62% reduction in communication costs.

Federated Learning (FL) has emerged as a promising framework for privacy-preserving machine learning. FL enables distributed data owners (clients) to collaboratively train a global model without sharing their local data with a central server. However, FL is inherently vulnerable to free-rider and poisoning attacks, where free riders dissimulate their participation of training by sending counterfeit yet harmless model updates to the central server, while adversarial clients send poisonous model updates to the server to degrade the global model performance. Their distinctive attacking patterns make the simultaneous defense against both attacks very challenging. To address this challenge, we propose a novel model-agnostic Shapley value-based robust and fair federated learning method (SVRFL), which models FL as a cooperative game and leverages Shapley values of model updates to defend against free riders and adversarial clients. Specifically, a client reputation score and a model utility score are computed using the Shapley value. Based on these scores, we ensure the basic fairness within FL by identifying and eliminating free riders, and realize adversarial robustness through discarding poisonous model updates, with theoretical convergence guaranteed. Extensive experiments show that SVRFL can detect typical free-rider attacks with up to full precision and is resistant to poisoning attacks launched by adversarial clients.

Foundation models (FMs) such as GPT-4 exhibit exceptional generative capabilities across diverse downstream tasks through fine-tuning. Split Federated Learning (SFL) facilitates privacy-preserving FM fine-tuning on resource-constrained local devices by offloading partial FM computations to edge servers, enabling device-edge synergistic fine-tuning. Practical edge networks often host multiple SFL tenants to support diversified downstream tasks. However, existing research primarily focuses on single-tenant SFL scenarios, and lacks tailored incentive mechanisms for multi-tenant settings, which are essential to effectively coordinate self-interested local devices for participation in various downstream tasks, ensuring that each SFL tenant’s distinct FM fine-tuning requirements (e.g., FM types, performance targets, and fine-tuning deadlines) are met. To address this gap, we propose a novel Price-Incentive Mechanism (PRINCE) that guides multiple SFL tenants to offer strategic price incentives, which solicit high-quality device participation for efficient FM fine-tuning. Specifically, we first develop a bias-resilient global SFL model aggregation scheme to eliminate model biases caused by independent device participation.We then derive a rigorous SFL convergence bound to evaluate the contributions of heterogeneous devices to FM performance improvements, guiding the incentive strategies of SFL tenants. Furthermore, we model inter-tenant device competition as a congestion game for Stackelberg equilibrium(SE) analysis, deriving each SFL tenant’s optimal incentive strategy. Extensive simulations involving four representative SFL tenant types (ViT, BERT, Whisper, and LLaMA) across diverse data modalities (text, images, and audio) demonstrate that PRINCE accelerates FM fine-tuning by up to 3.07x compared to state-of-the-art approaches, while consistently meeting fine-tuning performance targets.

The rise of edge intelligence is driving distributed machine learning toward a new paradigm of edge-collaborative computing. To overcome the severe communication bottleneck in this paradigm, In-Network Aggregation is a critical enabling technology. However, its effectiveness is fundamentally undermined by the profound resource heterogeneity of edge networks. Specifically, edge devices, adapting to hardware constraints, operate at varying numerical precisions, leading to significant data inflation as gradients are aggregated. Compounding this, unevenly distributed network resources and traditional, precision-oblivious routing strategies often misallocate critical, high-precision gradients to low-quality paths. This mismatch creates severe network congestion, crippling the efficiency of distributed training. To address this, we propose the Precision-Aware Hierarchical In-Network Aggregation (PAHInA) framework, the first, to our knowledge, to perform routing optimization for in-network aggregation that explicitly considers precision heterogeneity. The core of PAHInA is an intelligent control-plane scheduler that co-optimizes for gradient priority and path cost, dynamically planning the most cost-effective aggregation strategy for each flow. This fine-grained scheduling guarantees that high-priority gradients are routed through premium, low-latency paths, minimizing global communication overhead. On the data plane, we leverage the eXpress Data Path (XDP) for high-performance packet processing to reduce aggregation-induced overhead. Extensive simulations show that, compared to state-of-the-art baselines, PAHInA significantly mitigates network congestion, reducing end-to-end communication time by up to 33% and boosting overall training throughput by approximately 30%.

Federated Learning (FL) enhances data privacy for End Equipment Workers (EWs) by enabling the sharing of model parameters instead of raw data. However, energy constraints and individual self-interest may discourage EWs from participating or slow down training, ultimately affecting the performance of the global FL model. To address these challenges, we propose a three-stage Stackelberg game-based framework that leverages wireless power to incentivize participation while ensuring the successful completion of FL tasks. In this framework, the Base Station (BS) publishes FL task and seeks to obtain an improved global model at a reduced cost. EWs train local models, aiming to maximize their payments while minimizing energy consumption. Meanwhile, the Charging Service Provider (CSP) supplies energy to EWs via Wireless Power Transfer (WPT) during model training and uploading, charging appropriate fees for the service. We employ the backward induction method to analyze the proposed game problem, proving the existence of a unique Stackelberg equilibrium and Nash equilibrium. Furthermore, we propose the Trust Region Method (TRM) to solve the unit payment strategy problem of BS. Extensive simulations validate that our method consistently outperforms benchmark schemes, achieving higher average utility across a wide range of scenarios.

Edge intelligence capitalizes on heterogeneous edge resources to empower artificial intelligence–driven applications while mitigating dependence on centralized cloud infrastructures. In mobile edge computing (MEC) systems, resource scheduling constitutes a latency-critical task within inherently dynamic environments. Deep reinforcement learning (DRL) has been widely employed to address this challenge, as it enables agents to derive task-specific policies through continual interactions with the environment. Nevertheless, MEC environments exhibit substantial heterogeneity, and the relative importance of various resource types may fluctuate as the system evolves, thereby altering task objectives. Consequently, agents often necessitate retraining across new domains, the process that is computation ally intensive and time inefficient. To surmount these challenges, transfer reinforcement learning (TRL) has emerged as a promising paradigm that facilitates the transfer of agents' acquired knowledge from the source domain to the target domain. To the best of our knowledge, this is the first comprehensive survey dedicated to TRL applications in MEC systems. Specifically, we first elucidates the foundational principles of TRL, encompassing problem formulation and DRL methodologies. Subsequently, we systematically reviews and critically analyzes existing research on TRL and its applications in MEC systems. Finally, we discuss persistent technical limitations and delineates promising avenues for future exploration.

The widespread adoption of wireless communication systems in both military and civilian applications has significantly advanced technological progress and social development across various industries. However, narrowband interference signals pose a significant challenge, severely disrupting the normal operation of wireless communication equipment. A major obstacle in existing narrowband interference detection lies in enhancing robustness under complex channel propagation conditions and diverse, dynamically changing types of interference. In view of those challenges, we propose a robustness-enhanced narrowband interference detection method by utilizing unlabeled data. The proposed detection network incorporates soft-shrink technology to isolate irrelevant signal features while adaptively extracting and fusing original and time-frequency features. The proposed method leverages the distribution characteristics of interference frequency bands to enhance model robustness in varying channel propagation environments. Additionally, we design a pseudo-label-based model tuning process to exploit the potential of unlabeled data, further enhancing the model’s robustness. Comparative experiments demonstrate the superiority of the proposed method against various baselines, as well as against configurations incorporating individual network modules.

Digital task-oriented semantic communication (ToSC) aims to transmit only task-relevant information, significantly reducing communication overhead. Existing ToSC methods typically rely on learned codebooks to encode semantic features and map them to constellation symbols. However, these codebooks are often sparsely activated, resulting in low spectral efficiency and underutilization of channel capacity. This highlights a key challenge: how to design a codebook that not only supports task-specific inference but also approaches the theoretical limits of channel capacity. To address this challenge, we construct a spectral efficiency-aware codebook design framework that explicitly incorporates the codebook activation probability into the optimization process. Beyond maximizing task performance, we introduce the Wasserstein (WS) distance as a regularization metric to minimize the gap between the learned activation distribution and the optimal channel input distribution. Furthermore, we reinterpret WS theory from a generative perspective to align with the semantic nature of ToSC. Combining the above two aspects, we propose a WS-based adaptive hybrid distribution scheme, termed WS-DC, which learns compact, task-driven and channel-aware latent representations. Experimental results demonstrate that WS-DC not only outperforms existing approaches in inference accuracy but also significantly improves codebook efficiency, offering a promising direction toward capacity-approaching semantic communication systems.

The smart traffic light (STL) system, as one of the key components of smart cities, relies on the ubiquitous intelligence of edge computing. Various artificial intelligence (AI) services are enhanced by the resource-constrained edge servers (ESs). However, deploying ESs and resources to establish a largescale service coverage can be extremely costly and requires tremendous efforts. In this paper, we unveil the potential of crowd edge intelligence by designing EdgeLight, a novel STL system that does not require dedicated deployment of ESs. The key insight of EdgeLight is to empower STLs by exploiting the edge devices carried by the surrounding crowds. The video frames captured by the traffic cameras will be offloaded to the crowd devices for processing, and the results are then sent to the traffic lights for smart control. We establish the above paradigm by proposing novel techniques including service discovery and task splitting. We implement EdgeLight and conduct real world experiments, and the comparison to existing STL solutions shows a significant improvement, with a 92.41% reduction in total latency and a 53.26% reduction in payment.

Spiking Neural Network (SNN) simulation involves emulating the activation and firing of spiking neurons on hardware platforms. This is a highly time-sensitive task, requiring the simulation of billions of neurons and their intercommunication within a few milliseconds. Each neuron performs a complex, interdependent multi-stage communication and computation task. We consider the task placement of SNN on supercomputers to accelerate SNN simulation. Existing task placement methods for SNN simulations have two major limitations. First, they lack the capability to handle large-scale SNNs with billions of neurons. Second, they focus primarily on optimizing communication delay, while neglecting multi-stage computation delays in SNN simulations. In this paper, we formalize the SNN Joint Multi-stage Communication and Computation Placement (SJCCP) problem. We demonstrate that SJCCP can be solved using an approximation algorithm with an approximation ratio of $O\left( {{k^2}\sqrt {\log n\log k} } \right)$, where n is the number of voxels in the SNN and k is the number of GPUs. To further reduce the time complexity of solving SJCCP in practice, we propose a novel efficient framework, FastSJP, tailored for large-scale SNN placement. Then we apply the FastSJP framework to a human brain simulation that runs a large-scale SNN model derived from authentic biological data on a supercomputer equipped with 1024 GPUs. Experimental results verify that our framework notably reduces time overhead, ranging from 17.31% to 28.45%, compared to state-of-the-art methods. Leveraging the computational power of the supercomputer, FastSJP maximizes the problem size and processing performance, significantly advancing the development of brain-inspired intelligence.

Road networks are the vein of modern cities. Yet, maintaining up-to-date and accurate road network information is a persistent challenge, especially in areas with rapid urban changes or limited surveying resources. Crowdsourced trajectories, e.g., from GPS records collected by mobile devices and vehicles, have emerged as a powerful data source for continuously mapping the urban areas. However, the inherent noise, irregular and often sparse sampling rates, and the vast variability in movement patterns make the problem of road network generation from trajectories a non-trivial task. Existing methods often approach this from an appearance-based perspective: they typically render trajectories as 2D density maps and then employ heuristic algorithms to extract road networks - leading to inevitable information loss and thus poor performance especially when trajectories are sparse or ambiguities present, e.g. flyovers. In this paper, we propose a novel approach, called GraphWalker, to generate high-fidelity road network graphs from raw trajectories in an end-to-end manner. We achieve this by designing a bespoke latent diffusion transformer T2W-DiT, which treats input trajectories as generation conditions, and gradually denoises samples from a latent space to obtain the corresponding walks on the underlying road network graph - then assemble them together as the final road network. Extensive experiments on multiple datasets demonstrate the proposed GraphWalker can effectively generate high quality road networks from noisy and sparse trajectories, showcasing significant improvements over state-of-the-art.

The Internet of Vehicles (IoV) significantly enhances the capabilities for road information collection and processing by enabling real-time connectivity between vehicles, infrastructure, and cloud systems. Leveraging these technological advantages, multi-vehicle collaborative real-time crack detection is expected to become a crucial method to guarantee the health and safety of infrastructures. Due to different vehicles being equipped with various types of sensors, the collected data are heterogeneous, and the limited computational resources of onboard units obstacle the efficient data processing and effective crack detection in infrastructures. To address these challenges, this study proposes a novel Distributed Edge Computing for Crack detection (DECCD), vehicle serve as edge nodes that locally collect and analyze data. The central node continuously aggregates and processes data from multiple edge nodes to train a robust model. This model is periodically refined and then distributed to edge nodes, where it is further training to detect cracks. A multi-scene dataset, called CrackMS, is constructed by integrating multi-scene datasets of different modalities, and the data are enhanced by Deep Convolutional Generative Adversarial Network (DCGAN) to simulate the complexity of crack data acquired by vehicles. A crack detection model, called the Multi-Scene Auxiliary Prediction Network (MSA-Net), which includes an AUX module and a Scene module is proposed to optimize feature extraction and processing of scene changes. Then a lightweight student model with similar performance is trained by knowledge distillation. Experimental results show that the proposed model, while maintaining a lightweight design, achieves a significant improvement in detection accuracy compared to baseline models.

The rapid development of the Internet-of-Things (IoT) has transformed human interaction with the world. The Social Internet-of-Things (SIoT) integrates social, emotional, and behavioral aspects into traditional IoT, creating an intelligent network that connects various smart devices. By combining Edge Computing with Artificial Intelligence (AI), data can be processed and analyzed directly on edge devices, improving processing efficiency. However, limited edge resources hinder local AI training, requiring cloud-based training of high-precision models, which are then deployed on edge devices for inference. In time series forecasting, Multilayer Perceptrons (MLPs) are widely used for their computational efficiency but often overlook correlations between time series. Some models adopt channel mixing mechanisms to improve modeling capability but increase computational complexity. To address this problem, we propose the Core Fusion Time Series Dense Encoder (CFTD) model, which incorporates a Core Extract-Distribute (COED) module for efficient channel fusion. Extensive experiments on real-world datasets demonstrate that this novel CFTD model achieves excellent predictive performance compared to the state-of-the-art models.

Mobile Edge Computing (MEC) can accelerate computation-intensive applications and emerge as a promising technology for enabling Internet of Things (IoT). MEC improves the processing performance of tasks by assigning them to the edge nodes. However, with massive terminals contending for computation and communication resources simultaneously, how to develop a flexible computational offloading mechanism becomes the fundamental issue of MEC-enabled IoT systems. This paper aims to develop an effective computational offloading decision scheme by jointly considering the computational resource and diverse user demands with two goals, i.e., minimizing both the latency and the energy consumption. Specifically, we develop a two-stage computational offloading mechanism, where the computational resources and offloading decisions can be allocated and coordinated with the variation of computation requirements. To achieve the two goals, this work introduces an edge node recommendation model within the cloud-edge-end architecture to reduce the offloading optimization search space. Furthermore, we propose a new computational offloading (CROCA) algorithm based on Chemical Reaction Optimization (CRO) for optimizing offloading utility, which thoroughly considers the competition between mobile device requests and computational resources. Extensive evaluation results demonstrate that the proposed CROCA scheme can effectively improve the computational offloading performance.

Workflow scheduling plays a critical role in optimizing completion time and throughput in distributed cloud environments, leveraging the parallelism of heterogeneous computing resources. However, existing workflow scheduling algorithms often fall short due to heuristic limitations and the challenges in adaptability within heterogeneous settings, leading to suboptimal scheduling solutions. In this paper, we present a novel deep reinforcement learning (DRL) framework tailored for continuous workflow scheduling in heterogeneous environments. First, we propose an intelligent scheduler that updates the policy network through interactions with a multi-tenant environment, triggered by scheduling events. Next, the framework incorporates a Graph Attention Network (GAT) and a self-attention MultiLayer Perceptron (MLP) to preprocess the workflow topology and embed dynamic features of ready tasks and available processors into the state input at each scheduling step. Additionally, a k-dimensional tree-based k-nearest neighbors (kNN) algorithm is employed to map the output action vector to a pair of executed ready task and processor, facilitating the transition from continuous to discrete action spaces and addressing challenges associated with dynamic action spaces. Experimental results demonstrate that our method converges effectively in continuous workflow scheduling scenarios and significantly outperforms the best-known methods in terms of average makespan and load balancing efficiency.

With the advent of the sixth-generation (6G) wireless communications, transmission speeds are projected to exceed tenfold those of 5G, reaching theoretical peak download speeds of up to 1 Tbps. Data transmission capacity and speed will be significantly enhanced, enabling emerging applications, such as mixed reality, federated learning, and digital twins, driving exponential data traffic growth. To address this, the space-air–ground integrated network (SAGIN) combines satellite, aerial, and ground communication technologies, offering seamless global coverage and high-speed connectivity. In this article, we proposes an SAGIN framework integrated with mobile edge computing (MEC) to jointly optimize system energy consumption and delay costs. Specifically, we decompose the optimization problem into three subproblems: 1) uncrewed aerial vehicle (UAV) computational resource allocation; 2) satellite computational resource allocation; and 3) task offloading and channel allocation. The subproblems are then transformed and addressed using Newton’s interior point method and the deep reinforcement learning DQN algorithm to derive optimal allocation strategies for UAV and satellite computing resources, along with task offloading and channel resources, that our proposed algorithm effectively reduces system energy consumption and delay costs compared to other algorithms.

Along with the rapid development of the fourth industrial revolution, industrial cyber-physical systems (ICPS) are anticipated to achieve precise mapping and management for the physical world by integrating digital sensing and automated control. However, the conflict between limited computing resources and extensive sampling data, combined with severe industrial interference, exacerbates the system’s processing burden and diminishes its accuracy, hindering its ability to meet the low-latency and high-reliability control requirements. To address this issue, this paper investigates an end-edge collaborative control framework to enhance control performance for a short-packet transmission ICPS by providing powerful computation capability. We utilize the age of information (AoI) to characterize the impact of information freshness on control accuracy and construct an AoI-aware control law to assist in data sensing, transmission, and computing strategy design. In addition, we consider the influence of sampling and short-packet decoding errors in AoI-aware control performance to enhance the reliability of sampling and transmission strategies design. A joint optimization scheme of sampling interval, sampling time, computation offloading, and bandwidth allocation based on the block coordinate descent method and game theory is proposed to achieve a tradeoff between the control cost and energy consumption. By considering a real-world trolley inverted pendulum manipulation model, numerical results verify the performance gain of the proposed end-edge collaborative framework and the effectiveness of the presented algorithm.

Sliding window aggregation is a core operation in data stream analysis that extracts summaries from the most recent data stream. An evict or insert of the window can be handled in$O(1)$for in-order data streams. However, real-world data streams are typically disordered due to network delays. To process out-of-order data streams, existing methods primarily use a tree to maintain the sliding windows. Since the complexity of the tree is related to the window size, the performance of these methods will drop sharply or become unavailable when facing a big window. To overcome the limitation of existing methods, this paper presents Finger B-Trees Forest Aggregation (FIFA). This novel forest-based sliding window aggregation scheme optimally handles out-of-order data streams. At its heart, FIFA uses aggregation forest to extend Finger B-Trees. Specifically, FIFA evenly divides a window into several chunks and constructs a separate tree to maintain each chunk. When an out-of-order item arrives, FIFA first locates the corresponding chunk of the item and then uses Finger B-Trees to insert it into the window efficiently. Chunking reduces the complexity of the tree and the coupling of aggregation results by isolating items within windows. Thus, an insert or evict takes amortized$O(c)$in the worst case, where$c$is the size of each chunk. Finally, extensive experiments based on real-world data demonstrate that FIFA achieves an average 2-fold throughput improvement on out-of-order data streams compared with the state-of-the-art (SOTA) aggregation schemes.

Cloud Data Centers are typically equipped with various types and performance levels of GPUs, making it crucial to effectively leverage these heterogeneous resources when deploying deep learning tasks. However, differences in GPU performance pose complex resource management challenges. Accurate workload forecasting can help address these challenges. Many existing prediction models employ Multi-Layer Perceptrons (MLPs) due to their simplicity, computational efficiency, and general applicability. Nevertheless, most MLP-based methods tend to prioritize low-frequency features, neglecting high-frequency features that are essential for capturing fine-grained patterns in resource utilization data. Our analysis reveals that this bias primarily stems from the dominance of low-frequency features in the dataset, causing the model's attention to disproportionately focus on them. To tackle this issue, we propose a frequency domain patch-based MLP model called FP-MLP, which partitions the frequency series into small patches, thereby balancing the representation of high and low-frequency features across different bands. This approach enables the model to fully capture hidden features in high-frequency data, thus improving predictive accuracy. Extensive experiments demonstrate that the FP-MLP model consistently outperforms various state-of-the-art baseline models with stable performance. For instance, on the Alibaba dataset, compared to the best baseline model, the FP-MLP model reduces the Mean Squared Error (MSE) by 8% and the Mean Absolute Error (MAE) by 17%; meanwhile, it also achieves competitive results on the Google.

The rapid growth of Cloud Computing, Artificial Intelligence, and Big Data cloud workloads, intensifying resource contention, operational costs, and carbon emissions due to underutilized data centers. Accurate workload prediction is thus for proactive resource management and improved utilization of Cloud data centers. However, traditional statistical and machine learning methods struggle with the dynamic, high-dimensional, and heterogeneous nature of cloud workloads. This paper proposes STiFF, a novel prediction framework that, for the first time in workload forecasting, transforms time series data into graph-based image representations to capture spatiotemporal dependencies. STiFF integrates three key modules: (1) a Two-Dimensional Moving Average Decomposition (2D-MAD) for trend smoothing, (2) a Global-Local Feature Extraction (GLE) module combining CNNs and Transformers for hierarchical pattern learning, and (3) a Multi-modal Feature Fusion (MFF) module leveraging attention mechanisms and partial prior knowledge. Extensive experiments on four real-world datasets demonstrate that STiFF achieves an average error reduction of 62.14%, with a maximum of 90.84%, and outperforms state-of-the-art methods in 84.375% of the evaluated cases.

Cloud gaming represents a major part of contemporary gaming. To boost the Quality-of-Experience (QoE) of cloud gaming, the integration of Dynamic Adaptive Video Encoding (DAVE) with Multi-access Edge Computing (MEC) has become the natural candidate owing to its flexibility and reliable transmission support for real-time interactions. However, as multiple gamers compete for limited resources to achieve personalized QoE, such as ultra-high video quality and ultra-low latency, how to support efficient edge resource optimization is a fundamental and important problem. Furthermore, determining the optimal game video encoding configuration in real-time poses significant challenges, especially when lacking the information on future video and edge network resources. To address these key issues, we jointly optimize the video encoding as well as computing and communication resource allocation by active mutual adaptation of video coding configurations and physical resources in a Software Defined Networking (SDN)-assisted edge network. This eliminates the performance bottleneck caused by decoupling optimization of coding parameter configuration and physical resource allocation. The SDN-assisted edge network architecture supports efficient on-demand resource management, provides global network information, and meets the stringent time-varying game requests. Due to the significant time scale difference between video chunk and physical resource block, we propose a novel Asynchronous Decision-Making Multi Agent Proximal Policy Optimization algorithm (AD-MAPPO), which can address the credit assignment problem with a single agent. It can also adapt to the highly dynamic cloud gaming environment without prior knowledge and a deterministic environmental model. Extensive experimentation based on real cloud gaming datasets convincingly demonstrates that our approach can significantly enhance the overall QoE of gamers.

Deep neural networks (DNNs) have achieved remarkable performance in various tasks, including image classification. However, recent research has revealed the susceptibility of trained DNNs to subtle perturbations introduced into input images. Addressing these vulnerabilities is pivotal, leading to a significant area of study focused on developing attack algorithms capable of generating potent adversarial images. In scenarios where access to gradient information is restricted (black-box scenario), many existing methods introduce optimized perturbations to each individual pixels of an image to cause trained DNNs to mis-classify. However, due to the high-dimensional nature of this approach, current methods have inherent limitations. In contrast, our proposed approach involves the construction of perturbations by concatenating a series of overlapping semi-transparent shapes. Through the optimization of these shapes’ characteristics, we generate perturbations that result in the desired misclassification by the DNN. By conducting a series of attacks on state-of-the-art DNNs trained of CIFAR-10 and Imagenet datasets, our method consistently outperforms existing attack algorithms in terms of both query efficiency and success rate.

Recently, many laws and regulations have granted users the right to be forgotten, i.e., the right to require data controllers to delete user data. Various methods for machine unlearning have been proposed to remove individual data points. However, they do not scale to the scenarios where larger groups of features are to be removed. To address this challenge, we propose MAFRO, an optimal-granularity fuzzy decision rule–based classifier that accelerates unlearning via influence functions. Building on granular computing (GrC), MAFRO first selects a minimal reduct of attributes, then constructs fuzzy granules with a Gaussian membership function to extract concise decision rules and realizes unlearning through the influence function. Specifically, instead of training with the full set of attributes, we use the reduct, a minimal subset of attributes that can classify the data with the same accuracy as the full set of attributes. Next, we extract fuzzy rules based on the reduct. Finally, fusing the generated rules establishes the linear model with strongly convex loss functions. In this way, MAFRO can quantify the divergence caused by attribute deleting and update the model without retraining it, thereby adapting the influence of data removal on the model and accelerating the unlearning process. We conduct extensive experiments to evaluate MAFRO on ten typical datasets in terms of performance and unlearning speed. We compare MAFRO with the state-of-theart algorithms. Experimental results demonstrate that MAFRO enhances accuracy by an average of 6.96%, and achieves up to 236× speedup for attribute unlearning tasks.

The widespread adoption of face manipulation systems has brought entertainment and convenience to users while posing significant challenges to media forensics. Conventional active defense strategies typically generate adversarial images by introducing perturbations into the original images. When adversarial images undergo facial manipulation, they often exhibit distortions or speckle artifacts, which helps reduce the dissemination of forged content on social media platforms. Nevertheless, the widespread dissemination of degraded images may contribute to facial stigmatization. Furthermore, conventional perturbation techniques are vulnerable to failure under JPEG compression and various image processing operations on OSN platforms. To address these challenges, we introduce a robust and unstigmatized imperceptible perturbation (RUIP) method designed to counteract face manipulation. First, RUIP utilizes an end-to-end adversarial training framework to generate robust and imperceptible perturbations. Second, to mitigate facial stigmatization, we incorporate both pixel-level and feature-level guidance losses during training, ensuring that the output images remain visually natural and closely aligned with the original images. Finally, we develop a novel module, the Flexible Random Enhancement Generator (FREG), to simulate complex JPEG compression and diverse image processing operations on OSN platforms, enhancing the model’s robustness against perturbations. Extensive qualitative and quantitative experiments demonstrate that the proposed method effectively defends against face manipulation attacks while preserving the visual quality of facial images under JPEG compression and other image processing operations on OSN platforms. We propose an effective and unstigmatized defense algorithm to safeguard privacy and maintain the stability of the social media ecosystem.Code is available athttps://github.com/silencecmsj/RUIP.

Distributed microgrids are being deployed into our power grids to form large-scale multimicrogrid systems for utilizing growing renewable energy sources. An effective energy management strategy is fundamental to balancing energy supply and demand alongside maintaining the stability of multimicrogrid. In this article, we propose a scalable, privacy-preserving, distributed energy management approach (SPDEM) for multimicrogrid. Specifically, we first formulate the energy management problem in multimicrogrid as a decentralized partially observable Markov decision process (Dec-POMDP). Next, we develop an intelligent energy management algorithm using mean-field multiagent recurrent reinforcement learning to efficiently solve the Dec-POMDP. This approach incorporates a novel fingerprint-based importance sampling technique to address the obsolete experiences induced by mean field approximation. Extensive experiments on real-world datasets demonstrate that SPDEM can make effective energy management decisions under variable renewable energy generation and load demand. Comparisons with five typical baselines illustrate the superb performance of SPDEM in cost reduction and scalability enhancement.

UAV swarms have attracted much attention due to their high potential to execute complex missions more robustly and effectively. Essential technologies for swarms are the family of algorithms that allow the individual agents to undertake tasks intelligently, localize their relative positions, perceive surroundings, and plan and track collision-free and low-cost trajectories cooperatively so that the swarm’s overall objectives are efficiently achieved. There is still a lack of corresponding surveys that provide a systematic summary covering the control layer to task allocation and guide application-driven researchers in leveraging these capabilities for diverse UAV swarm applications. This survey debates the essential technologies of UAV swarms, including swarm trajectory planning, task assignment, control approaches, localization, perception, and communications. State-of-the-art algorithms and recent technical advancements have been investigated to expose the potential for developing highly autonomous and intelligent swarm systems. It further explores the use cases of UAV swarms in civil applications and critically analyzes existing technologies. The paper concludes by emphasizing the challenges for autonomous and intelligent UAV swarms and outlining potential future research directions. Overall, this paper provides a contemporary and comprehensive review of UAV swarm technologies and investigates their potential to transform civil application fields and support future technology advancement.

The rapid growth of Internet of Vehicle (IoV) devices and Artificial Intelligence (AI) applications has accelerated the adoption of Cloud and Edge Computing. The advent of sixth-generation mobile communication technology (6G) further facilitates the deployment of Cloud-Edge collaborative computing in large-scale Intelligent Transportation Systems (ITS). Effective ITS must efficiently handle both latency-sensitive tasks (e.g., obstacle detection, traffic signal recognition) and computationally intensive tasks (e.g., path optimization, traffic flow prediction). However, existing Cloud-Edge collaborative frameworks struggle to accurately classify diverse workloads and provide efficient low-latency processing, leading to energy inefficiencies and task failures. To address these challenges, this paper introduces a Deep Learning-based Cloud-Edge Collaboration Framework (CECF) designed to optimize energy conservation in Cloud and Edge environments. CECF employs a DNN-based classifier to categorize workloads for processing in the Cloud or Edge. The classified tasks are managed by a dedicated Cloud scheduler (DSGA) and an Edge scheduler (EA-DFPSO), respectively. To enhance scheduling efficiency for highly variable Cloud tasks, DSGA incorporates a novel self-adaptive mutation algorithm and a random point fixed distance crossover method. Extensive evaluations using real-world workload traces demonstrate that CECF achieves up to a 8.5% improvement in system reliability and reduces energy consumption by 35.88% compared to baseline approaches.

With the explosion of connected devices and Internet-of-Things (IoT) services in the smart city, the challenge to meet the demands of urban computing is increasingly prominent. Recent advances in vehicle-to-everything (V2X) communications promote urban Internet-connected vehicles to become excellent candidates for computing tasks. However, due to the limited computing capacity of vehicles, conducting computation in the vehicular networks themselves is insufficient to satisfy the demands of smart city applications. Edge computing, which delivers computing tasks to edge servers (e.g., base stations, BSs, or roadside units, RSUs) with plenty of computing resources, could be a possible solution. However, the static deployment of edge servers may cause severe load unbalance among servers in both real-time communication and computation, thereby decreasing the system performance. This paper explores a two-hop vehicle-assisted edge computing network framework in which vehicles are able to offload the tasks beyond their capabilities to underloaded edge servers relaying via neighbor vehicles. According to the state of the time-varying vehicular environment and the dynamic traffic loads among RSUs, we formulate the task offloading, relay node selection, and resources allocations problem as a Markov decision process (MDP) aiming at maximizing the performance of the computation offloading capacity with the considerations of load balancing and latency constraints. We propose a deep reinforcement learning (DRL) algorithm with a DNN as Q action-value function approximator to solve this problem. Extensive simulation results reveal that the proposed scheme can significantly improve the system performance compared to other state-of-the-art algorithms.

Aiming to improve the efficiency of urban traffic management, previous studies have achieved considerable traffic prediction accuracy. For example, methods based on time series analysis perform well in short-term traffic prediction, and neural networks show strong capabilities in processing complex nonlinear relationships within traffic data. However, previous studies also have the following two limitations: 1) a large amount of complex traffic data will increase the complexity of the model during training and further reduce the accuracy of the training results; 2) the large-scale distribution of traffic data leads to incomplete model training and data security issues. To address these issues, we propose a Formal Concept-enhanced Federated Graph Convolutional Network (FC-FedGCN), which adopts formal concept analysis to fully mine graph data and improve the training accuracy of the GCNs model. Under federated learning, the GCNs model can be trained independently on different clients, and the local model is optimized by sharing model parameters. Coupled with the premise of protecting data privacy, the integrity of the data is guaranteed and the training accuracy of the GCNs model is improved. We compare our model with various baseline models based on the PEMS datasets, and the results demonstrate that FC-FedGCN has significant advantages in traffic prediction, outperforming the comparison methods in multiple indicators.

The integration of autonomous driving technologies with vehicular networks presents significant challenges in privacy preservation, communication efficiency, and resource allocation. This paper proposes a novel U-shaped split federated learning (U-SFL) framework to address these challenges on the way of realizing autonomous driving in vehicular edge networks. U-SFL is able to enhance privacy protection by keeping both raw data and labels on the vehicular user (VU) side while enabling parallel processing across multiple vehicles. To optimize communication efficiency, we introduce a semantic-aware auto-encoder (SAE) that significantly reduces the dimensionality of transmitted data while preserving essential semantic information. Furthermore, we develop a deep reinforcement learning (DRL) based algorithm to solve the NP-hard problem of dynamic resource allocation and split point selection. Our comprehensive evaluation demonstrates that U-SFL achieves comparable classification performance to traditional split learning (SL) while substantially reducing data transmission volume and communication latency. The proposed DRL-based optimization algorithm shows good convergence in balancing latency, energy consumption, and learning performance.

Sliding window aggregation, which extracts summaries from data streams, is a core operation in streaming analysis. Though existing sliding window algorithms that perform single eviction and insertion operations can achieve a worst-case time complexity of$O(1)$for in-order streams, real-world data streams often involve out-of-order data and exhibit burst data characteristics, which pose performance challenges to these sliding window algorithms. To address this challenging issue, we proposeGecko- a novel sliding window aggregation algorithm that supports bulk eviction. Gecko leverages a granular-based eviction strategy for various bulk sizes, enabling efficient bulk eviction while maintaining the performance close to that of in-order stream algorithms for single evictions. For large data bulks, Gecko performs coarse-grained eviction at the chunk level, followed by fine-grained eviction using leftward binary tree aggregation (LTA) as a complementary method. Moreover, Gecko partitions data based on chunks to prevent the impacts of out-of-order data on other chunks, thereby enabling efficient handling of out-of-order data streams. We conduct extensive experiments to evaluate the performance of Gecko. Experimental results demonstrate that Gecko exhibits superior performance over other solutions, which is consistent with theoretical expectations. In real-world data scenarios, Gecko improves the average throughput of the state-of-the-art algorithm b_FiBA by 1.7 times, with a maximum improvement of up to 3.5 times. Gecko also demonstrates the best latency performance among all compared schemes.

Predicting information popularity in social networks has become a central focus of network analysis. While recent advancements have been made, most existing approaches rely solely on the final cascade size as the primary supervision signal for model optimization. This narrow focus limits the model generalization ability, particularly when faced with highly heterogeneous cascades. Additionally, in real-world scenarios, obtaining detailed social relationships is challenging, complicating effective structural feature learning. To address these issues, this paper proposes a semi-supervised model called Dual Variational Cascade AutoEncoders (DVCAE), which leverages parallel structural and temporal variational autoencoders for enhanced feature learning and popularity prediction. The model first aggregates multiple cascades into a global interaction graph, enabling structural information sharing across cascades. Then, it applies sparse matrix factorization-based graph embedding and graph filtering techniques on global and local cascade graphs respectively, generating initial node embeddings that are insensitive to topological perturbations. After that, two parallel variational autoencoders are designed to generate hidden representations for structural and temporal features respectively, with two self-supervised reconstruction losses integrated into the prediction loss to enrich supervision signals. Extensive experiments conducted on three real-world datasets demonstrate that DVCAE outperforms state-of-the-art models in terms of prediction accuracy.

Mobile Edge Computing (MEC) offers low-latency and high-bandwidth support for Internet-of-Vehicles (IoV) applications. However, due to high vehicle mobility and finite communication coverage of base stations, it is hard to maintain uninterrupted and high-quality services without proper service migration among MEC servers. Existing solutions commonly rely on prior knowledge and rarely consider efficient resource allocation during the service migration process, making it hard to reach optimal performance in dynamic IoV environments. To address these important challenges, we proposeSR-CL, a novel mobility-aware seamless Service migration and Resource allocation framework via Convex-optimization-enabled deep reinforcement Learning in multi-edge IoV systems. First, we decouple the Mixed Integer Nonlinear Programming (MINLP) problem of service migration and resource allocation into two sub-problems. Next, we design a new actor-critic-based asynchronous-update deep reinforcement learning method to handle service migration, where the delayed-update actor makes migration decisions and the one-step-update critic evaluates the decisions to guide the policy update. Notably, we theoretically derive the optimal resource allocation with convex optimization for each MEC server, thereby further improving system performance. Using the real-world datasets of vehicle trajectories and testbed, extensive experiments are conducted to verify the effectiveness of the proposedSR-CL. Compared to benchmark methods, theSR-CLachieves superior convergence and delay performance under various scenarios.

The emerging load prediction techniques support up-front and rational resource provisioning in edge systems to enhance system efficiency and Quality-of-Service (QoS). Classic prediction methods may handle loads with apparent trends, but they cannot achieve accurate prediction for highly-variable edge loads. With the advantage of sequential data analysis, recurrent neural networks (RNNs) are often used for load prediction but reveal limited generalization ability and low training efficiency. Moreover, it is hard to obtain a well-performed prediction model by discrete single-edge training with insufficient historical data. To address these important challenges, we propose a novel Multi-edge Cooperative universal framework for load Prediction with Personalized Federated deep learning (MC-2PF), enabling multi-edge cooperative training of load prediction models. Specifically, to solve the client-drift issue in federated learning (FL) caused by distinct data distribution, we customize personalized models for each edge by independent control parameters and theoretically analyze the model convergence improvement. Meanwhile, we prove the generalization bound of the MC-2PF and its universality to RNN-based prediction models through a practical example. Using the real-world testbed and load datasets, extensive experiments verify the effectiveness and practicality of the MC-2PF for different RNN-based prediction models. Compared to state-of-the-art frameworks, the MC-2PF achieves higher prediction accuracy, faster convergence, and stronger adaptiveness.

Mobile Edge Computing (MEC) distributes resources such as computing, storage, and bandwidth to the side close to users, which can provide low-latency services to in-vehicle users, thus promising a more efficient and safer driving environment. However, due to the dynamic scale of vehicle and the variability of resource requirements, it is a significant challenge to quickly obtain effective task offloading in large-scale vehicle scenarios. The existing studies generally adopt the centralized decision-making method, with long decision-making time and high computational overhead, which cannot effectively achieve good offloading decisions in large-scale scenarios. To address these problems, we propose a Multi-agent Collaborative Method for vehicular task offloading using Federated Deep Reinforcement Learning called MCM-FDRL. First, each vehicle as an agent, independently makes offloading decisions based on local information. Next, the offloading decision model of each vehicle is obtained through federated reinforcement learning training. At runtime, an effective vehicle offloading plan can be gradually developed through multi-agent collaboration. Using two real-world datasets, experiments show that the MCM-FDRL has good adaptability and scalability. Moreover, compared to the state-of-the-art methods, the task's average response time of the MCM-FDRL is reduced by 9.75%-64.90%, respectively.

The rapid evolution of the Internet-of-Vehicles (IoV) has amplified the need for mobile computing resources, driving the shift toward offloading tasks to edge servers or vehicles with idle resources to optimize computational efficiency. To this end, an approach based on Deep Reinforcement Learning (DRL) is presented in this paper, termed DVTP, which integrates Variational Graph Attention Networks (VGAT) and Transformer models to optimize Directed Acyclic Graph (DAG) task scheduling in vehicular networks. DVTP effectively captures both the spatiotemporal information and task dependencies, enabling more accurate and efficient task offloading decisions. Extensive simulation experiments demonstrate that DVTP outperforms traditional methods in reducing task completion times across various multi-vehicle and multi-edge server scenarios, showcasing its potential for real-world IoV applications.

Federated Learning (FL) stands as a privacy-preserving machine learning paradigm that enables collaborative training of a global model across multiple clients. However, the practical implementation of FL models often confronts challenges arising from data heterogeneity and limited communication resources. To address the aforementioned issues simultaneously, we develop a Sparsified Random Partial Update framework for personalized Federated Learning (SRP-pFed), which builds upon the foundation of dynamic partial model updates. Specifically, we decouple the local model into personal and shared parts to achieve personalization. For each client, the ratio of its personal part associated with the local model, referred to as the update rate, is regularly renewed over the training procedure via a random walk process endowed with reinforced memory. In each global iteration, clients are clustered into different groups where the ones in the same group share a common update rate. Benefiting from such design,SRP-pFedrealizes model personalization while substantially reducing communication costs in the uplink transmissions. We conduct extensive experiments on various training tasks with diverse heterogeneous data settings. The results demonstrate that theSRP-pFedconsistently outperforms the state-of-the-art methods in test accuracy and communication efficiency.

Edge intelligence is an emerging paradigm in edge computing that deploys Deep Neural Network (DNN) models on edge servers with limited storage and computation capacities to provide inference services for high mobility and real-time applications, such as autonomous driving or smart surveillance, with varying accuracy and delay requirements. Adapting application configurations (e.g., image resolution or video frame rate) while selecting different DNN models and deployment locations can provide high-accuracy, low-delay inference services that meet user requirements. However, the configurations and DNN models of various inference services are highly heterogeneous. As balancing inference accuracy, resource cost, and delay is a multi-objective programming problem, it is a great challenge to obtain the optimal solution. To address this challenge, we propose a novel online framework to jointly optimize the configuration adaption, DNN model selection, and deployment for heterogeneous inference services. Specifically, we first formulate this joint optimization problem as an integer linear programming problem and prove it is NP-hard. Then, we further model the problem as a Partial Observable Markov Decision Process (POMDP) and solve it by developing a Heterogeneous-Agent Reinforcement Learning (HARL) based algorithm, named Heterogeneous Inference Service ProvidER (HISPER). It allows agents to have different action spaces corresponding to different types of configurations and DNN models. Finally, extensive experiments demonstrate that the proposed algorithm outperforms other state-of-the-art counterparts.

The accurate prediction of Quality of Service (QoS) in terms of response time, packet loss rate, latency and throughput for component services is essential for 5 G to fulfill specific Service Level Agreements (SLAs). However, most current efforts failed to fully exploit the time-varying mobility features of users and parallel iteration multi-rules to perform QoS prediction for component services, incurring poor prediction accuracy. Therefore, in this paper, we are devoted to accurate QoS Prediction of Component Services (QPCS) for 5 G via Graph-based Deep Reinforcement Learning (GDRL) to tackle this issue. Towards this end, the QoS prediction is modeled as GDRL-based QoS tensor factorization by designing a Spatio-Temporal-Recurrent-based Graph Attention Network (STR-GAT) and introducing it into Deep Deterministic Policy Gradient (DDPG) to factorize QoS tensor with multiple available rules in parallel. Specifically, a low-rank QoS tensor and an adjacency tensor are established, which include partial QoS observations of component services in each Base Station (BS), along with some missing elements, and evolving spatial information of users across these BSs, respectively. Then, the novel STR-GAT is designed by introducing spatio-temporal relations into conventional GAT to fully derive the mobility features of users to explore potential actions, while the derivative DDPG is adopted to perform tensor factorization with multiple available rules in parallel. Furthermore, the action smoothing and hierarchical-based replay buffer with priority-based and random sampling are designed and introduced into DDPG to stabilize training process and accelerate model convergence. Experimental simulation results on real-world datasets validate the superiorities of QPCS compared with the state-of-the-art approaches in predicting the QoS of component services in 5 G.

The accurate prediction of required resources in terms of storage, computing and bandwidth is essential for 5G to host diverse services. The existing efforts illustrate that it is more promising to efficiently predict the unknown required resources with a third-order tensor compared to the 2D-matrix-based solutions. However, most of them fail to leverage the inherent features hidden in network traffic like temporal stability and service correlation to build a third-order tensor for the multi-dimensional required resource prediction in an intelligent manner, incurring coarse-grained prediction accuracy. Furthermore, it is difficult to build a third-order tensor with rate-varied measurements in 5G due to different lengths of measurement time slots. To address these issues, we propose an Accurate Prediction of Multi-Dimensional Required Resources (APMR) approach in 5G via Federated Deep Reinforcement Learning (FDRL). We first confirm the resource requests originated from different Base Stations (BSs) at varied measurement rates have similar features in service and time domains, but cannot directly form a series of regular tensors. Built on these observations, we reshape these measurement data to form a series of standard third-order tensors with the same size, which include many elements obtained from measurements and some unknown elements needed to be inferred. In order to obtain accurately predicted results, the FDRL-based tensor factorization approach is introduced to intelligently utilize multiple specific iteration rules for local model learning, and the accuracy-aware and latency-based depreciation strategies are exploited to aggregate local models for resource prediction. Extensive simulation experiments demonstrate that APMR can accurately predict the multi-dimensional required resources compared to the state-of-the-art approaches.

Mobile Edge Computing (MEC)-enabled vehicular networks have emerged as a promising approach to enhancing the performance and efficiency of the Internet-of-Vehicles (IoV) applications. By leveraging some vehicles to act as transmission relays, multi-hop task offloading addresses the problem of intermittent connectivity between vehicles and edge servers to cope with the issues of network congestion or obstacles. However, two critical issues, i.e., uncooperative behaviors of selfish vehicles and network resource dynamics, resulting from multi-vehicle concurrent offloading are not fully considered in the existing work. To fill this gap, this paper proposes a novel and efficient task offloading scheme, namely MMTO, that exploits the multi-hop computational resources to maximize the system-wide profit, and supports incentive compatibility of vehicular users and concurrent offloading. Specifically, an iterative hierarchical estimation algorithm is designed to estimate the offloading delay and energy cost in order to iteratively optimize the offloading decisions. An energy-efficient routing approach is then proposed to schedule the transmission paths for the offloading vehicles. Furthermore, an effective reward-driven auction-based incentive mechanism is designed for incentivizing relayers and calculators to engage in collaboration. Both simulation and field experiments are conducted; extensive results demonstrate that MMTO outperforms the state-of-the-art approaches in terms of the system-wide profit improvement and overall task delay reduction.

Recent years have witnessed the proliferation of wireless energy transfer for Wireless Sensor Networks (WSNs), which are mainly used for data gathering in real-world applications. A number of studies have investigated mobile vehicle scheduling to charge sensor nodes via wireless Mobile Chargers (MCs). Unfortunately, most of them cannot parallelly charge all nodes in an intelligent manner with the global network attributes. Furthermore, the time-variable charging ignores the optimal data gathering, resulting in poor Joint Energy Replenishment and Data Gathering (JERDG). To fill this gap, this paper proposes a Federated Deep Reinforcement Learning (FDRL)-based JERDG (FERG) solution for WSNs. To this end, FERG first partitions the networks into a set of clusters to distribute the workload evenly among multiple MCs, and then designs an FDRL-based framework that incorporates various time-variant network attributes to determine the optimal schedule for charging and data gathering via multiple MCs and a base station (BS). The BS as the cloud server is responsible for global training of JERDG models, while multiple MCs will parallelly train local models to jointly charge energy-exhausted nodes and gather the data from all nodes in clusters. To reserve more personalized characteristics of each cluster, a density-based partial aggregation strategy is designed to train the global model. Furthermore, a reward-weighted update and selection solution is proposed to generate and exploit reference samples with high rewards. Simulation results obtained from various scenarios demonstrate that FERG significantly outperforms the state-of-the-art approaches in terms of network lifetime, energy efficiency and data collection latency.

Federated learning (FL) is recognized as a pivotal paradigm for 6G, offering decentralized model training without compromising data privacy. Recent works have proposed deploying FL in cell-free massive MIMO (CF-mMIMO) networks for reliable model transmission between FL clients and the server. Nevertheless, the problem of simultaneous access point (AP) clustering (i.e., dynamically forming AP groups to facilitate client-server communication) and transmit power allocation has not been thoroughly investigated. Furthermore, most existing solutions do not simultaneously consider the fast decision-making requirements brought by user mobility and the scalability of solutions in large-scale networks. To address this gap, we propose DACPA, a multi-agent deep reinforcement learning (DRL)-based scheme that accounts for client mobility (walking speed) and heterogeneous computing capabilities. DACPA strategically assigns each client a customized AP cluster and corresponding transmit power configuration, thereby optimizing model update latency. Extensive simulation results demonstrate the superior performance of DACPA in terms of convergence stability, spectral efficiency, global model update latency, and average energy consumption.

To leverage the vast amounts of onboard data while ensuring privacy and security, federated learning (FL) is emerging as a promising technology for supporting a wide range of vehicular applications. Although FL has great potential to improve the vehicular edge intelligence(VEI), challenges arise due to vehicle mobility, wireless channel instability, and data heterogeneity. To mitigate the issue of heterogeneous data across vehicles in FL, artificial intelligence-generated content (AIGC) can be employed as an innovative data synthesis technique to enhance FL model performance. In this paper, we propose AIGCassisted Federated Learning for Vehicular Edge Intelligence (GenFV). We further propose a weighted policy using the Earth Mover's Distance (EMD) to measure data distribution heterogeneity and introduce a convergence analysis for GenFV. Subsequently, we analyze system delay and formulate a mixedinteger nonlinear programming (MINLP) problem to minimize system delay. To solve this MINLP NP-hard problem, we propose a two-scale algorithm. At large communication scale, we implement label sharing and vehicle selection based on mobility and data heterogeneity. At the small computation scale, we optimally allocate bandwidth, transmission power and amount of generated data. Extensive experiments show that GenFV significantly improves the performance and robustness of FL in dynamic, resource-constrained environments, outperforming other schemes and confirming the effectiveness of our approach.

The evolution of future network and control technologies has enabled unmanned aerial vehicles (UAVs) to collaborate across diverse geographical areas and task domains, enhancing task execution efficiency through data and resource sharing. In response to the increasing demand for cross-domain task allocation and operations for UAVs, establishing robust authentication mechanisms within trusted domains has become a critical foundation for ensuring secure cross-domain access. Despite significant progress in UAV identity authentication and cross-domain access, challenges persist, such as cumbersome and inefficient processes, UAV resource limitations, and establishing trust relationships across different domains. To address these challenges, this paper introduces a dual blockchain-assisted trusted authentication scheme for UAVs' cross-domain access. Our approach utilizes a certificateless signcryption algorithm for lightweight UAV authentication, thereby eliminating the need for certificate management. Then, an efficient credit-based trust model is designed to measure the trustworthiness of data-in-transit and cross-domain entities. Furthermore, blockchain technology is introduced to store the relevant information of UAVs and credibility to assist cross-domain authentication. Theoretical security analysis and extensive simulations have been conducted, demonstrating the effectiveness and efficiency of our proposed scheme.

The growth of Electric Vehicles (EVs) places an increasingly heavy burden on the limited charging infrastructure, necessitating an effective charging station recommendation strategy that assists EVs in finding the most suitable charging stations. Deep reinforcement learning is a promising technology that has been applied to optimize EVs’ charging recommendations. However, existing schemes have low scalability and high communication costs as they usually require collecting real-time information on both charging requests and charger availability at various stations during policy training or execution. To address this challenge, we develop a real-time distributed charging station recommendation approach, named ReDirect, to minimize the charging duration experienced by EVs, considering dynamic charging requests of EVs and fluctuating availability at charging stations. ReDirect employs federated meta-reinforcement learning (RL) to empower distributed stations to collaboratively learn effective recommendation strategies and make decisions without sharing their local information, yielding improved scalability, reduced communication overhead, and enhanced data privacy. Furthermore, we conduct a rigorous theoretical analysis of the convergence performance of ReDirect. Extensive experimental results on real-world datasets demonstrate that ReDirect performs closely to the centralized recommendation algorithm and outperforms several state-of-the-art distributed algorithms in EV charging duration while realizing a balanced distribution of charging requests across multiple stations.

As a promising vehicular communication technology, Cellular Vehicle-to-Everything (C-V2X) is expected to ensure the safety and convenience of Intelligent Transportation Systems (ITS) by providing global road information. However, it is difficult to obtain global road information in practical scenarios since there will still be many vehicles on the road without onboard units (OBUs) in the near future. Specifically, although C-V2X vehicles have sensors that can perceive their surroundings and broadcast their perceived information to the C-V2X system, their line-of-sight (LoS) is limited and obscured by the environment, such as other vehicles and terrain. Besides, vehicles without OBUs cannot share their perceived information. These two problems cause extensive areas with unperceived information in the C-V2X system, and whether vehicles are in these areas is unknown. Thus, extending the perceivable range of the limited scenario for C-V2X applications that require global road information is necessary. To this end, this paper pioneers investigating the scenario inpainting task problem in C-V2X. To solve this challenging problem, we propose an effiCient trAfficScenario inpainTing (CAST) solution consisting of a generative architecture and knowledge distillation, simultaneously considering the inpainting precision and computation efficiency. Extensive experiments have been conducted to demonstrate the effectiveness of CAST in terms of Precise Inpaint Rate (PIR), Rough Inpaint Rate (RIR), Lane-Level Inpaint Rate (LLIR), and Inpaint Confidence Error (ICE), paving the way for novel solutions for the inpainting problem in more complex road scenarios.

Unmanned Aerial Vehicle (UAV)-assisted Mobile Edge Computing (MEC) has received extensive attention because it provides resilient computation services for multiple Mobile Users (MUs). However, due to the increasing scale of offloaded tasks, the uncertain mobility of MUs, and the limited energy budget of UAV and MUs, it is extremely challenging to achieve satisfactory Quality-of-Service (QoS). Non-Orthogonal Multiple Access (NOMA), a promising technology to serve multiple MUs with limited communication resources, has great potential to be integrated with MEC. To this end, this paper proposes a QoS-oriented NOMA-enhanced UAV-MEC system, which aims to capture the potential gains of uplink NOMA and enable more MUs to benefit from edge computing servers in resource-constrained UAV-assisted MEC environments. This synergy reduces MUs' uplink energy consumption but poses new challenges in resource allocation and UAV trajectory design. To address these challenges, we define a new metric called System Overhead Ratio (SOR) to reflect the system's QoS, and then consider a joint optimization problem of resource allocation, transmission power control, and UAV trajectory design, with the goal of minimizing the SOR. Given the NP-hard nature of the optimization problem, we propose a Lyapunov and convex optimization-based Low-complexity Online Resource allocation and Trajectory optimization method (LORT) to solve it, and further analyze the convergence and complexity of LORT. Finally, extensive simulations show that the proposed method surpasses other benchmarks, reducing the SOR by approximately$10\%$-$25\%$under various scenarios.

As a key technique for future networks, the performance of emerging multi-edge caching is often limited by inefficient collaboration among edge nodes and improper resource configuration. Meanwhile, achieving optimal cache hit rates poses substantive challenges without effectively capturing the potential relations between discrete user features and diverse content libraries. These challenges become further sophisticated when caching schemes are exposed to adversarial attacks that seriously impair cache performance. To address these challenges, we introduce RoCoCache, a resilient collaborative caching framework that uniquely integrates robust federated deep learning with proactive caching strategies, enhancing performance under adversarial conditions. First, we design a novel partitioning mechanism for multi-dimensional cache space, enabling precise content recommendations in user classification intervals. Next, we develop a new Discrete-Categorical Variational Auto-Encoder (DC-VAE) to accurately predict content popularity by overcoming posterior collapse. Finally, we create an original training mode and proactive cache replacement strategy based on robust federated deep learning. Notably, the residual-based detection for adversarial model updates and similarity-based federated aggregation are integrated to avoid the model destruction caused by adversarial updates, which enables the proactive cache replacement adapting to optimized cache resources and thus enhances cache performance. Using the real-world testbed and datasets, extensive experiments verify that the RoCoCache achieves higher cache hit rates and efficiency than state-of-the-art methods while ensuring better robustness. Moreover, we validate the effectiveness of the components designed in RoCoCache for improving cache performance via ablation studies.

Network-assisted full-duplex (NAFD) cell-free (CF) massive MIMO systems enable simultaneous uplink and downlink transmissions, where interference suppression and beamforming are critical for improving spectral efficiency and system performance. However, the asymmetric time-varying properties of current network traffic, coupled with the interference problems associated with complex network topologies, make existing resource allocation and interference management strategies difficult to handle, and unable to satisfy the low-latency, high-reliability Quality-of-Service (QoS) requirements of the growing number of terminal devices (TDs). To address these challenges, we propose a novel access method based on decoupled uplink-downlink multi-connectivity transmission to achieve flexible access selection and formulate an optimization problem that maximizes the cumulative fair spectral efficiency by simultaneously optimizing power allocation and link scheduling. To solve this mixed-integer nonlinear programming (MINLP) problem, we propose an optimized transfer scheme that reduces the dimensionality of the action and constraint spaces. Then, we characterize the network states as heterogeneous graph structures and employ node-level and metapath-level attention mechanisms for message passing and aggregation, and obtain graph-level scheduling policy via the heterogeneous graph neural network (HGNN). Finally, in light of the superior performance of Deep Reinforcement Learning (DRL) in exploration-based tasks, we design a holistic updating mechanism using environmental feedback and advantage state-action function, named as HGN-DRL for this end-to-end learning framework. Simulation results demonstrated the effectiveness and scalability of HGN-DRL in large-scale cell-free scenarios.

Machine learning has been a driving force in the evolution of tremendous computing services and applications in the past decade. Traditional learning systems rely on centralized training and inference, which poses serious privacy and security concerns. To solve this problem, distributed learning over wireless edge networks (DLWENs) emerges as a trending solution and has attracted increasing research interests. In DLWENs, corresponding services need to be placed onto the edge servers to process the distributed tasks. Apparently, different placement of training services can significantly affect the performance of all distributed learning tasks. In this article, we propose TASP, a task-aware service placement scheme for distributed learning in wireless edge networks. By carefully considering the structures (directed acyclic graphs) of the distributed learning tasks, the fine-grained task requests and inter-task dependencies are incorporated into the placement strategies to realize the parallel computation of learning services. We also exploit queuing theory to characterize the dynamics caused by task uncertainties. Extensive experiments based on the Alibaba ML dataset show that, compared to the state-of-the-art schemes, the proposed work reduces the overall delay of distributed learning tasks by 38.6% on average.

Graph neural network (GNN) is a state-of-the-art technique for learning structural information from graph data. However, training GNNs on large-scale graphs is very challenging due to the size of real-world graphs and the message-passing architecture of GNNs. One promising approach for scaling GNNs is distributed training across multiple accelerators, where each accelerator holds a partitioned subgraph that fits in memory to train the model in parallel. Existing distributed GNN training methods require frequent and prohibitive embedding exchanges between partitions, leading to substantial communication overhead and limited the training efficiency. To address this challenge, we propose XDGNN, a novel distributed GNN training method that eliminates the forward communication bottleneck and thus accelerates training. Specifically, we design an explanation-guided subgraph expansion technique that incorporates important structures identified by eXplanation AI (XAI) methods into local partitions, mitigating information loss caused by graph partitioning. Then, XDGNN conducts communication-free distributed training on these self-contained partitions through training the model in parallel without communicating node embeddings in the forward phase. Extensive experiments demonstrate that XDGNN significantly improves training efficiency while maintaining the model accuracy compared with current distributed GNN training methods.

Computation offloading utilizes powerful cloud and edge resources to process workflow applications offloaded from Mobile Devices (MDs), effectively alleviating the resource constraints of MDs. In end-edge-cloud environments, workflow applications typically exhibit complex task dependencies. Meanwhile, parallel tasks from multi-MDs result in an expansive solution space for offloading decisions. Therefore, determining optimal offloading plans for highly dynamic and complex end-edge-cloud environments presents significant challenges. The existing studies on offloading tasks for multi-MD workflows often adopt centralized decision-making methods, which suffer from prolonged decision time, high computational overhead, and inability to identify suitable offloading plans in large-scale scenarios. To address these challenges, we propose a Multi-agent Collaborative method for Workflow Task offloading in end-edge-cloud environments with the Actor-Critic algorithm called MCWT-AC. First, each MD is modeled as an agent and independently makes offloading decisions based on local information. Next, each MD's workflow task offloading decision model is obtained through the Actor-Critic algorithm. At runtime, an effective workflow task offloading plan can be gradually developed through multi-agent collaboration. Extensive simulation results demonstrate that the MCWT-AC exhibits superior adaptability and scalability. Moreover, the MCWT-AC outperforms the state-of-art methods and can quickly achieve optimal/near-optimal performance.

Trajectory synthesis with a series of fake locations has been deemed as a promising obfuscation technology to preserve the individual privacy of users in Location-Based Services (LBSs). However, a number of previous approaches fail to take into consideration the geographic distance and motion direction of the real locations to synthesize trajectories. As a result, most of them always cannot represent the statistical characteristics of real trajectories in a privacy-preserving manner, and thus suffer from various attacks through data analysis. To tackle this issue, this paper presents SPSD, a novel privacy-preserving trajectory synthesis approach with a$k$-anonymous guarantee, through extracting the semantic, geographic and directional similarity of locations from the real trajectories to create plausible trajectories. SPSD first classifies all historical trajectory data into a series of sets for location identity, by introducing the visiting time and visiting duration, which can clearly represent the semantic information of locations. Then,$4k$locations and$2k$of$4k$ones have been selected from each set to act as the initial disguises of each corresponding real location, with quantitative semantic and geographic similarities, respectively. In order to find enough fake locations for each real location in less time, the candidate locations have been narrowed down to$k$in direction recovery through step-by-step screening, with the$k$-anonymous property. Experiment results built on the real-world trajectory datasets indicate that SPSD has outperformed the previous approaches in terms of semantic similarity, directional accuracy and security resistance to synthesize privacy-preserving trajectories at the tolerable time cost.

Wireless-powered multi-access edge computing (WP-MEC), as a promising computing paradigm with the great potential for breaking through the power limitations of wireless devices, is facing the challenges of reliable task offloading and charging power allocation. Towards this end, we formulate a joint optimization problem of wireless charging and computation offloading in socially-aware D2D-assisted WP-MEC to maximize the utility, characterized by wireless devices’ residual energy and the strength of social relationship. To address this problem, we propose a deep reinforcement learning (DRL)-based approach with hybrid actor-critic networks including three actor networks and one critic network as well as with Proximal Policy Optimization (PPO) updating policy. Further, to prevent the policy collapse, we adopt the PPO-clip algorithm which limits the update steps to enhance the stability of algorithm. The experimental results show that the proposed algorithm can achieved superior convergence performance and, meanwhile, improves the average utility efficiently compared to other baseline approaches.

The reduction of energy consumption will be even more urgent in cloud data centers due to the explosive increase of application data. Virtual machine (VM) integration is a relatively standard technology currently applied for computing facilities of data centers. However, excessive VM consolidation can easily lead to local hot spots that lower the energy efficiency and reliability of data centers. In addition, on account of the impact of heat recirculation in data centers, the traditional VM scheduling strategy cannot comprehensively ponder optimizing the holistic data center energy, which encompasses both server energy and cooling energy. To handle these issues, we proposedEAVMS- an Energy-Aware VM Scheduling approach for minimizing the holistic energy consumption of data centers. EAVMS adopts a two-phase approach to gain energy efficiency while guaranteeing QoS. First, EAVMS leverages a Blended Genetic algorithm and Simulated Annealing algorithm (BGSA) to optimize the initial placement of VMs. Second, EAVMS utilizes a dynamic migration algorithm to achieve effective migration by setting a maximum server temperature threshold without violating the service level agreement (SLA) that cuts down energy consumption by moderating the hot spots of servers. We conducted extensive experiments using two real-world traces (i.e., PlanetLab and Google Cluster datasets) to evaluate the effectiveness of EAVMS. The experimental results unveil that our approach is capable of saving 3.23$ \%$–43.07$ \%$in the holistic energy consumption of cloud data centers with only a tiny service performance degradation compared to other state-of-the-art alternatives (e.g., MJPM, GRANITE, TAS, XINT-GA, and Random).

In recent years, the Internet of Medical Things (IoMT) has significantly boosted the healthcare industry. In the IoMT, federated learning (FL) can be applied, which can increase the utilization of patient data while protecting patient privacy. This work proposes a cutting-edge framework that combines differential privacy (DP) with FL and utilizes game theory to optimize power allocation and client selection in IoMT environments. Utilizing a Stackelberg game model, we orchestrate power allocation strategies among IoMT devices to enhance communication efficiency while meeting stringent privacy standards. We propose non-uniform and uniform pricing strategies based on the availability of network state information. Then, we derive the optimal interference price and power for the IoMT devices using nonlinear programming and convex optimization. In addition, our approach integrates DP to protect patients’ data, carefully balancing between privacy and the accuracy of the learning model. The conducted simulations show that our proposed method is effective in terms of communication efficiency, privacy preservation and FL performance.

In the edge computing system, split learning (SL) is an emerging distributed learning approach that allows mobile users (MUs) and edge nodes (ENs) to train the model together without sharing the raw data of the MU. Although MU can preserve its privacy in SL, attacks on the intermediate data at the cut layer for model training can still lead to privacy leakage, which prevents privacy-sensitive MUs from participating in training. Therefore, it is important to implement an effective incentive mechanism to motivate MUs to join SL while preserving their privacy. In this work, from the perspective of maximizing the utility of edge service provider (ESP) while considering the privacy-sensitivity of different MUs, the incentive problem of ESP and MUs is transformed into the utility optimization problem, and an incentive mechanism based on the differential privacy (DP) and contract theory is established to model the interactions between the MUs and EN. The obtained convex optimization problem is obtained through the mathematical derivations, and the optimal contract is presented by solving this problem. The simulation results demonstrate the effectiveness of our proposed privacy preserved incentive mechanism.

Recently, federated learning (FL) has been threat-ened by the gradient inversion attack that infers user-private data from shared gradients. To cope with this problem, the differential privacy (DP) technique is widely employed in FL. However, when FL faces the non-independent identically distributed (non-IID) data scenarios, applying DP to protect user data privacy remains inefficient in terms of model accuracy and communication costs. In this paper, inspired by the Mixup data augmentation method, we propose a privacy-preserving FL approach called Fed2VAEs to address this problem. Specifically, we introduce a Mixup Module consisting of two variational autoencoders to remove the private information of user data. To balance the trade-off between data privacy and data utility, from the perspective of mutual information, a learning objective is proposed. We conduct extensive experiments under different non-IID data settings, and the experimental results show that Fed2VAEs can significantly reduce the communication cost and improve model accuracy (up to 8.57%) on the premise of successfully protecting user data privacy.

Real-time object detection in disasters facilitates efficient rescue operations and mitigates secondary disasters. Artificial intelligence techniques and remote sensing have recently been widely used in disaster management, especially for vision-related tasks. To counter the need for more annotated data in deep learning-based object detection, we introduce a disaster-specific dataset called DisasterScope containing high-resolution disaster-related imagery. The dataset encompasses a range of images depicting diverse disaster scenarios, enhancing the breadth of training data for improved model performance. Besides, we present an enhanced version of the Real-Time Models for Object Detection (RTMDet) and conduct training and validation on the mentioned dataset. Experimental results demonstrate that the proposed approach outperforms state-of-the-art methods.

Federated Graph Learning (FGL) has garnered widespread attention by enabling collaborative training on multiple clients for semi-supervised classification tasks. However, most existing FGL studies do not well consider the missing inter-client topology information in real-world scenarios, causing insufficient feature aggregation of multi-hop neighbor clients during model training. Moreover, the classic FGL commonly adopts the FedAvg but neglects the high training costs when the number of clients expands, resulting in the overload of a single edge server. To address these important challenges, we propose a novel FGL framework, named SpreadFGL, to promote the information flow in edge-client collaboration and extract more generalized potential relationships between clients. In SpreadFGL, an adaptive graph imputation generator incorporated with a versatile assessor is first designed to exploit the potential links between subgraphs, without sharing raw data. Next, a new negative sampling mechanism is developed to make SpreadFGL concentrate on more refined information in downstream tasks. To facilitate load balancing at the edge layer, SpreadFGL follows a distributed training manner that enables fast model convergence. Using real-world testbed and benchmark graph datasets, extensive experiments demonstrate the effectiveness of the proposed SpreadFGL. The results show that SpreadFGL achieves higher accuracy and faster convergence against state-of-the-art algorithms.

The implicit bias of gradient descent has long been considered the primary mechanism explaining the superior generalization of over-parameterized neural networks without overfitting, even when the training error is zero. However, the implicit bias toward adversarial robustness has rarely been considered in the research community, although it is crucial for the trustworthiness of machine learning models. To fill this gap, in this paper, we explore whether consecutive layers collaborate to strengthen adversarial robustness during gradient descent. By quantifying this collaboration between layers using our proposed concept, co-correlation, we demonstrate a monotonically increasing trend in co-correlation, which implies a decreasing trend in adversarial robustness during gradient descent. Additionally, we observe different behaviours between narrow and wide neural networks during gradient descent. We conducted extensive experiments that verified our proposed theorems.

With the rapid development of the Internet-of-Vehicles (IoV) technologies, security and privacy issues associated with IoV data sharing have become increasingly prominent. Although attribute-based encryption (ABE) schemes offer effective solutions to these problems, the prevalent single-point failure vulnerabilities and risks of user privacy leakage in existing ABE schemes must be addressed. To this end, an original hidden policy scheme based on multi-authority ciphertext policy ABE is proposed. This scheme validates users by introducing multiple attribute authorities and generating intermediate attribute keys, effectively dispersing single-point performance pressure. Simultaneously, partial policy-hiding techniques are developed to ensure efficient system operation while protecting user privacy. Furthermore, this scheme introduces a central authority to track potentially malicious attribute authorities, preventing them from continuously generating incorrect attribute intermediate keys, thereby maintaining the overall security of the system. Additionally, by updating and revoking attribute versions, a flexible attribute revocation mechanism is achieved to further enhance system flexibility. Through in-depth security and performance analyses, the scheme is proven to be both secure and efficient for securing IoV.

Being an up-and-coming application scenario of mobile edge computing (MEC), the post-disaster rescue suffers multitudinous computing-intensive tasks but unstably guaranteed network connectivity. In rescue environments, quality of service (QoS), such as task execution delay, energy consumption and battery state of health (SoH), is of significant meaning. This paper studies a multi-user post-disaster MEC environment with unstable 5G communication, where device-to-device (D2D) link communication and dynamic voltage and frequency scaling (DVFS) are adopted to balance each user's requirement for task delay and energy consumption. A battery degradation evaluation approach to prolong battery lifetime is also presented. The distributed optimization problem is formulated into a mixed cooperative-competitive (MCC) multi-agent Markov decision process (MAMDP) and is tackled with recurrent multi-agent Proximal Policy Optimization (rMAPPO). Extensive simulations and comprehensive comparisons with other representative algorithms clearly demonstrate the effectiveness of the proposed rMAPPO-based offloading scheme.

Traffic forecasting has become a core component of Intelligent Transportation Systems. However, accurate traffic forecasting is very challenging, caused by the complex traffic road networks. Most existing forecasting methods do not fully consider the topological structure information of road networks, making it difficult to extract accurate spatial features. In addition, spatial and temporal features have different impacts on traffic conditions, but the existing studies ignore the distribution of spatial-temporal features in traffic regions. To address these limitations, we propose a novel graph neural network architecture named Attention-based Spatial-Temporal Adaptive Integration Gated Network (AST-AIGN). The originality of AST-AIGN is to obtain a spatial feature that more accurately reflects the topological structure of the road networks by embedding Graph Attention Network (GAT) into Jumping Knowledge Net (JK-Net). We propose a data-dependent function called spatial-temporal adaptive integration gate to process the diversity of feature distribution and highlight features in road networks that significantly affects traffic conditions. We evaluate our model on two real-world traffic datasets from the Caltrans Performance Measurement System (PEMS04 and PEMS08), and the extensive experimental results demonstrate the proposed AST-AIGN architecture outperforms other baselines.

In Mobile Edge Computing (MEC) systems, Unmanned Aerial Vehicles (UAVs) facilitate Edge Service Providers (ESPs) offering flexible resource provisioning with broader communication coverage and thus improving the Quality-of-Service (QoS). However, dynamic system states and various traffic patterns seriously hinder efficient cooperation among UAVs. Existing solutions commonly rely on prior system knowledge or complex neural network models, lacking adaptability and causing excessive overheads. To address these critical challenges, we propose the DisOff, a novel profit-aware cooperative offloading framework in UAV-enabled MEC with lightweight Deep Reinforcement Learning (DRL). First, we design an improved DRL with twin critic-networks and delay mechanism, which solves the Q-value overestimation and high variance and thus approximates the optimal UAV cooperative offloading and resource allocation. Next, we develop a new multi-teacher distillation mechanism for the proposed DRL model, where the policies of multiple UAVs are integrated into one DRL agent, compressing the model size while maintaining superior performance. Using the real-world datasets of user traffic, extensive experiments are conducted to validate the effectiveness of the proposed DisOff. Compared to benchmark methods, the DisOff enhances ESP profits while reducing the DRL model size and training costs.

Password, fingerprint and face recognition are the most popular authentication schemes on smartphones. However, these user authentication schemes are threatened by shoulder surfing attacks and spoof attacks. In response to these challenges, eye movements have been utilized to secure user authentication since their concealment and dynamics can reduce the risk of suffering those attacks. However, existing approaches based on eye movements often rely on additional hardware (such as high-resolution eye trackers) or involve a time-consuming authentication process, limiting their practicality for smartphones. This paper presents DEyeAuth, a novel dual-authentication system that overcomes these limitations by integrating eyelid patterns with eye gestures for secure and convenient user authentication on smartphones. DEyeAuth first leverages the unique characteristics of eyelid patterns extracted from the upper eyelid margins or creases to distinguish different users and then utilizes four eye gestures (i.e., looking up, down, left, and right) whose dynamism and randomness can counter threats from image and video spoofing to enhance system security. To the best of our knowledge, we are among the first to discover and prove that the upper eyelid margins and creases can be used as potential biometrics for user authentication. We have implemented the prototype of DEyeAuth on Android platforms and comprehensively evaluated its performance by recruiting 50 volunteers. The experimental results indicate that DEyeAuth achieves a high authentication accuracy of 99.38% with a relatively short authentication time of 6.2 seconds, and is effective in resisting image presentation, video replaying, and mimic attacks.

Cellular vehicle-to-everything (C-V2X) can provide ubiquitous mobile computing and communication services for vehicles, acting as a key technology to realize future urban intelligent transportation systems (ITS). Due to the lack of long-term insight into complex and dynamic urban road states, the existing historical road information-based strategies for C-V2X applications are inadequate to satisfy their high-performance requirements. Fortunately, it is feasible to provide fine-grained future road states for C-V2X decision-making by predicting traffic states to address this issue. To this end, this article proposes a fine-grained joint traffic prediction method in the urban road network with high-spatial complexity (ROUTE). ROUTE uniquely forecasts both micro-level (individual vehicle states) and macro-level traffic, thus supporting the diverse requirements of C-V2X applications. ROUTE is comprised of three key parts, including a vehicle coordinate transformation model, a spatial interaction-based turning model, and a micro-traffic prediction model. First, the complex spatial topology of the urban regional road network is normalized in ROUTE using the coordinate transformation model. Second, the turning model calculates the next road that the vehicle chooses after leaving the current one. Third, a transformer and generative adversarial network-based model (FORMERGAN) predicts future micro-traffic states. Extensive experimental results demonstrate that ROUTE surpasses its competitors in accurately predicting fine-grained long-term micro-traffic and macro-traffic states.

Mobile devices are becoming increasingly capable of delivering intelligent services by leveraging deep learning architectures such as deep neural networks (DNNs). However, due to the compute-intensive nature of these tasks, mobile devices often struggle to handle them independently, leading to the exploration of collaborative inference as a promising solution for achieving low-latency mobile intelligence. Despite its potential benefits, many challenges need to be addressed in realizing the full potential of inference acceleration. This article presents a collaborative device-edge inference optimization framework as a promising solution to inference acceleration. The framework comprises fundamental modules, including the parameters generator (PG), accuracy predictor (AP), delay calculator (DC), and optimizer (OP), which are specifically designed to identify the optimal set of parameters for model compression, DNN partition, and feature compression. To illustrate its implementation, an example of a deep CNN network is introduced, and the collaborative inference latency optimization is formulated as a mixed-integer programming problem. The implementation of a specific algorithm instance using a quantum-inspired OP within the optimization framework is then presented. A multiple regression-based inference accuracy prediction model is proposed to maintain inference accuracy close to that of the original network while significantly reducing the time consumption during the offline phase. Through various simulation scenarios involving inference tasks of AlexNet and RegNet on CIFAR-10, incorporating diverse hardware computation specifications and wireless communication link conditions, the proposed framework demonstrates superior performance in terms of inference acceleration compared to the compared methods.

In the digital divide regions, the edge computing can improve the performance of application services for the Internet of Things (IoT) devices. However, the lagging of information and communication technology (ICT) results in congested access spectrum and imbalanced computational load. Moreover, the mobility of IoT devices further exacerbates the fluctuating quality of communication links and the frequent changing of access positions. So, how to realize the reliable service requirements of devices in a heterogeneous environment with multiscale constraints should be considered appropriately and comprehensively. In this article, we model a relay-assisted multiaccess edge computing (MEC) framework, employing multihop transmission to enable the cross-domain service coverage. Under this framework, we formulate a quantitative model to characterize communication and computation processes within task migration, and derive analytical results for service latency. To improve the access resource efficiency, we adopt a joint nonorthogonal multiple access (NOMA) scheme to extend the transmission dimension, and employ proportional fairness to dynamically allocate resources. Besides, we propose a multiagent deep reinforcement learning (DRL) for optimizing the long-term task offloading scheduling, address the optimization problem of maximizing the system throughput efficiency. And we improve the action exploration and output dimensions of DRL to achieve convergence and performance enhancement. Simulation and analytical results show that our proposed algorithm outperforms the comparison algorithms in the key performance indicators.

Machine learning-based semantic communication is a promising enabler for future-generation wireless network systems such as 6G networks. In practice, effective semantic communication requires online training for unknown content. In highly mobile vehicular networks, however, reliable, and efficient model training becomes significantly challenging. The existing distributed learning approaches are also unable to effectively operate in highly dynamic vehicular semantic communication networks. To address these challenges, we propose a novel mobility-aware split-federated with transfer learning (MSFTL) framework based on vehicle task offloading scenarios in this paper. To enable adaptation to the complex vehicle semantic communication, the proposed framework divides the training of the model into four parts and uses the proposed new splitfederated learning. Furthermore, to improve training efficiency, model accuracy, and the ability to adapt in highly mobile environments, we also present a new transfer learning approach integrated into the proposed framework. Particularly, we propose a high-mobility training resource optimisation mechanism based on a Stackelberg game for MSFTL to further reduce training costs and adapt vehicle mobility scenarios. We also investigate the performance of the proposed schemes through extensive simulations. The results validate the proposed approach and indicate its superiority compared to the conventional learning frameworks for semantic communication in vehicular networks.

Biometric-based authentication methods have been widely used, for example on portable devices (e.g., Android and iOS devices). However, there are several known limitations in existing authentication methods based on biometrics (e.g., those using facial, iris, and fingerprint). For example, in a healthcare context, a user may be physically incapable of completing the authentication due to his/her medical conditions. Hence, as a complementary authentication mechanism, there have been attempts to also utilize electrocardiogram (ECG). In this work, we propose an ECG authentication system that leverages deep learning. Specifically, to achieve generalization ability, complementary ensemble empirical decomposition (CEEMD) is introduced in our design. Moreover, a 1-D Multi-scale Convolutional Neural Network (1-D MCNN) is implemented to achieve accurate authentication. To evaluate the usability of our proposed approach, we have performed extensive experiments on eight databases, and the findings show that our proposed approach achieves good performance even on abnormal databases and can be adapted for different application environments. In addition, our adopted data from eight public databases requires theoretical statistical treatment for practical applications in real authentication scenarios.

The emerging Space-Air-Ground Integrated Networks (SAGIN) empower Mobile Edge Computing (MEC) with wider communication coverage and more flexible network access. However, the fluctuating user traffic and constrained computing architecture seriously hinder the Quality-of-Service (QoS) and resource utilization in SAGIN. Existing solutions generally depend on prior knowledge or adopt static resource provisioning, lacking adaptability and resulting in serious system overheads. To address these important challenges, we propose THOAS, a novel Traffic-aware lightweight Hierarchical Offloading framework towards Adaptive Slicing-enabled SAGIN. First, we innovatively separate SAGIN into Communication Access Platforms (CAPs) and Computation Offloading Platforms (COPs). Next, we design a new self-attention-based prediction method to accurately capture the traffic changes on each platform, enabling adaptive slice resource adjustments. Finally, we develop an improved deep reinforcement learning method based on proximal clipping with dynamic confidence intervals to reach optimal offloading. Notably, we employ knowledge distillation to compress offloading policies into lightweight networks, enhancing their adaptability in resource-limited SAGIN. Using real-world datasets of user traffic, extensive experiments are conducted. The results show that the THOAS can accurately predict traffic and make adaptive resource adjustments and offloading decisions, which outperforms other benchmark methods on multiple metrics under various scenarios.

Information granules are effective in revealing the structure of data. Therefore, it is a common practice in data mining to use information granules for classifying datasets. In the existing granular classifiers, the information granules are often classified according to the standard membership function only without considering the influence of different feature weights on the quality of granules and label classification results. In this article, we utilize the feature weighting of data to produce the information granules with high consistency rate called FIG. Firstly, we use consistency rate and contribution scores to generate information granules. Then, we propose a granular two-stage classifier GTC based on FIG. GTC divides the data into fuzzy and fixed points and then calculates the interval matching degree to assign data points to the most suitable cluster in the second step. Finally, we compare FIG with two state-of-the-art granular models (T-GrM and FGC-rule), and classification accuracy is also compared with other classification algorithms. The extensive experiments on synthetic datasets and public datasets from UCI show that FIG has sufficient performance to describe the data structure and excellent capability under the constructed granular classifier GTC. Compared with T-GrM and FGC-rule, the time overhead required for FIG to obtain information granules is reduced by an average of 51.07%, the per unit quality of the granules is also increased by more than 14.74%. Compared with other classification algorithms, an average of 5.04% improves GTC accuracy.

Virtual machine (VM) consolidation strategies are widely used in cloud data centers (CDC) to optimize resource utilization and reduce total energy consumption. Although existing strategies consider current and future resource utilization, the impact of sudden bursts in historical resource utilization on the hosts has been underestimated in uncertain future periods. Insufficient analysis of historical resource utilization may increase the risk of host overloading and Service Level Agreement Violation (SLAV). By defining historical and future trends based on resource utilization, we propose a novel combined trend VM consolidation (CTVMC) strategy which can effectively reduce energy consumption and SLAV. The VMs with the largest combined trend are selected for migration to prevent host overloading. Based on the temporal locality and prediction technique, CTVMC then employs the past, present, and future resource utilization to filter candidate hosts, and identifies the most complementary host to place VM using combined trends. We conduct extensive simulation experiments with PlanetLab Trace and Google Cluster Trace in the CloudSim simulator. Compared with the well-known strategies, CTVMC strategy using the PlanetLab Trace can reduce the number of migrations by over 72.39%, SLAV by over 75.85%, and ESV (a combined metric that judges the trade-off between energy consumption and SLAV) by over 81.54%. According to the Google Cluster Trace, our strategy can reduce the number of migrations by over 61.51%, SLAV by over 37.37%, and ESV by over 35.30%.

Edge computing satisfies sudden demands of computation-intensive applications of Internet of Things (IoT) devices. Multi-hop task offloading has been a promising technology to provide edge services to areas with poor server coverage via multi-hop task forwarding. However, the existing multi-hop offloading approaches have primarily assumed that complete information is required, which does not always hold in heterogeneous IoT systems due to the privacy. To overcome this limitation, we propose a novel two-stage method with incomplete information (TMII) to minimize overall task execution cost with an incomplete information setting. Specifically, a hierarchical minority game (HMG) is proposed to estimate the offloading costs by the hierarchical estimation model and the historical data in Stage I. By comparing the estimated offloading cost with the local cost, each IoT device individually decides where to execute the tasks. In Stage II, a tree-based routing mechanism schedules the transmission efficient paths for the offloading nodes by building distributed tree structures. The augmented paths balance the transmission loads to further reduce the offloading delay. Furthermore, the extensive simulation experiments demonstrate TMII outperforms the state-of-art approaches in terms of overall cost reduction with less communication overhead.

Vehicular Edge Computing (VEC) is a transportation-specific version of Mobile Edge Computing (MEC) designed for vehicular scenarios. Task offloading allows vehicles to send computational tasks to nearby Roadside Units (RSUs) in order to reduce the computation cost for the overall system. However, the state-of-the-art solutions have not fully addressed the challenge of large-scale task result feedback with low delay, due to the extremely flexible network structure and complex traffic data. In this paper, we explore the joint task offloading and resource allocation problem with result feedback cost in the VEC. In particular, this study develops a VEC computing offloading scheme, namely, a Lagrange multipliers-based adaptive computing offloading with prediction model, considering multiple RSUs and vehicles within their coverage areas. First, the VEC network architecture employs GAN to establish a prediction model, utilizing the powerful predictive capabilities of GAN to forecast the maximum distance of future trajectories, thereby reducing the decision space for task offloading. Subsequently, we propose a real-time adaptive model and adjust the parameters in different scenarios to accommodate the dynamic characteristic of the VEC network. Finally, we apply Lagrange Multiplier-based Non-Uniform Genetic Algorithm (LM-NUGA) to make task offloading decision. Effectively, this algorithm provides reliable and efficient computing services. The results from simulation indicate that our proposed scheme efficiently reduces the computation cost for the whole VEC system. This paves the way for a new generation of disruptive and reliable offloading schemes.

Unmanned aerial vehicle (UAV)-assisted wireless communication systems are able to provide high-quality services and ubiquitous connectivity for massive Internet of Things (IoT) devices. In this paper, we study the Age of Information (AoI) and energy tradeoff in a system where an employed UAV performs data collection for multiple IoT nodes (INs). Bearing in mind the importance of AoI and energy consumption during the data collection process, we present a multi-objective optimization problem to minimize the AoI and UAV energy consumption. To explore the tradeoff between AoI and energy consumption, we jointly optimize the collection time, the UAV trajectory, and the duration of time slots. Due to the non-convexity of the formulated problem, we divide the main problem into three sub-problems and address them by leveraging successive convex approximation (SCA) and Lagrangian dual methods. Finally, we design a multi-variable fixed algorithm to iteratively solve the three sub-problems. Simulations are carried out to investigate the tradeoff between AoI and UAV energy consumption, revealing that reducing AoI and energy consumption simultaneously is unattainable. Furthermore, the convergence and validity of the proposed algorithm are presented and analyzed.

Attributed social networks are pervasive in real life and play a crucial role in shaping various aspects of society. These networks not only capture the connections between individuals but also encompass the associated attributes and characteristics. Analyzing and understanding these attributes provide insights into social behaviors, information diffusion patterns, and the formation of influential communities. Consequently, we propose a novel algorithm for detecting fairness-aware maximal cliques in the attributed social networks. We extract the concept lattice of attributed social networks and quantify these concepts using the concept stability and fairness measures defined in this article. By utilizing the proposed fairness-aware distance, we identify fairness-aware maximal cliques within attributed social networks. The effectiveness of the algorithm is then validated using five real-world network datasets. Experimental results fully demonstrate the effectiveness and scalability of our approach in identifying key structures, analyzing attribute networks, and promoting the development of responsible computational systems.

Camouflaged object detection has been considered a challenging task due to its inherent similarity and interference from background noise. It requires accurate identification of targets that blend seamlessly with the environment at the pixel level. Although existing methods have achieved considerable success, they still face two key problems. The first one is the difficulty in removing texture noise interference and thus obtaining accurate edge and frequency domain information, leading to poor performance when dealing with complex camouflage strategies. The latter is that the fusion of multiple information obtained from auxiliary subtasks is often insufficient, leading to the introduction of new noise. In order to solve the first problem, we propose a frequency domain reconstruction module based on contrast learning, through which we can obtain high-confidence frequency domain components, thus enhancing the model’s ability to discriminate target objects. In addition, we design a frequency domain representation decoupling module for solving the second problem to align and fuse features from theRGBdomain and the reconstructed frequency domain. This allows us to obtain accurate edge information while resisting noise interference. Experimental results show that our method outperforms 12 state-of-the-art methods in three benchmark camouflaged object detection datasets. In addition, our method shows excellent performance in other downstream tasks such as polyp segmentation, surface defect detection, and transparent object detection.

Unmanned aerial vehicles (UAVs) have emerged as pivotal roles within internet of vehicles (IoV), serving as mobile base stations. However, while expanding coverage and improving mobility, the deployment of UAVs also poses a threat to the integrity and privacy of sensitive data due to open wireless communication channels in IoV. Therefore, preventing unauthorized access and data tampering is critically important between UAVs and vehicles. For the authenticity and legitimacy of the UAV certificate, existing authentication approaches may lead to significant challenges in key management overhead or dependence on a trusted third party. In this paper, a blockchain-based authentication scheme for UAV-assisted IoV system (BASUV) is proposed. This solution enables dependable UAV registration and authentication services, and permits the dynamic addition and removal. Specifically, blockchain is introduced to achieve the decentralized management and distributed trust of the UAV certificate ledger. Furthermore, to prevent information tampering and identity deception, we design CMPES, a novel combined scheme based on multiple public key generators (PKGs) for encryption and signature. Identical key pair in encryption and signature can reduce key generation and management overhead. The security and experimental analysis demonstrates the effectiveness and efficiency of the proposed scheme.

Due to the maneuverability and cost-effectiveness, UAVs are visioned as a versatile assistant for networking in intelligent transportation systems. Per-packet path reconstruction that reveals the multi-hop forwarding path of each packet is a fundamental service for network management and optimization. Unfortunately, most existing reconstruction schemes are designed for static networks with stationary devices which cannot be applied to UAV networks with strong mobility and frequent topology changes. Besides, the limited energy and resources of UAVs make it even more challenging to reconstruct dynamic paths. To achieve accurate and low-cost reconstruction, we propose an incremental path reconstruction (InPrec) for dynamic UAV networks. With InPrec, each UAV only records the changes of its one-hop neighbors in a distributed and change-driven manner. The sink UAV then incrementally recovers the full path information by replaying the recorded changes to the historical paths. In this way, InPrec can adapt to the topology changes and avoid repetitive records of the common sub-paths in dynamic UAV networks. To explore the pros and cons of InPrec, we conduct measurement studies and theoretical analysis from perspective of information entropy. Simulations also demonstrate that InPrec can accurately reconstruct the paths with time-varying topology and reduces much redundancy (by 85% on average) of the state-of-the-art work. As far as we know, this is the first path reconstruction approach applicable to large-scale dynamic UAV networks.

With the unprecedented scalability issues rising in vehicular edge computing (VEC), we argue in this paper that the scalability, along with the remarkable growth of demands for offloading, should be integrated into the modelling for effective offloading decision-making strategies requested by a large number of vehicles. A two-stage game-theory model can depict offloading decision-making strategies by considering both the revenue of network operators and the cost of VEC users. However, heuristic processes of solving such models show significant limitations in terms of high computational complexity and energy consumption due to the changing VEC environment. Therefore, our objective in this study is to solve the game-theory model efficiently and achieve scalable offloading for the changing VEC environment. We first develop a two-stage game-theory model for the offloading decision-making strategy for VEC, by which an operator’s revenue, energy consumption and latency are considered. Then a neural network (NN) model is designed to learn the predicted behaviours of the established game-theory model for offloading decisions in a more efficient manner. After that, a feature-based transfer learning algorithm is proposed for scalable offloading optimization under unseen VEC environments. Experimental results show that the proposed NN can significantly improve the efficiency of solving the game theory model, and the developed transfer learning approach can effectively achieve the scalability of offloading decisions in a changing VEC environment. The results demonstrate that the accuracy of the proposed transfer learning approach is 37% higher than that of several state-of-the-art algorithms, and the runtime halves.

Through deploying computing resources at the network edge, Mobile Edge Computing (MEC) alleviates the contradiction between the high requirements of intelligent mobile applications and the limited capacities of mobile End Devices (EDs) in smart communities. However, existing solutions of computation offloading and resource allocation commonly rely on prior knowledge or centralized decision-making, which cannot adapt to dynamic MEC environments with changeable system states and personalized user demands, resulting in degraded Quality-of-Service (QoS) and excessive system overheads. To address this important challenge, we propose a novel Personalized Federated deep Reinforcement learning based computation Offloading and resource Allocation method (PFR-OA). This innovative PFR-OA considers the personalized demands in smart communities when generating proper policies of computation offloading and resource allocation. To relieve the negative impact of local updates on global model convergence, we design a new proximal term to improve the manner of only optimizing local Q-value loss functions in classic reinforcement learning. Moreover, we develop a new partial-greedy based participant selection mechanism to reduce the complexity of federated aggregation while endowing sufficient exploration. Using real-world system settings and testbed, extensive experiments demonstrate the effectiveness of the PFR-OA. Compared to benchmark methods, the PFR-OA achieves better trade-offs between delay and energy consumption and higher task execution success rates under different scenarios.

With the emergence of the 5G/6G communications, edge computing has attracted increasing research interests in recent years. To provide pervasive 5G/6G edge computing services, numerous edge servers are required for service coverage, and the deployment cost can be$\gt$10000 times larger than the deployment cost of the 4G infrastructure. To address this fundamental limit, we propose ParallEdge, a deployment scheme that employs mobile edge servers for cost-effective service coverage. ParallEdge is designed based on the observation that the processing delay and server moving delay become comparable in many computing-intensive applications in the 5G/6G edge computing. Unlike the traditional “move-then-process” frameworks, ParallEdge follows a “move-while-processing” paradigm, which exploits the parallelism between task processing and server movement to enable resource sharing among more users. Moreover, with the joint optimization of path planning and task scheduling for multiple mobile servers, the deployment cost for service coverage can be further reduced. We analyze the approximation gap of the proposed algorithm, and conduct extensive simulation experiments based on the real-world application data, and the results show that ParallEdge can significantly reduce deployment cost and improve resource utilization compared to the state-of-the-art schemes.

Vision-based real-time object detection has become a key fundamental service for smart-city applications such as auto-drive and digital twins. Due to the limited resource available at camera devices, edge-assisted object detection has attracted increasing research attention. The existing edge-assisted schemes often assume stable or averaged wireless links during the frame offloading process. However, the assumption does not hold in real-world dynamic edge networks and will lead to significant performance degradation in terms of both detection latency and accuracy. In this paper, we propose$Kite$, a link-adaptive scheme for real-time object detection. Based on measurement studies and systematic analysis, we devise a lightweight yet representative performance indicator – “frame-anchor” distance, to incorporate the immeasurable impact of wireless dynamics into a measurable metric. Based on this performance indicator, we model the offloading process as an integer nonlinear programming problem, and propose an online link-adaptive algorithm for frame offloading decisions. We implement$Kite$in a neuro-enhanced live streaming application and conduct comparative experiments with four different datasets in WiFi/LTE based edge networks. The results show thatKitecan improve the detection accuracy by 40.53% in highly dynamic networks, compared to the state-of-the-art works.

Blink detection is essential for various human-computer interaction scenarios, such as virtual reality and driving state detection. It has gained significant attention from industry and academia alike in recent years. Existing non-contact detection systems (cameras, acoustics, etc.) have made significant progress, but various issues have prevented their widespread adoption, including privacy concerns, line-of-sight requirements, and cost issues. Therefore, there is a critical need for a simple and robust system that can detect eye blinks using common commercial equipment. In this paper, we propose BlinkRadar, which uses a low-cost customized impulse-radio ultra- wideband (IR-UWB) radar for non-contact and fine-grained blink detection. BlinkRadar can reliably detect driver blinks in driving conditions, making it possible to infer drowsy driving. To effectively extract the eye blink signal, we analyzed real experimental data to study the characteristics of the eye blink pattern and successfully used the multi-sequence variational mode decomposition (MS-VMD) algorithm to separate the blink signal from the noise signal. We conducted extensive experiments in two different environments (a quiet room and moving vehicles) and found that BlinkRadar had an average blink detection accuracy of over 96.2%. Our results demonstrate the feasibility of using UWB radar for non-contact eye blink detection.

Internet-of-Things (IoT) has played a critical role in developing sustainable smart cities and emerging numerous latency-sensitive IoT applications. Mobile edge computing (MEC) federation has the capability to incorporate a transparent resource management approach, which enables the sharing and utilization of MEC services from edge infrastructure providers (EIPs) and provides agile access services to mobile devices (MDs). In this paper, we investigate the joint optimization problem of computation offloading, task migration, and resource allocation in the MEC federation. The objective is to minimize the weighted sum of latency and energy consumption while maintaining load balancing under the constraint of the long-term migration cost budget of EIPs. To address the problem, we decompose it into two sub-problems: 1) the MDs clustering sub-problem and 2) the sub-problem of joint computation offloading, task migration, and resource allocation. Firstly, an MDs clustering matching (MDCM) algorithm is proposed to cluster the MDs in edge servers (ESs) according to the differences in channel gains. Afterward, the second sub-problem is simplified by the Lyapunov optimization technique, and then we propose a Transformer-based mobility prediction model and a decentralized deep deterministic policy gradient (DDPG)-based framework to solve it. Extensive simulation results demonstrate the cost-efficiency of the proposed algorithm.

The recent breakthrough in Wireless Power Transfer (WPT) provides a promising way to prolong network lifetime by employing a charging vehicle to replenish energy. Data transmissions from nodes typically happen in response to physical sensory events, leading to time-varying energy consumption. To improve charging efficiency, the existing schemes collect energy information by employing a data-gathering vehicle or data collection protocol. However, in duty cycle networks, these schemes either incur extra vehicles or high data collection delay. To solve this problem, we propose an mobile adaptive charging scheme with rapid data sharing (rShare), which establishes multi-layer collection trees and collects overall energy data to the vehicle. A spatial predicted active sending (SPAS) algorithm is proposed for distant nodes to actively estimate the future position and transmit their data to cover potential positions of the charging vehicle, which significantly reduces data collection delay. We also propose an estimated time of arrival (ETA)-aware scheme based on the TSP Nearest Neighbor algorithm that updates the charging path based on the collected data. Extensive simulation results demonstrate that our scheme outperforms the state-of-the-arts in terms of dead node avoidance with less communication overhead.

Federated Learning (FL) has been widely used to facilitate distributed and privacy-preserving machine learning in recent years. Different from centralized training that usually has independent and identically distributed (IID) distribution of all users' data, FL suffers from significant communication cost and model performance degradation due to the non-IID data from individual edge devices. Existing work calibrates the local models using a global anchor or sharing global data. However, these studies either assume that the central server has the global dataset or require participating devices to share raw data, which incurs additional communication costs and privacy concerns. In this paper, we proposeSlaugFL, a novel selective GAN-based data augmentation scheme for communication-efficient edge FL, which selects representative devices to share specific local class prototypes with the central server for GAN model training and improves FL performance with the trained GAN. Specifically, on the server side, we generate diverse labeled candidate data with the help of powerful generative models (the stable diffusion model and ChatGPT). To ensure that the GAN-generated data possesses a similar domain to the devices' local data, we leverage these selected local class prototypes to pick desired GAN training samples from the labeled candidate data. On the device side, we propose a dual-calibration approach consisting of two calibration manners. Concretely, we augment devices' non-IID data with the trained GAN model, where devices utilize the trained GAN model to generate the IID dataset. Thus, the device's local model can be directly calibrated with the augmented data. With the generated IID data, we yield privacy-free (p-f) global class prototypes which can be employed to further calibrate devices' local models. Combining these two calibrations effectively improves devices' local models. Extensive experimental results show thatSlaugFLcan significantly reduce the communication cost (up to 52.49%) while achieving the same accuracy, compared to the state-of-the-art work.

Quantitative performance analysis plays a pivotal role in theoretically investigating the performance of Vehicular Edge Computing (VEC) systems. Although considerable research efforts have been devoted to VEC performance analysis, all of the existing analytical models were designed to derive the average system performance, paying insufficient attention to the worst-case performance analysis, which hinders the practical deployment of VEC systems to support mission-critical vehicular applications, such as collision avoidance. To bridge this gap, we develop an original performance analytical model by virtue of Stochastic Network Calculus (SNC) to investigate the worst-case end-to-end performance of VEC systems. Specifically, to capture the bursty feature of task generation, an innovative bivariate Markov Chain is firstly established and rigorously analysed to derive the stochastic task envelope. Then, an effective service curve is created to investigate the severe resource competition among vehicular applications. Driven by the stochastic task envelope and effective service curve, a closed-form end-to-end analytical model is derived to obtain the latency bound for VEC systems. Extensive simulation experiments are conducted to validate the accuracy of the proposed analytical model under different system configurations. Furthermore, we exploit the proposed analytical model as a cost-effective tool to investigate the resource allocation strategies in VEC systems.

By utilizing on-board sensors and computing resources in intelligent vehicles, vehicular crowdsensing can collect a series of sensing data. Typically, sensing vehicles can be divided into opportunistic vehicles with fixed trajectories and participatory vehicles with changeable trajectories. Therefore, to complete sensing tasks more effectively, how to combine the advantages of the mobility characteristics of the two vehicles is a challenging problem. To solve this problem, this paper innovatively proposes a joint scheduling and incentive-driven two-stage hybrid sensing method. Specifically, the method is divided into two stages: opportunistic vehicle selection and participatory vehicle scheduling. In particular, both types of vehicles are managed through the Crowd Sensing Platform (CSP). For the first stage, this paper proposes a reverse auction-based incentive mechanism to select the lowest-cost set of vehicles to complete sensing tasks. This mechanism mainly consists of two steps: winning vehicle selection and reward payment. It is also verified that the proposed mechanism can ensure the individual rationality and truthfulness of opportunistic vehicles. For the second stage, based on the first-stage sensing results, this paper proposes a Soft Actor-Critic (SAC) based approach to scheduling participatory vehicle trajectories to complete sensing tasks. In addition, this paper also considers sensing fairness to ensure the balance of sensing task completion in different sub-regions. Through the two-stage hybrid sensing method, this paper aims to minimize the CSP overhead while ensuring sensing fairness. Finally, extensive evaluation results based on Roma taxi data sets demonstrate that the proposed method works effectively and outperforms other benchmark schemes in different working scenarios.

Spatial Crowdsourcing (SC) has been an indispensable Location-based Service where the SC server assigns tasks to workers based on the locations of task requesters and workers, raising strong privacy concerns. Limited by the computational and time complexity, existing works prefer differential privacy-based methods to protect location privacy. However, most differential privacy-based works ignore the road network, perturbing locations on two-dimensional plane, resulting in more failures in tasks and moreover extensive privacy disclosure in practice. This paper aims to implement a multi-task assignment with both high utility and efficiency while protecting the location privacy of both task requesters and workers on road networks. Specifically, we design a Road Network-aware Exponential Mechanism and propose an Obfuscated Locations Selection algorithm to guarantee location privacy of all participants and extensive privacy. Then, we propose region distance. Based on this, we further formulate multi-task assignment as a Binary Linear Programming problem and a utility-aware optimization problem. We solve the first problem to obtain optimal efficiency and then propose a utility-aware optimization algorithm for the second problem to improve the utility. Our experiments demonstrate sufficient and stable privacy guarantee and the well-performance on both utility and efficiency of our framework.

In connected autonomous vehicles (CAVs), the driving safety can be greatly deteriorated, in the presence of occlusions which are adverse to CAVs' perception of region-of-interest (RoI). Collaborative perception on the basis the information sharing of occlusions among CAVs, in a real-time and accurate manner, provides a means of the occlusion-free RoI perception for safe driving. In this paper, we propose a novel framework ofCollaborativeOcclusion-freePerception (COFP) in CAVs, to regain the real-time and accurate occlusion awareness. The innovative COFP targets two goals: well-balanced computation resource allocation, as well as fast and high-quality RoI information fusion. Specifically, the resource allocation problem, with the objective of minimizing CAVs' completion delay, is formulated as a multi-player continuous potential game and solved by a better response dynamics (BRD) algorithm. The RoI information fusion, with the objective of maximizing the overall object depiction quality, is formulated as a combinatorial optimization problem, and solved by a modified discrete salp swarm (MDSSA) algorithm. Experimental results show that the proposed COFP with 5GHz computing power can achieve full occlusion awareness for CAVs with 69.61% completion time reduction and 19.03% fusion quality improvement, compared to the existing methods.

To exploit the massive amounts of onboard data in vehicular networks while protecting data privacy and security, federated learning (FL) is regarded as a promising technology to support enormous vehicular applications. Despite that FL has great potential to improve the architecture of intelligent vehicular networks, the mobility of the vehicles and the dynamic nature of wireless channels make the integration of FL and vehicular networks more challenging. In this paper, we propose a vehicle mobility- and channel dynamic-aware FL (MADCA-FL) scheme to fit vehicular networks and enhance learning performances. This novel scheme enables the RSU to select appropriate vehicles and weightedly average the local models. Afterward, MADCA-FL formulates a problem to maximize the model accuracy while assuring the latency and energy restrictions, by jointly optimizing the computation and communication resources. With a mixed- integer non-linear programming structure, the problem is NP-hard. Firstly, we utilize the successive convex approximation algorithm to handle the non-convexity, and then apply the Lagrange multiplier method and the block coordinate descent method to obtain the optimal solution. Extensive experiments are conducted to confirm the effectiveness of our proposed scheme.

Electric Vehicle-assisted Multi-access Edge Computing (EV-MEC) is a promising paradigm where EVs share their computation resources at the network edge to perform intensive computing tasks while charging. In EV-MEC, a fundamental problem is to jointly decide the charging power of EVs and computation task allocation to EVs, for meeting both the diverse charging demands of EVs and stringent performance requirements of heterogeneous tasks. To address this challenge, we propose a new joint charging scheduling and computation offloading scheme (OCEAN) for EV-MEC. Specifically, we formulate a cooperative two-timescale optimization problem to minimize the charging load and its variance subject to the performance requirements of computation tasks. We then decompose this sophisticated optimization problem into two sub-problems: charging scheduling and computation offloading. For the former, we develop a novel safe deep reinforcement learning (DRL) algorithm, and theoretically prove the feasibility of learned charging scheduling policy. For the latter, we reformulate it as an integer non-linear programming problem to derive the optimal offloading decisions. Extensive experimental results demonstrate that OCEAN can achieve similar performances as the optimal strategy and realize up to 24% improvement in charging load variance over three state-of-the-art algorithms while satisfying the charging demands of all EVs.

Generative adversarial networks (GANs) have been advancing and gaining tremendous interests from both academia and industry. With the development of wireless technologies, a huge amount of data generated at the network edge provides an unprecedented opportunity to develop GANs applications. However, due to the constraints such as bandwidth, privacy, and legal issues, it is inappropriate to collect and send all data to the cloud or servers for analysis, training, and mining. Thus, deploying and training GANs at the edge becomes a promising alternative solution. The instability of GANs introduced by non-independent and identical data (Non-IID) poses significant challenges to training GANs. To address these challenges, this paper presents a novel federated learning framework for GANs, namely,Collaborated gAmeParallel Learning (CAP). CAP supports parallel training of data and models for GANs, breaking the isolated training among generators that exists in the previous distributed algorithms, and achieving collaborative learning among cloud, edge servers, and devices. Then, to further enhance the ability of CAP-GAN for addressing Non-IID issues, we propose a Mix-Generator module (Mix-G) which divides a generator into the sharing layer and personalizing layer. The Mix-G module extracts the generic and personalization features and improves the performance of CAP-GAN on extremely personalizing datasets. Experimental results and analysis substantiate the usefulness and superiority of our proposed CAP-GAN scheme which can achieve better results in the Non-IID scenarios compared with the state-of-the-art algorithms.

Vehicular Edge Computing (VEC) is the transportation version of Mobile Edge Computing (MEC) in road scenarios. One key technology of VEC is task offloading, which allows vehicles to send their computation tasks to the surrounding Roadside Units (RSUs) or other vehicles for execution, thereby reducing computation delay and energy consumption. However, the existing task offloading schemes still have various gaps and face challenges that should be addressed because vehicles with time-varying trajectories need to process massive data with high complexity and diversity. In this paper, a VEC-based computation offloading model is developed with consideration of data dependency of tasks. The minimization of the average response time and average energy consumption of the system is defined as a combinatorial optimization problem. To solve this problem, we propose aMobility-aware dependent taskoffloading (MESON) Scheme for urban VEC and develop a DRL-based algorithm to train the offloading strategy. To improve the training efficiency, a vehicle mobility detection algorithm is further designed to detect the communication time between vehicles and RSUs. In this way, MESON can avoid unreasonable decisions by lowering the size of the action space. Moreover, to improve the system stability and the offloading successful rate, we design a task priority determination scheme to prioritize the tasks in the waiting queue. The experimental results show that MESON is superior compared to other task offloading schemes in terms of the average response time, average system energy consumption, and offloading successful rate.

The potential of using electrocardiogram (ECG), an important physiological signal for humans, as a new biometric trait has been demonstrated, and ongoing efforts have focused on utilizing deep learning (e.g., 2D neural networks) to improve authentication accuracy (with some efficiency tradeoffs). In most of the existing ECG-based authentication approaches, the ECG recordings for enrollment and testing are collected within short intervals (e.g., within an hour). However, since ECG biometrics change over time, this design may decrease authentication accuracy when ECG recordings are collected weeks or even months prior. In this article, we propose 1D Integrated EfficientNet (1DIEN) to achieve cross-session ECG authentication. We adopt 1D neural networks as a lightweight alternative to 2D neural networks, and a voting scheme is designed to reduce variance and improve general authentication performance. We use three public ECG databases (i.e., an inter-session database, a mixed-session database, and an intra-session database) to evaluate our proposed 1DIEN under different authentication scenarios. The experimental results show that our approach achieves satisfactory performance for ECG authentication at a 3-month interval and is suitable for practical applications.

A large number of distributed applications necessitate accurate network distance, for example, in the form of delay or latency, to ensure the Quality of Service (QoS). Due to high network measurement overhead and severe traffic congestion, network distance prediction has been introduced, instead of direct network measurements, to infer the unknown network distance with the partial measurements. However, most existing efforts neglect to fully capitalize on the potential latent factors, such as spatial correlations, long-existing temporal results and multi-rule exploration fusion, to achieve better accuracies with quicker convergence. To fill this gap, in this paper, we propose an Accurate Prediction of Network Distance (APND) solution via Federated Deep Reinforcement Learning (FDRL), which has four novel features distinguishing from the previous work. Firstly, a local feature-based matrix with low rank is established in each network cluster, referring to a set of neighbor nodes, to represent the potential spatial correlations among reachable node-pairs. Secondly, the parallel FDRL-based matrix factorization with multi-rule exploration fusion is introduced into APND and executed in all local clusters to minimize prediction errors and accelerate learning convergence. Thirdly, the long-existing learning experience is designed for local model training via Deep Reinforcement Learning (DRL) with rapid convergence. Fourthly, following the real-world routing paths, the cross-domain network nodes are simultaneously classified into adjacent clusters, built on the spatial correlations among them, and their coordinates will be further refined with error-based and average-based policies. Extensive experiments built on available real-world datasets illustrate that APND can accurately predict network distance compared with state-of-the-art approaches at the moderate computing cost.

Network Function Virtualization (NFV) introduces a new network architecture that offers different network services flexibly and dynamically in the form of Service Function Chains (SFCs), which refer to a set of Virtualization Network Functions (VNFs) chained in a specific order. However, the service latency often increases linearly with the length of SFCs due to the sequential execution of VNFs, resulting in sub-optimal performance for most delay-sensitive applications. In this paper, a novel Parallel VNF Placement (PVFP) approach is proposed for real-world networks via Federated Deep Reinforcement Learning (FDRL). PVFP has three remarkable characteristics distinguishing from previous work: 1) PVFP designs a specific parallel principle, with three parallelism identification rules, to reasonably decide partial VNF parallelism; 2) PVFP considers SFC partition in multi-domains built on their remaining resources and potential parallel VNFs to ensure that VNFs can be reasonably distributed for resource balancing among domains; 3) FDRL-based framework of parallel VNF placement is designed to train a global intelligent model, with time-variant local autonomy explorations, for cross-domain SFC deployment, avoiding data sharing among domains. Simulation results in different scenarios demonstrate that PVFP can significantly reduce the end-to-end latency of SFCs at the medium resource expenditures to place VNFs in multiple administrative domains, compared with the state-of-the-art mechanisms.

Topology robustness is critical to the connectivity and lifetime of large-scale Internet-of-Things (IoT) applications. To improve robustness while reducing the execution cost, the existing robustness optimization methods utilize neural learning schemes, including neural networks, deep learning, and reinforcement learning. However, insufficient exploration of reinforcement learning agents for topological environments is likely to yield local optima. Moreover, convergence speed is influenced by the sparse reward problem generated while exploring topological environments. To address these problems, this study proposes a self-adaptive robustness optimization method with an evolutionary multi-agent for IoT topology (ROMEM). ROMEM introduces a new multi-agent co-evolution scheme that leverages a non-deterministic strategy to extend the exploration in multi-directions, enabling the reinforcement learning agent to transcend local optima. Furthermore, ROMEM presents a novel distributed training mechanism for multiple agents to accelerate convergence. Experimental results demonstrate that ROMEM can achieve multi-directional collaborative training and outperform other state-of-the-art learning-based robustness optimization methods in terms of convergence efficiency and robustness.

To achieve low latency and high link utilization, ECN-based transport protocols (i.e., DCTCP) are widely deployed in data center networks (DCN). In multi-tenant environment, however, the newly introduced ECN-enabled TCP greatly impairs the performance of applications with out-dated and misconfigured TCP stacks. The reason is that the ECN-enabled switch fails to treat the mixed TCP traffic fairly, resulting in the distinguished performance gap between the ECN-enabled and ECN-disabled TCPs. This paper proposes DDT (Dual Dynamic Thresholds), an active queue management algorithm (AQM) to achieve the flow-level fairness for coexisting heterogeneous TCP traffic. DDT monitors the switch queue in real time, and dynamically tunes the distance between ECN-marking and packet-dropping thresholds to mitigate the aggressiveness difference between the ECN-enabled and ECN-disabled TCPs. The results of real implementations and large-scaled simulations show that DDT elegantly fills the aggressiveness gap of heterogeneous TCP traffic without disturbing their own control loops, while only introducing acceptable deployment overhead at switch.

As an effective technique to relieve the problem of resource constraints on mobile devices (MDs), the computation offloading utilizes powerful cloud and edge resources to process the computation-intensive tasks of mobile applications uploaded from MDs. In cloud-edge computing, the resources (e.g., cloud and edge servers) that can be accessed by mobile applications may change dynamically. Meanwhile, the parallel tasks in mobile applications may lead to the huge solution space of offloading decisions. Therefore, it is challenging to determine proper offloading plans in response to such high dynamics and complexity in cloud-edge environments. The existing studies often preset the priority of parallel tasks to simplify the solution space of offloading decisions, and thus the proper offloading plans cannot be found in many cases. To address this challenge, we propose a novel real-time and Dependency-aware task Offloading method with Deep Q-networks (DODQ) in cloud-edge computing. In DODQ, mobile applications are first modeled as Directed Acyclic Graphs (DAGs). Next, the Deep Q-Networks (DQN) is customized to train the decision-making model of task offloading, aiming to quickly complete the decision-making process and generate new offloading plans when the environments change, which considers the parallelism of tasks without presetting the task priority when scheduling tasks. Simulation results show that the DODQ can well adapt to different environments and efficiently make offloading decisions. Moreover, the DODQ outperforms the state-of-art methods and quickly reaches the optimal/near-optimal performance.

The combination of 5G/6G and edge computing has been envisioned as a promising paradigm to empower pervasive and intensive computing for the Internet-of-Things (IoT). High deployment cost is one of the major obstacles for realizing 5G/6G edge computing. Most existing works tried to deploy the minimum number of edge servers to cover a target area by avoiding coverage overlaps. However, following this framework, the resource requirement per server will be drastically increased by the peak requirement during workload variations. Even worse, most resources will be left under-utilized for most of the time. To address this problem, we propose CoopEdge, a cost-effective server deployment scheme for cooperative multi-access edge computing. The key idea of CoopEdge is to allow deploying overlapped servers to handle variable requested workloads in a cooperative manner. In this way, the peak demands can be dispersed into multiple servers, and the resource requirement for each server can be greatly reduced. We propose a Two-step Incremental Deployment (TID) algorithm to jointly decide the server deployment and cooperation policies. For the scenarios involving multiple network operators that are unwilling to cooperate with each other, we further extend the TID algorithm to a distributed TID algorithm based on the game theory. Extensive evaluation experiments are conducted based on the measurement results of seven real-world edge applications. The results show that compared with the state-of-the-art work, CoopEdge significantly reduces the deployment cost by 38.7% and improves resource utilization by 36.2%, and the proposed distributed algorithm can achieve a comparable deployment cost with CoopEdge, especially for small-coverage servers.

One fundamental problem of content caching in edge computing is how to replace contents in edge servers with limited capacities to meet the dynamic requirements of users without knowing their preferences in advance. Recently, online deep reinforcement learning (DRL)-based caching methods have been developed to address this problem by learning an edge cache replacement policy using samples collected from continuous interactions (trial and error) with the environment. However, in practice, the online data collection phase is often expensive and time-consuming, thus hindering the practical deployment of online DRL-based methods. To bridge this gap, we propose a novel Agile edge Cache replacement method based on Offline-online deep Reinforcement learNing (ACORN), which can efficiently learn an edge cache replacement policy offline from a training dataset collected by a behavior policy (e.g., Least Recently Used) and then improve it with fast online fine-tuning. We also design a specific convolutional neural network structure with multiple branches to effectively extract content popularity knowledge from the dataset. Experimental results show that the offline policy generated by ACORN outperforms the behavior policy by up to 38%. Through online fine-tuning, ACORN also achieves the number of cache hits as good as that of several advanced DRL-based methods while significantly reducing the number of training epochs by up to 40%.

In elastic cloud service systems, it is a challenge to evaluate and match the fluctuating resource demand of workloads. Existing studies typically monitor workload characteristics and build models that map these characteristics to actual demand. However, workload characteristics are multidimensional, and the impact of each dimension on resource demand differs, so it requires differentiated treatment when building models. This paper proposes a Correlation-Based Universal Resource Matching (CBURM) strategy to realize a Heterogeneous and Elastic Cloud Service System (HECSS). CBURM consists of a Correlation-based resource Demand Evaluation (CDE) method and a Universal Resource Measurement (URM) scheme. Specifically, CDE discriminates the relevance of each dimension in workload characteristics, based on the correlations between workload characteristics and the demand. Then, it generates resource demand decisions dimension by dimension, from the most relevant to the least relevant dimensions. After that, it generates a complete decision tree model to evaluate subsequent workload demand for heterogeneous resources. Finally, URM optimizes the resource allocation to achieve a low-overhead resource matching. Experimental results show that, URM reduces the total comprehensive operation cost by 82%+, compared to a normal resource allocation scheme. Additionally, CDE outperforms two state-of-the-art methods (LTP and 2SP), with its performance closer to the ideal baseline. Specifically, CDE achieves a 40.275% overall resource saving rate, which is 38.62% higher than LTP and 8.46% higher than 2SP. Besides, CDE achieves a 92.43% average service quality satisfaction ratio, higher than the 82.9% and 88.83% achieved respectively by LTP and 2SP.

With the rapid growth of cloud computing, frequent workload bursts show an increasing influence on the Quality of Service (QoS) and energy efficiency of cloud-based data centers. Existing virtual machine placement schemes are expected to optimize either QoS or energy efficiency for cloud data centers running under bursty workload conditions. To bridge this gap, we propose a burst-aware and thermal-efficient virtual machine placement technique calledBTVMP. BTVMP adopts a two-step strategy to achieve energy efficiency while assuring QoS. First, BTVMP leverages a split-and-recombine algorithm – SAR – to deal with bursty workloads. SAR prioritizes critical workloads while preventing low-priority workloads from starvation, thereby assuring QoS. Second, BTVMP utilizes an enhanced simulated annealing algorithm calledESAto offer optimal thermal-efficient virtual machine placement (VMP) solutions, aiming to minimize the energy consumption of data centers. To facilitate estimating energy consumption, we integrate into BTVMP a thermal model that takes into account heat re-circulation effects. We conduct extensive experiments with a real-world trace. We compare BTVMP with the leading-edge VMP strategies, including Genetic Algorithm (XINT-GA), Power-Aware and Performance-Guaranteed Virtual Machine Placement (PPVMP), Peak Load Scheduling Control Method (PLSC), First Come First Serve (FCFS), and GReedy based scheduling Algorithm miNImizing Total Energy (GRANITE). The experimental results unveil that BTVMP not only enhances QoS but also exhibits superb energy efficiency. In particular, BTVMP reduces PLSC's workload delay and FCFS's critical workload delay by 18$\%$and 11$\%$, respectively. Moreover, BTVMP lowers the total energy consumption of the three alternative algorithms –GRANITE, XINTGA, PPVMP, and PLSC – by anywhere between 27.8$\%$and 49.4$\%$.

The explosion of large-scale data has increased the scale and capacity of storage clusters in data centers, leading to huge power consumption issues. Cloud providers can effectively promote the energy efficiency of data centers by employing energy-aware data placement techniques, which primarily encompass storage cluster's power and cooling power. Traditional data placement approaches do not diminish the overall power consumption of the data center due to the heat recirculation effect between storage nodes. To fill this gap, we build an elaborate thermal-aware data center model. Then we propose two energy-efficient thermal-aware data placement strategies, ETDP-I and ETDP-II, to reduce the overall power consumption of the data center. The principle of our proposed algorithm is to utilize a greedy algorithm to calculate the optimal disk sequence at the minimum total power of the data center and then place the data into the optimal disk sequence. We implement these two strategies in a cloud computing simulation platform based on CloudSim. Experimental results unveil that ETDA-I and ETDP-II outperform MinTin-G and MinTout-G in terms of the supplied temperature of CRAC, storage nodes power, cooling cost, and total power consumption of the data center. In particular, ETDP-I and ETDP-II algorithms can save about 9.46%-38.93% of the overall power consumption compared to MinTout-G and MinTin-G algorithms.

To cope with the complex and constantly changing communication environment, Multi-Link Operation (MLO) has attracted extensive attention in research and development of next-generation Wi-Fi technology, IEEE 802.11be standard (Wi-Fi 7). MLO can transmit information simultaneously on different channels in the same device, which can significantly increase the capacity of Wi-Fi for future communication systems. Previous relevant studies have shown that network throughput is not simply and positively correlated with frame aggregation length. Furthermore, due to the variability of communication environments, the optimal frame aggregation length in the scheduling process is not unique within a given time, and the traditional methods are limited to solving non-convex optimization problems. To fill this gap, we present a novel approach using deep reinforcement learning (DRL) to tackle the optimization of frame aggregation lengths in 802.11be for multiple links. Our research offers a comprehensive depiction of the communication and interaction structure among multiple links and DRL, which helps drive the advancement of artificial intelligence (AI) solutions in future network designs and demonstrates the feasibility of exploiting DRL in next-generation wireless networks. Extensive simulation experiments show that the proposed method can achieve superior performance compared to the existing methods.

The use of evolutionary strategies in generating images is a common practice within the computational art community. In particular, a popular approach is to approximate a target image using overlapping, semi-transparent shapes and optimizing their attributes to increase similarity to the target image. However, existing methods usually require millions of fitness evaluations to construct good approximations. Within the evolutionary computation and machine learning communities, the use of surrogates has shown to decrease the number of fitness evaluations while achieving state-of-the-art results. Despite the gained traction of surrogate-assisted algorithms, their use within the computational art community is nonexistent. To address this, we extend the previous work of Bayesian Optimization by density-ratio estimation (BORE) to the image approximation task. By estimating the probability of improvement acquisition function using a convolutional probabilistic classifier, we search for solutions that maximize the acquisition function using an evolutionary strategy. By conducting experiments on six different styled target images, we demonstrate the superior performance achieved with the use of surrogate assistance.

Digital twin (DT) technology enables the replica of physical objects and environmental statuses of a physical system, which can be used for further simulation, analysis, and prediction. By combining DT with mobile edge computing (MEC), a new paradigm called digital twin edge networks (DITEN) is able to fill the gap between physical edge networks and digital systems and provide novel services to physical devices. Due to possible failure in data sensing, balancing sensing time and successful sensing rate needs to be considered to ensure the freshness of collected data in DITEN. Additionally, an optimal data scheduling policy is necessary to ensure efficient communication between physical devices and the edge server while maintaining the accuracy of DT. Therefore, this paper proposes a joint optimization problem for the sensing and communication for DITEN. Due to the nonconvex nature of the formulated problem, we decompose the original problem into three subproblems, and an iterative optimization algorithm is proposed to minimize the system overhead of DNT realization. The effectiveness of the proposed method is evaluated through extensive simulations.

Vehicle trajectory prediction is a promising technology for improving the performance of Cellular Vehicle-to-Everything (C-V2X) applications by providing future road states. Various vehicle trajectory prediction methods have been proposed to increase the accuracy of the predicted trajectory. Although the existing vehicle trajectory prediction methods can accurately predict the future trajectory under the assumption that data comply with the Independent and Identically Distributed (IID), their performance is seriously degraded in practical implementation due to the ubiquitous distribution shifts in vehicle trajectory data. To improve the universality of the vehicle trajectory prediction method, generalizing the method to an environment that never appeared in the training data, namely, the Domain Generalization (DG) task, should be considered. Thus, we propose a plug-and-play inFORmaTive caUsality-based vehicle trajectory predictioN architecturE (FORTUNE) to improve the DG capability of vehicle trajectory prediction methods. First, a novel structural causal model (SCM) of vehicle trajectory prediction is established to simulate the causality of the data-generating process. Second, we utilize the principle of mutual information to learn the invariant representation of the SCM. Third, an invariant knowledge-transferring module is proposed to increase learning ability without destroying the structure of the original model. The results from simulation experiments demonstrate that the proposed scheme can significantly improve the DG capability of vehicle trajectory prediction methods.

Earth observation applications, such as emergency surveillance and disaster relief, are thriving due to the availability of earth observation satellites that provide timely and objective observation data at different spatial and temporal scales. Such observation data is processed at the satellite edge with orbital edge computing, leading to potentially reduced bandwidth cost and transmission delay. However, most existing studies primarily focus on optimizing computation offloading but ignore the consideration of object observation and observation data transmission. To fill this gap, this paper proposes a novel scheduling approach that jointly considers observation satellites, relay satellites, and computing satellites in LEO satellite systems, aiming to maximize the number of completed observation tasks while taking into account various requirements of observation, transmission, and computation resources. Specifically, we first formulate the problem of jointly scheduling observation, relay, and computing satellites to maximize the number of accomplished observation tasks. Then, we decompose the formulated problem into two sub-problems and design a resource-aware algorithm called ORCA to determine the optimal scheduling of observation, relay, and computing satellites. Simulation results demonstrate that ORCA outperforms existing algorithms in terms of completing a number of observation tasks.

Vehicular edge computing (VEC) has been introduced to bring powerful in-proximity computing solutions to vehicles. VEC is able to boost the development of vehicular networks by handling computing tasks and accommodating artificial intelligence (AI). To fulfill the requirements of low latency and security in realizing AI for vehicular networks, and fully utilize the vehicles' capabilities on sensing and computing, federated learning (FL) in VEC emerges as a potential solution. However, privacy protection, data security and information asymmetry issues pose challenges on efficiently and securely motivating more vehicles to participate in FL. Thus, this paper proposes a contract-based incentive mechanism for blockchain-enabled FL, which employs contract theory to establish an optimal contract design between VEC servers and vehicles. We present the necessary and sufficient conditions to obtain an optimal contract and analyze the simplification of the constraints. The simulation results show that our proposed method is effective in providing incentives and outperforms other benchmark schemes.

In mobile edge computing (MEC)-assisted federated learning (FL), the MEC users can train data locally and send the results to the MEC server to update the global model. However, the implementation of FL may be prevented by the selfish nature of MEC users, as they need to contribute considerable data and computing resources while scarifying certain data privacy for the FL process. Therefore, it is of great importance to design an efficient incentive mechanism to motivate the users to join the FL. In this work, with explicit consideration of the impact of wireless transmission and data privacy, we design an energy-efficient and privacy-preserved incentive scheme to facilitate the FL process by investigating interactions between the MEC server and MEC users in a MEC-assisted FL system. Using a Stackelberg game model, we explore the transmit power allocation and privacy budget determination of MEC users and reward strategy of the MEC server, and then analyze the Stackelberg equilibrium. The simulation results demonstrate the effectiveness of our proposed scheme.

In the era of big data, network data increase rapidly in a distributed manner, giving birth to the network big data. Network big data with the extra features such as distributed and decentralized data collection and storage, distributed and parallel data processing, more complex and evolving relationships among data, and heterogeneous data representation, pose opportunities together with challenges to the traditional network analysis algorithms. A hopeful solution is combining machine learning techniques with network big data analysis. In this paper, we proposed a novel time series clustering method which effectively combines machine learning techniques with network big data analysis for fault diagnosis task based on network logs. Verification experimental results on classic HDFS dataset demonstrate the outstanding performance of the proposed method.

LoRa has been widely applied in various vertical areas such as smart grids, smart cities, etc. Packet collisions caused by concurrent transmissions have become one of the major limitations of LoRa networks due to the ALOHA MAC protocol and dense deployment. The existing studies on packet recovery usually assume that the collided packet signals are above the noise floor. However, considering the large-scale deployment and low-power nature of LoRa communications, many collided packets are below the noise floor. Consequently, the existing schemes will suffer from significant performance degradation in practical LoRa networks. To address this issue, we propose CPR, a Cooperative Packet Recovery mechanism aiming at recovering the collided packets below the noise floor. CPR firstly employs the incoherence of signals and noises at multiple gateways to detect and extract the frequency features of the collided packets hidden in the noise. Then, CPR adopts a novel gateway selection strategy to select the most appropriate gateways based on their packet power domain features extracted from collision detection, such that the interference can be eliminated and the original packets can be recovered. Extensive experimental results demonstrate that CPR can significantly increase the symbol recovery ratio in low-SNR scenarios.

With the gradual development of unmanned aerial vehicles (UAV) related disciplines such as mechanics, electronics and wireless communication. UAV technology is an important direction for the future development of sixth generation mobile communications (6G) technology. When the BS computing capacity is insufficient or unavailable, UAV-aided 6G mobile edge computing (MEC) is considered a practical solution to maintain the balance between the number of computing tasks and the number of base stations (BS). Firstly, we consider the transmission power setting and design a prioritization mechanism to determine the link selection. Secondly, we construct energy consumption models for user devices (UDs), BS and UAVs separately. Finally, we propose UAV-aided MEC Genetic Algorithm (UMGA) based on genetic algorithm (GA) to minimize the overall energy consumption of the UAV-aided MEC system. Simulation results show that the system energy consumption of our proposed scheme is lower than the system energy consumption of other baseline schemes. Compared with the three baseline algorithms, the performance of our algorithm is improved by 660%, 300% and 41.2%, respectively.

In this paper, we consider an Internet of Things (IoT) system where the employed unmanned aerial vehicle (UAV) carries edge computing server to perform data collection and execution for multiple IoT nodes (INs). For such a network, UAV trajectory and uplink transmission power optimization are integrated to minimize the Age of Information (AoI) of the results returned to all ground INs subject to energy consumption limitations. Due to the non-convex nature of the formulated problem, it is divided into two subproblems, which are respectively solved by Lagrangian dual and convex optimization methods, and block coordinate descent method is applied to solve the overall problem. Simulation results show that the proposed algorithm achieves the lowest average AoI of all INs compared with other schemes. The results also reveal the relationship between the average AoI and the number of INs and advantages of the proposed scheme.

Voice assistants support contactless smart device control and thus act as a holy grail of human–computer interaction. However, recent studies reveal that an adversary can manipulate devices by vicious voice commands. This security risk is caused by only executing one-time liveness detection and lacking safeguard modules after service activation. Therefore, identifying speaker type (i.e., human articulators or loudspeakers) is critical in protecting voice-driven services during an entire interaction session. In this article, we propose a continuous voice liveness detection approach LiveProbe, leveraging unique energy response patterns in frequency bands induced by distinct voice generation mechanisms. The rationality behind LiveProbe is presented in two aspects: human articulator reshapes initial voices by exquisitely coordinated movements of vocal organs, which act as band-pass filters generating unique energy responses; nevertheless, the internal modules of loudspeakers are position fixed and cannot reproduce this response characteristic. To that end, we first work on voice generation mechanisms behind two-type speakers that cause spectrum differences. Then, we elaborately construct signal processing and deep-learning modules to extract liveness features. Especially, our approach does not interfere with normal voice interaction and need not to carry customized sensors. The experiment presents its effectiveness against potential attacks with a false acceptance rate of 0.51%.

Mobile edge computing (MEC) relieves the latency and energy consumption of mobile applications by offloading computation-intensive tasks to nearby edges. In wireless metropolitan area networks (WMANs), edges can better provide computing services via advanced communication technologies. For improving the Quality-of-Service (QoS), edges need to be collaborated rather than working alone. However, the existing solutions of multiedge collaboration solely adopt a centralized or decentralized decision-making way of load balancing, making it hard to achieve the optimal result because the local and global conditions are not jointly considered. To solve this problem, we propose a novel two-stage decision-making method of load balancing for multiedge collaboration (TDB-EC). First, the centralized decision making is executed with global information, where a deep neural networks (DNNs)-based prediction model is designed to evaluate the range of task scheduling between adjacent edges. Next, considering the global condition of load balancing, the decentralized decision making is executed with local information, where a deep$Q$-networks (DQN)-based$Q$-value prediction model of adjustment operations is developed to evaluate the load balancing plan among edges. Finally, the objective load balancing plan is obtained via feedback control. Extensive simulation experiments demonstrate the adaptability of the TDB-EC to various scenarios of multiedge load balancing, which approximates the optimal result and outperforms three classic methods.

Vehicle-to-vehicle (V2V) computation offloading has emerged as a promising solution to facilitate computing-intensive vehicular task processing, where task vehicles (i.e., TaVs) will be requested to offload computing-intensive tasks to server vehicles (i.e., SeVs) in order to keep task delay low. However, it is challenging for TaVs to obtain the optimal V2V computation offloading decisions (i.e., realizing the minimal task delay) due to the constraints, including: 1) incomplete offloading information; 2) degraded Quality-of-Service (QoS) of SeVs; and 3) privacy leakage risks. In this article, we develop a learning-based V2V computation offloading algorithm enhanced by SeV’s ability & trustfulness awareness to solve these problems. We emphasize that the proposed algorithm learns the offloading performance of candidate SeVs based on history offloading selections, without requiring the complete offloading information in advance. Additionally, both the QoS of SeVs and safe V2V computation offloading are enhanced in the proposed learning-based algorithm. Furthermore, we conduct extensive simulation experiments to validate the proposed algorithm. The results demonstrate that the proposed algorithm reduces the average task delay by 35% and 40%, and at the same time decreases the learning regret by 39% and 41%, compared to the algorithms without SeV’s ability and trustfulness awareness.

Nowadays, face recognition technology has been dramatically boosted by the advances in deep learning and big data fields. However, this also poses grand challenges in protecting personal identity information in intelligent applications of the Internet of Things (IoT). Existing methods based on the$K$-Same algorithm have low effectiveness for protecting personal identity while preserving face attributes. In this article, we propose an attribute-preserving face de-identification framework called Enhanced Embedded AutoEncoders to address this problem. Our framework consists of three parts: 1) a privacy removal network (PRN); 2) a feature selection network; and 3) a privacy evaluation network. The main purpose of our framework is to ensure that the PRN is capable of discarding information involving identity privacy and retaining desired face attributes for certain prediction applications. In order to achieve this goal, the design of the PRN is crucial. Specifically, we employ two different autoencoders, one of which is embedded within the other. Extensive experimental results show that our framework outperforms existing methods by an average of 3.42%–26.22% in terms of data utility under comparable face de-identification performance, which indicates that the proposed framework can not only effectively retain face attributes but also protect personal identity well.

Federated learning (FL) has shown its great potential for achieving distributed intelligence in privacy-sensitive IoT. However, popular FL approaches, such as FedAvg and its variants share model parameters among clients during the training process and thus cause significant communication overhead in IoT. Moreover, nonindependent and identically distributed (non-IID) data across learning devices severely affect the convergence and speed of FL. To address these challenges, we propose a communication-efficient FL framework based on Two-step Knowledge Distillation, Fed2KD, which boosts the classification accuracy through privacy-preserving data generation while improving communication efficiency through a new knowledge distillation scheme empowered by an attention mechanism and metric learning. The generalization ability of Fed2KD is analyzed from the view of domain adaption. Extensive simulation experiments are conducted on Fashion-MNIST, CIFAR-10, and ImageNet data sets with various non-IID data distributions. The performance results show that Fed2KD can reduce the communication overhead and improve classification accuracy compared to FedAvg and its latest variants.

In the era of the Internet of Things (IoT), it is a promising way to improve system energy utility and better meet users’ requirements for Quality of Service (QoS) via integrating nonorthogonal multiple access (NOMA) and mobile-edge computing (MEC) technologies. In light of this idea, we investigate device access, subchannel division, and transmission power allocation for NOMA-enabled IoT systems. To maximize the energy utility of IoT systems while satisfying the minimum demands of IoT Devices (IoTDs) on achievable uplink data rate, a joint optimization problem is formulated with the consideration of device access, subchannel division, and transmission power allocation. Due to the nonconvexity of this problem, we propose an alternating optimization algorithm aiming to find the optimal solution. The proposed algorithm first decomposes the joint optimization problem into three subproblems through the block coordinate descent (BCD), and then obtains the near-optimal solution by solving the decomposed subproblems alternately. Extensive simulations validate our analysis for the convergence of the proposed algorithm. The numerical results demonstrate that the proposed algorithm significantly outperforms the benchmark algorithms in terms of improving system energy utility.

Unmanned aerial vehicles (UAVs) are considered as a promising method to provide additional computation capability and wide coverage for mobile users (MUs), especially when MUs are not within the communication range of the infrastructure. In this article, a UAV-aided mobile-edge computing (MEC) network, including one UAV-MEC server, one BS-MEC server, and several MUs, is investigated for computation offloading, in which the edge service provider (ESP) manages two kinds of servers. It is considered that MUs have a large number of computation tasks to conduct, while the ESP has idle computational resources. MUs can choose to offload their tasks to the ESP to reduce their pressure and cost, and the ESP can make a profit by selling computational resources. The interaction among the ESP and MUs is modeled as a Stackelberg game, and both the ESP and MUs want to maximize their utility. The proposed game is analyzed by using the backward induction method, and it is proved that a unique Nash equilibrium can be achieved in the game. Then, a gradient-based dynamic iterative search algorithm (GDISA) is proposed to get the approximate optimal solution. Finally, the effectiveness of GDISA is verified by extensive simulations, and the results show that GDISA performs better than other benchmark methods under different scenarios.

Autonomous driving has so far received numerous attention from academia and industry. However, the inevitable occlusion is a great menace to safety and reliable driving. Existing works have primarily focused on improving the perception ability of a single autonomous vehicle (AV), but the safety problem brought by occlusions remains unanswered. In this paper, we propose a multi-tier perception task offloading framework with a collaborative computing approach, where an AV is able to achieve a comprehensive perception of the concerned region-of-interest (RoI) by leveraging collaborative computation with nearby AVs and road side units (RSUs). Besides, the collaborative computation provides offloading service for computationally intensive tasks so as to reduce processing delay. Specifically, we formulate a joint problem of perception task assignment, offloading and resource allocation, by fully considering the AV’s mobility, task dependency, and delay requirement. The collaborative offloading is modeled as a mixed-integer nonlinear programming (MINLP) problem. We design a two-layer binary intelligent firefly (TL-BIFA) algorithm to solve MINLP, with the goal of minimizing execution delay. The proposed TL-BIFA synthesizes the advantages of heuristic methods and deterministic methods. Through extensive simulations, the proposed collaborative offloading approach and the TL-BIFA show superiority in enhancing the autonomous driving system’s safety, efficiency and resource utilization.

Collaborative mobile edge computing (MEC) is a new paradigm that allows cooperative peer offloading among distributed MEC servers to balance their computing workloads. However, the highly dynamic workloads and wireless network conditions pose great challenges to achieving efficient task offloading in collaborative MEC. To address this challenge, digital twin (DT) has emerged as one promising solution by building a high-fidelity virtual mirror of the physical MEC to simulate its behaviors and help make optimal operational decisions. In this paper, we propose a DT-driven intelligent task offloading framework for collaborative MEC, where DT is employed to map the collaborative MEC system into a virtual space and optimize the task offloading decisions. We model the task offloading process as a Markov decision process (MDP) with the objective of maximizing the MEC system’s total income from providing computing services, and then develop a deep reinforcement learning (DRL)-based intelligent task offloading scheme (INTO) to jointly optimize the peer offloading and resource allocation decisions. An efficient action refinement method is proposed to ensure that the action selected by the DRL agent is feasible. Experimental results show that our proposed approach can effectively adapt the task offloading decisions according to the dynamic environment, and significantly improve the MEC system’s income through extensive comparison with three state-of-the-art algorithms.

In the real world, relationships between objects are often complex, involving multiple variables and modes. Hypergraph neural networks possess the capability to capture and represent such intricate relationships by deriving and inheriting their graph-based counterparts. Nevertheless, both graph and hypergraph neural networks suffer from the problem of over-smoothing when multiple graph convolution layers are stacked. To address this issue, this article introduces the Multi-modal Hypergraph Neural Network with Parametric Filtering and Feature Sampling (MHNet) to encode complex hypergraph features and mitigate over-smoothing. The proposed approach uses hypergraph structures to model high-order and multi-modal data correlations, a polynomial hypergraph filter to dynamically extract multi-scale node features through parametric polynomial fitting, and a feature sampling strategy to learn from sparse and labeled samples while avoiding overfitting. Experimental results on four hypergraph datasets and two multi-modal visual datasets demonstrate that the proposed MHNet outperforms state-of-the-art algorithms.

Mobile CrowdSensing (MCS) is an emerging paradigm that employs massive mobile devices (MDs) to complete sensing tasks cooperatively. To provide ubiquitous MCS services, Unmanned Aerial Vehicle (UAV), featured by high agility and flexibility, becomes increasingly attractive as a powerful assistant for MCS to collect sensing data in hard-to-reach and infrastructure-restrained areas. Focusing on urban MCS scenarios where a tremendous amount of data needs to be uploaded by massive mobile devices, we propose a Three-Dimensional Multi-UAV assisted crowdsensing, termed 3DM, to collect sensing data efficiently in an infrastructure-free manner. Different from the existing methods, 3DM has two unique advantages: 1) removing the assumption of the ideal distributions of mobile devices and 2) fully exploiting the 3D flexibility to optimize the device matching and data transmission between UAVs and MDs. By employing a joint optimization metric that incorporates both energy efficiency and collection latency, 3DM dynamically maintains cost-effective UAV-MD links and 3D UAVs trajectories thus completes the collection tasks with less time and energy. Compared with the baseline algorithm and two state-of-the-art counterparts, extensive simulations demonstrate that 3DM saves at least 50% energy and 25% time of baseline while achieving 76% improvement of the sub-optimal competitor on overall utility.

Federated Learning (FL) has emerged as a privacy-preserving distributed Machine Learning paradigm, which collaboratively trains a shared global model across a number of end devices (clients) without exposing their raw data. However, FL typically assumes that all clients are benign and trust the coordinating central server, which is unrealistic for many real-world scenarios. In practice, clients can harm the FL process by sharing poisonous model updates while the server could malfunction or misbehave. Moreover, the deployment of FL for real-world applications is hindered by the high communication overhead between the server and clients that are often at the network edge with limited bandwidth. To address these key challenges, we propose a lightweight Blockchain-Empowered secure and efficient Federated Learning (BEFL) system. BEFL is built by integrating a communication-efficient and mutual-information guarded training scheme, a cost-effective Verifiable Random Function (VRF)-based consensus mechanism, and Inter-Planetary File System (IPFS)-enabled scalable blockchain architecture. Extensive simulation experiments using two benchmark FL datasets demonstrate that BEFL is resistant against byzantine clients launching data poisoning and model poisoning attacks, fault-tolerant against colluded malicious blockchain nodes, scalable to a large number of blockchain nodes, and communication-efficient at the network edge.

Increasing workload conditions lead to a significant surge in power consumption and computing node failures in data centers. The existing workload distribution strategies focused on either thermal awareness or failure mitigation, overlooking the impact of node failures on the energy efficiency of cloud data centers. To address this issue, a new holistic model is built to characterize the impacts of workloads, computing and cooling costs, heat recirculation, and node failure on the energy efficiency of cloud data centers. Leveraging such a holistic model, we propose a novel thermal-aware workload distribution strategy calledHGSAthat takes node failure into accountand can improve the energy efficiency of cloud data centers. Our empirical findings confirm that (i) faulty nodes lead to a large rise in power consumption, and (ii) failure locations play a vital role in the power consumption of data centers. Experimental results unveil that HGSA is adroit at making near-optimal decisions in workload distribution strategies. In particular, HGSA cuts down the minimum inlet temperature by 5.2$\%$-15$\%$, improves the maximum air temperature of a Computer Room Air Conditioner (CRAC) model by 4.2$\%$-26.5$\%$, lowers the cooling cost by 15.4$\%$-50$\%$compared to the existing solutions. Furthermore, HGSA cuts back the total power consumption by 0.65$\%$-78$\%$.

Internet-of-Things (IoT) are increasingly operating in the zero-trust environments where any devices and systems may be compromised and hence untrusted. In addition, data collected by and sent from IoT devices may be shared with and processed by edge computing systems, in order to reduce the reliance on centralized (cloud) servers, leading to further security and privacy issues. To cope with these challenges, this paper proposes an innovative blockchain-enabled information sharing solution in zero-trust context to guarantee anonymity yet entity authentication, data privacy yet data trustworthiness, and participant stimulation yet fairness. This new solution is able to support filtering of fabricated information through smart contracts, effective voting, and consensus mechanisms, which can prevent unauthenticated participants from sharing garbage information. We also prove that the proposed solution is secure in the universal composability framework, and further evaluate its performance over an Ethereum-based blockchain platform to demonstrate its utility.

Federated Learning (FL) is a recent development in distributed machine learning that collaboratively trains models without training data leaving client devices, preserving data privacy. In real-world FL, the training set is distributed over clients in a highly non-Independent and Identically Distributed (non-IID) fashion, harming model convergence speed and final performance. To address this challenge, we propose a novel, generalised approach for incorporating adaptive optimisation into FL with the Federated Global Biased Optimiser (FedGBO) algorithm. FedGBO accelerates FL by employing a set of global biased optimiser values during training, reducing ‘client-drift’ from non-IID data whilst benefiting from adaptive optimisation. We show that in FedGBO, updates to the global model can be reformulated as centralised training using biased gradients and optimiser updates, and apply this framework to prove FedGBO's convergence on nonconvex objectives when using the momentum-SGD (SGDm) optimiser. We also conduct extensive experiments using 4 FL benchmark datasets (CIFAR100, Sent140, FEMNIST, Shakespeare) and 3 popular optimisers (SGDm, RMSProp, Adam) to compare FedGBO against six state-of-the-art FL algorithms. The results demonstrate that FedGBO displays superior or competitive performance across the datasets whilst having low data-upload and computational costs, and provide practical insights into the trade-offs associated with different adaptive-FL algorithms and optimisers.

As the workloads and service requests in cloud computing environments change constantly, cloud-based software services need to adaptively allocate resources for ensuring the Quality-of-Service (QoS) while reducing resource costs. However, it is very challenging to achieve adaptive resource allocation for cloud-based software services with complex and variable system states. Most of the existing methods only consider the current condition of workloads, and thus cannot well adapt to real-world cloud environments subject to fluctuating workloads. To address this challenge, we propose a novel Deep Reinforcement learning based resource Allocation method with workload-time Windows (DRAW) for cloud-based software services that considers both the current and future workloads in the resource allocation process. Specifically, an original Deep Q-Network (DQN) based prediction model of management operations is trained based on workload-time windows, which can be used to predict appropriate management operations under different system states. Next, a new feedback-control mechanism is designed to construct the objective resource allocation plan under the current system state through iterative execution of management operations. Extensive simulation results demonstrate that the prediction accuracy of management operations generated by the proposed DRAW method can reach 90.69%. Moreover, the DRAW can achieve the optimal/near-optimal performance and outperform other classic methods by 3$\sim$13% under different scenarios.

Cloud storage services can support data sharing for a group of users. However, the cloud server may lose some of the shared data when attacked. The integrity of stored data is a key issue for cloud storage. However, identity anonymity, an important problem in data integrity, has not been fully investigated yet. Furthermore, the existing schemes of data integrity checking are usually based on public key infrastructure and thus have to perform complex certificate management. In this paper, we propose an efficient integrity checking scheme to achieve full identity anonymity. Additionally, the proposed scheme can reduce the workloads of certificate management and simplify key management. Inspired by the idea of attribute-based signature, we devise a common predicate to manage the identities of legitimate users and disable illegal users from joining the data sharing. By adopting the technique of the monotone span program, the legitimate user can compute the valid authenticators of shared data for all attributes in the common predicate without the need of binding his attribute set to the shared data. Whereupon, the user's identity remains anonymous to all parties in the data sharing because he can share the data and authenticators without revealing his attribute set to other parties. The extensive experimental results demonstrate that the proposed scheme has less computational and communication overhead compared with the existing schemes while achieving full identity anonymity.

Task offloading has been widely used to extend the battery life of intelligent mobile devices. Existing task offloading approaches, focusing on perfecting the balance between latency and energy consumption, completely ignore the impacts of the user preference caused by low battery anxiety. The existence of low battery anxiety - mobile users’ common fear of losing battery energy, especially when the battery energy is already low - causes users to trade high latency for prolonged battery life. Taking into account the user preference impacts on task offloading, we propose a novel offloading approach calledUPOAto obtain refined offloading policies between low latency and energy consumption based on user preferences. In UPOA, we start the study by defining a user preference rule that determines users’ offloading preferences according to battery energy status. Then, we build a fine-grained task offloading model to delineate the task distribution characteristics of each node in its offloading link. Guided by this model, we develop a task prediction algorithm based on the long-short-term-memory neural network model to provide task predictions that facilitate offloading policies. Lastly, we implement a particle-swarm-optimization-based online offloading algorithm. The offloading algorithm provides the best long-term offloading policies by incorporating the user preference determined by our user preference rule and the task predictions generated by our task prediction algorithm. To quantitatively evaluate the performance of UPOA, we conduct extensive experiments in a real-world cloud-edge environment. We compare UPOA with three state-of-the-art offloading approaches, DRA, DRL-E2D, and MUDRL under various conditions. Experimental results demonstrate that UPOA can make effective policies based on user preferences compared with the existing approaches. UPOA reduces average latency by 12.49% when battery energy is sufficient and extends battery life by 20.14% when battery energy is low.

Data deduplication has been broadly used in Cloud due to its storage space saving ability. An issue of deduplication is the contiguous data chunks in a segment may be scattered in different containers. This phenomenon is called data fragmentation. Because of data fragmentation, a restore process must reference various containers across a wide variety of segments, thereby hurting the restore performance. Capping methods that rewrite the data chunks of low Container Reference Ratio (CRR) containers are developed to alleviate data fragmentation. We analyze and observe from real traces that a number of segments only point to lowCRRcontainers, while some others only contain highCRRcontainers. This interesting observation is ignored by the existing capping methods which sort containers from a single segment, falling short in searching multiple segments collectively. Thus, the reference count of selected containers in the existing capping methods is still high. To address this problem, we propose a multi-segment greedy rewriting method named MGRM. MGRM sorts containers of segments in a sequential way. More specifically, given thei-thsegment currently being processed, MGRM will sort all the containers in the topi-thsegments. This salient searching feature enables MGRM to select and rewrite the true low-reference container set. Moreover, to achieve a good balance between deduplication ratio and restore performance, MGRM has two working modes: an optimal rewriting mode and a radical rewriting mode. When working in the optimal rewriting mode, MGRM aims to improve the deduplication ratio; when the radical rewriting mode, MGRM strives to improve the restore performance. MGRM adaptively switches the working mode according to workload. Furthermore, unlike the existing capping methods that improve restore performance at the cost of the deduplication ratio, MGRM pays attention to both aspects. Our extensive experimental results show that MGRM achieves high restore performance, coupled with a high deduplication ratio. In particular, compared with the two state-of-art schemes FC and FLC, MGRM improves the deduplication ratio and restore performance by up to 114.83% and 99.34%, respectively.

Spectrum sensing is a key technique for dynamically detecting available spectrum in cognitive radio networks (CRNs), which can introduce high resource demands such as energy consumption. In this paper, we propose a novel cluster-based cooperative sensing-after-prediction scheme where a learning cluster and a sensing cluster are jointly considered to perform cooperative prediction and sensing efficiently. This enables us to skip the complex physical sensing to reduce the demands when the spectrum availability can be simply predicted using cooperative prediction. Furthermore, the clustering is flexible, in order to meet different performance requirements. We then formulate two optimization problems to minimize the total number of users in the two clusters or to minimize the total energy consumption, to meet different performance requirements, while in both cases guaranteeing the system accuracy requirement and individual energy constraints. To solve the two challenging integer programming problems, the unconstrained problems are mathematically solved first by relaxing the integer variable and fixing the cluster size. Such analytical solutions serve as a foundation for solving the original optimization problems. Then, two low-complexity search algorithms are proposed to achieve the global optimum, as they can obtain the same performance with exhaustive search. Simulation results validate the accuracy of the derived analytical expressions and demonstrate that the total energy consumption and the number of users contributing to learning and sensing can be greatly reduced by applying our optimized clustered sensing-after-prediction scheme.

In enterprise management systems (EMS), augmented Intelligence of Things (AIoT) devices generate delay-sensitive and energy-intensive tasks for learning analytics, articulate clarifications, and immersive experiences. To guarantee effective task processing, in this work, we present a cloud-assisted fog computing framework with task offloading and service caching. In the framework, tasks make offloading decisions to determine local processing, fog processing, and cloud processing with the goal of minimal task delay and energy consumption, conditioned on dynamic service caching. To this end, we first propose a distributed task offloading algorithm based on noncooperative game theory. Then, we adopt the 0–1 knapsack method to realize dynamic service caching. At last, we adjust the offloading decisions for the tasks offloaded to the fog server but without caching service support. In addition, we conduct extensive experiments and the results validate the effectiveness of our proposed algorithms.

During the past decade, Industry 4.0 has greatly promoted the improvement of industrial productivity by introducing advanced communication and network technologies in the manufacturing process. With the continuous emergence of new communication technologies and networking facilities, especially the rapid evolution of cellular networks for 5G and beyond, the requirements for smarter, more reliable, and more efficient cellular network services have been raised from the Industry 5.0 blueprint. To meet these increasingly challenging requirements, proactive and effective allocation of cellular network resources becomes essential. As an integral part of the cellular network resource management system, cellular traffic prediction faces severe challenges with stringent requirements for accuracy and reliability. One of the most critical problems is how to improve the prediction performance by jointly exploring the spatial and temporal information within the cellular traffic data. A promising solution to this problem is provided by graph neural networks (GNNs), which can jointly leverage the cellular traffic in the temporal domain and the physical or logical topology of cellular networks in the spatial domain to make accurate predictions. In this article, we present the spatial-temporal analysis of a real-world cellular network traffic dataset and review the state-of-the-art research works in this field. Based on this, we further propose a time-series similarity-based graph attention network, TSGAN, for the spatial-temporal cellular traffic prediction. The simulation results show that our proposed TSGAN outperforms three classic prediction models based on GNNs or GRU on a real-world cellular network dataset in short-term, mid-term, and long-term prediction scenarios.

Considering that low-cost and resource-cons- trained sensors coupled inherently could be vulnerable to growing numbers of intrusion threats, industrial Internet-of-Things (IIoT) systems are faced with severe security concerns. Data sharing for building high-performance intrusion detection models is also prohibited due to the sensitivity, privacy, and high value of IIoT data. This article presents an anomaly-based intrusion detection system with federated learning for privacy-preserving machine learning in future IIoT networks. To tackle the urgent issue of training local models with non-independent and identically distributed (non-IID) data, we adopt instance-based transfer learning at local. Furthermore, to boost the performance of this system for IIoT intrusion detection, we propose a rank aggregation algorithm with a weighted voting approach. The proposed system achieves superior detection performance with 95.97% and 73.70% accuracy for AdaBoost and Random Forest, respectively, outperforming the baseline models by 12.72% and 14.8%.

Greedy routing efficiently achieves routing solutions for vehicular networks due to its simplicity and reliability. However, the existing greedy routing algorithms have mainly considered simple routing metrics only, e.g., distance based on the local view of an individual vehicle. This consideration is insufficient for analysing dynamic and complicated vehicular communication scenarios which inevitably degrades the overall routing performance. Software-Defined Vehicular Network (SDVN) and Graph Convolutional Network (GCN) can overcome these limitations. Thus, this paper presents a novel GCN-based greedy routing algorithm (NGGRA) in the hybrid SDVN. The SDVN control plane trains the GCN decision model based on the globally collected data. Vehicles with transmission requirements can adopt this model for inferring and making the routing decisions. The proposed node-importance-based graph convolutional network (NiGCN) model analyses multiple correlated metrics to accurately evaluate the dynamic vehicular network is available at:https://github.com/a824899245/NiGCN. Meanwhile, the SDVN architecture offers a global view for model training and routing computation. Extensive simulation results demonstrate that NiGCN outperforms popular GCN models in training efficiency and accuracy. In addition, NGGRA can improve the packet delivery ratio and substantially reduce delay compared with its counterparts.

Collaborative machine learning, especially Federated Learning (FL), is widely used to build high-quality Machine Learning (ML) models in the Internet of Vehicles (IoV). In this paper, we study the performance evaluation problem in an inherently heterogeneous IoV, where the final models across the network are not identical and are computed on different standards. Previous studies assume that local agents are receiving data from the same phenomenon, and a same final model is fitted to them. However, this “one model fits all” approach leads to a biased performance evaluation of individual agents. We propose a general approach to measure the performance of individual agents, where the common knowledge and correlation between different agents are explored. Experimental results indicate that our evaluation scheme is efficient in these settings.

The quantitative performance analysis plays a critical role in assessing the capability of vehicular edge computing (VEC) systems to meet the requirements of vehicular applications. However, developing accurate analytical models for VEC systems is extremely challenging due to the unique features of intelligent vehicular applications. Specifically, recent work revealed that the tasks generated by intelligent vehicular applications exhibit a high degree of burstiness, rendering the existing models that were designed based on the assumption of the non-bursty Poisson process unsuitable for VEC systems. To fill this gap, we developed an original analytical model to investigate the performance of VEC systems with bursty task arrivals. To facilitate vehicle cooperation, a new priority-based resource allocation scheme is exploited to schedule the tasks of vehicular applications, which are modelled by a Markov Modulated Poisson Process (MMPP). Next, a multi-state Markov chain is established to investigate the impact of load sharing strategy on the performance of VEC systems. Then, the end-to-end transmission latency is derived based on the proposed model. Comprehensive experiments are conducted to validate the accuracy of this analytical model under various system configurations. Furthermore, the developed model is used as a cost-effective tool to investigate the performance bottleneck of VEC systems.

Multi-access Edge Computing (MEC) is an emerging computing paradigm that extends cloud computing to the network edge to support resource-intensive applications on mobile devices. As a crucial problem in MEC, service migration needs to decide how to migrate user services for maintaining the Quality-of-Service when users roam between MEC servers with limited coverage and capacity. However, finding an optimal migration policy is intractable due to the dynamic MEC environment and user mobility. Many existing studies make centralized migration decisions based on complete system-level information, which is time-consuming and also lacks desirable scalability. To address these challenges, we propose a novel learning-driven method, which is user-centric and can make effective online migration decisions by utilizing incomplete system-level information. Specifically, the service migration problem is modeled as a Partially Observable Markov Decision Process (POMDP). To solve the POMDP, we design a new encoder network that combines a Long Short-Term Memory (LSTM) and an embedding matrix for effective extraction of hidden information, and further propose a tailored off-policy actor-critic algorithm for efficient training. The extensive experimental results based on real-world mobility traces demonstrate that this new method consistently outperforms both the heuristic and state-of-the-art learning-driven algorithms and can achieve near-optimal results on various MEC scenarios.

In device to device (D2D) aided mobile edge computing (MEC) networks, by implementing content caching and D2D links, the edge server and nearby mobile devices can provide task offloading platforms. For parallel tasks, proper decisions on content caching and task offloading help reduce delay and energy consumption. However, what is often ignored in the previous works is the joint optimization of parallel task offloading and content caching. In this paper, we aim to find optimal content caching and parallel task offloading strategies, so as to minimize task delay and energy consumption. The minimization problem is formulated as a multi-objective optimization problem, concerning both content caching and parallel task offloading. The content caching is formulated as an integer knapsack problem (IKP). To solve the IKP problem, an enhanced Binary Particle Swarm Optimization algorithm is proposed. The parallel task offloading problem is formulated as a constrained multi-objective optimization problem, an improved multi-objective bat algorithm is proposed to address the problem. Experimental results show that our algorithm can decrease delay and energy cost by at most 45% and 56%, respectively. In addition, the parallel task offloading ratio remains over 91% even with large number of mobile devices (MDs).

LoRa has become one of the most promising networking technologies for Internet-of-Things applications. Distant end devices have to use a low data rate to reach a LoRa gateway, causing long in-the-air transmission time and high energy consumption. Compared with the end devices using high data rates, they will drain the batteries much earlier and the network may be broken early. Such an energy unfairness can be mitigated by deploying more gateways. However, with more gateways, more end devices may choose small spreading factors to reach closer gateways, increasing the collision probability. In this paper, we propose a networking solution for LoRa networks, EF-LoRa, that can achieve energy fairness among end devices by carefully allocating network resources, including frequency channels, spreading factors and transmission power. We develop a LoRa network model to study the energy consumption of the end devices, considering the unique features of LoRa networks such as LoRaWAN MAC protocol and the capacity limitation of a gateway. We formulate the energy fairness allocation as an optimization problem, and propose a greedy allocation algorithm to achieve max-min fairness of energy efficiency. Simulation results show that EF-LoRa can improve the energy fairness of the state-of-the-art works by 177.8%.

With the mushrooming growth of data volumes, data replica placement plays a key role in promoting the energy efficiency and Quality-of-Service (QoS) of data-intensive data centers. The existing data placement strategies mainly focus on storage performance improvement or QoS enhancement in data centers, but ignore the indispensable factor - heat recirculation. To bridge this gap, we propose a thermal-aware data replica placement strategy called TADRP, aiming to improve cooling efficiency and minimize the total power consumption of data-intensive data centers. TADRP leverages an ant colony optimization (ACO) algorithm coupled with Laplacian probability distribution to find a quasi-optimal disk sequence (or Disk Sequence for short), which consists of disks selected from different rack servers to place data replicas. TADRP categorizes disks of Disk Sequence into active and inactive ones, by placing hot and cold replicas on active and inactive disks, respectively. We quantitatively evaluate TADRP in terms of cooling costs, total power consumption, number of power-state transitions, and execution time. We compare TADRP with four alternative solutions, namely, Random, Hadoop, SRS, and CDP-NSGAII. Experimental results show that TADRP can reduce the cooling costs and the total power of the existing solutions by 14.7% - 61.7% and 19.2%-55.1%, respectively, without undesirable I/O performance drops.

With the explosive increase in mobile data traffic and stringent quality-of-experience requirements of users, mobile edge caching is a promising paradigm to reduce delivery latency and network congestions by serving content requests locally. However, it is extremely challenging to conduct cache replacement when the cache is full and the future request pattern is unknown subject to enormous content volume but limited cache capacity at the network edge. In this paper, we propose a cache replacement algorithm based on the oracle approximation named OA-Cache in an end-to-end manner to maximize the cache hit rate. Specifically, we construct a complex model that uses a temporal convolutional network to capture the long and short dependencies between content requests. Then, an attention mechanism is adopted to find out the correlations between the requests in the sliding window and cached contents. Instead of training a policy to mimic Belady that evicts the content with the longest reuse distance, we cast the learning task into a classification model to distinguish unpopular contents from popular ones. Finally, we apply the knowledge distillation approach to assist in transferring knowledge from a large pre-trained complex network to a lightweight network to readily accommodate to the network edge scenario. To validate the effectiveness of OA-Cache, we conduct extensive experiments on real-world datasets. The evaluation results demonstrate that OA-Cache can achieve the superior performance compared to candidate algorithms.

Resource provisioning for the ever-increasing applications to host the necessary network functions necessitates the efficient and accurate prediction of required resources. However, the current efforts fail to leverage the inherent features hidden in network traffic, such as temporal stability, service correlation and periodicity, to predict the required resources in an intelligent manner, incurring coarse-grain prediction accuracies. To tackle this problem, in this paper, we propose an Accurate Prediction of Required virtual Resources (APRR) approach via Deep Reinforcement Learning (DRL). We first confirm the resource requests have more similar features and identify the high-dimensional required resources in computing, storage and bandwidth can be effectively consolidated into a single standardized value. Built upon these observations, we then model the required resources as a time-variant network matrix, which includes a number of elements, obtained from the network measurements, and some missing elements needed to be inferred. To obtain accurately predicted results, DRL-based matrix factorization with a set of available rules has been introduced into APRR and alternately executed in agent to minimize the prediction errors. Moreover, the error-prioritized designed for model training with quicker convergence. Simulation experiments on real-world datasets illustrate that APRR can accurately predict the required virtual resources compared with the related approaches.

In Federated Learning (FL) client devices connected over the internet collaboratively train a machine learning model without sharing their private data with a central server or with other clients. The seminal Federated Averaging (FedAvg) algorithm trains a single global model by performing rounds of local training on clients followed by model averaging. FedAvg can improve the communication-efficiency of training by performing more steps of Stochastic Gradient Descent (SGD) on clients in each round. However, client data in real-world FL is highly heterogeneous, which has been extensively shown to slow model convergence and harm final performance when$K > 1$steps of SGD are performed on clients per round. In this article we propose decaying$K$as training progresses, which can jointly improve the final performance of the FL model whilst reducing the wall-clock time and the total computational cost of training compared to using a fixed$K$. We analyse the convergence of FedAvg with decaying$K$for strongly-convex objectives, providing novel insights into the convergence properties, and derive three theoretically-motivated decay schedules for$K$. We then perform thorough experiments on four benchmark FL datasets (FEMNIST, CIFAR100, Sentiment140, Shakespeare) to show the real-world benefit of our approaches in terms of real-world convergence time, computational cost, and generalisation performance.

Federated learning (FL) is a privacy-preserving distributed machine learning paradigm that enables collaborative training among geographically distributed and heterogeneous devices without gathering their data. Extending FL beyond the supervised learning models, federated reinforcement learning (FRL) was proposed to handle sequential decision-making problems in edge computing systems. However, the existing FRL algorithms directly combine model-free RL with FL, thus often leading to high sample complexity and lacking theoretical guarantees. To address the challenges, we propose a novel FRL algorithm that effectively incorporates model-based RL and ensemble knowledge distillation into FL for the first time. Specifically, we utilise FL and knowledge distillation to create an ensemble of dynamics models for clients, and then train the policy by solely using the ensemble model without interacting with the environment. Furthermore, we theoretically prove that the monotonic improvement of the proposed algorithm is guaranteed. The extensive experimental results demonstrate that our algorithm obtains much higher sample efficiency compared to classic model-free FRL algorithms in the challenging continuous control benchmark environments under edge computing settings. The results also highlight the significant impact of heterogeneous client data and local model update steps on the performance of FRL, validating the insights obtained from our theoretical analysis.

With the rapid development of Internet-of-Things (IoT) and the explosive advance of deep learning, there is an urgent need to enable deep learning inference on IoT devices in Mobile Edge Computing (MEC). To address the computation limitation of IoT devices in processing complex Deep Neural Networks (DNNs), computation offloading is proposed as a promising approach. Recently, partial computation offloading is developed to dynamically adjust task assignment strategy in different channel conditions for better performance. In this paper, we take advantage of intrinsic DNN computation characteristics and propose a novel Fused-Layer-based (FL-based) DNN model parallelism method to accelerate inference. The key idea is that a DNN layer can be converted to several smaller layers in order to increase partial computation offloading flexibility, and thus further create the better computation offloading solution. However, there is a trade-off between computation offloading flexibility as well as model parallelism overhead. Then, we investigate the optimal DNN model parallelism and the corresponding scheduling and offloading strategies in partial computation offloading. In particular, we propose a Particle Swarm Optimization with Minimizing Waiting (PSOMW) method, which explores and updates the FL strategy, path scheduling strategy, and path offloading strategy to reduce time complexity and avoid invalid solutions. Finally, we validate the effectiveness of the proposed method in commonly used DNNs. The results show that the proposed method can reduce the DNN inference time by an average of 12.75 times compared to the legacy No FL (NFL) algorithm, and is very close to the optimal solution achieved by the Brute Force (BF) algorithm with the difference of less than 0.04%.

We consider the problem of dependent task offloading in edge computing with unknown system-side information (e.g., edge transmission rate and computation resources). In this problem, tasks have complicated dependency relationships and have no prior knowledge of system-side information to assist offloading decision-making. Although existing learning-based approaches can help to address unknown system-side information, the impact of inherent task dependency on such approaches has not been formally explored. To bridge the gap, we first use a breadth-first-search (BFS) method to decouple task dependency, and then leverage the Lyapunov optimization technique to transfer the long-term offloading problem to an online optimization problem. Furthermore, we employ the multi-armed bandit (MAB) theory to develop theonlinelearning-baseddependenttaskoffloading algorithm, called OL-DTO. The algorithm can address the unknown system-side information and is augmented with task dependency awareness. We present a rigorous theoretical analysis to evaluate the performance of this algorithm in terms of application delay and UD energy consumption. Our extensive experimental results demonstrate that the OL-DTO algorithm significantly reduces application delay while satisfying the long-term energy budget constraint of the UD.

Network Functions Virtualization (NFV), which decouples network functions from the underlying hardware, has been regarded as an emerging paradigm to provide flexible virtual resources for various applications through the ordered interconnection of Virtual Network Functions (VNFs), in the form of Service Function Chains (SFCs). In order to achieve the desired performance as dedicated hardware, how to efficiently deploy SFCs in NFV-enabled networks with limited resources is still a tremendous challenge. In this article, RQAP, an effective Resource and Quality of Service (QoS) Aware SFC Placement approach is proposed to mitigate this issue with the QoS-guaranteed service provisioning at acceptable resource consumption. With the Markov property of VNFs, the resource and QoS aware placement of SFCs is modeled as a Markov-chain-based optimization problem, where the set of all possible placement states on diverse nodes is regarded as a state space in the Markov chain and each state is jointly determined by the initial state and transition matrices. Furthermore, the SFCs associated with traffic requests are re-sorted so as to efficiently instantiate VNFs of the same type in a resource-saving manner. On this basis, an efficient Backward-Viterbi-based heuristic mechanism is presented to conduct the optimal VNF placement in Markov chain space, with the aim of consumed-resource reduction, along with the QoS-based instantiation of virtual links between adjacent VNFs. Simulation results conducted in several scenarios demonstrate that RQAP can significantly achieve a trade-off between resource consumption optimization and QoS guarantee. Besides, the results show that our proposed approach can also effectively improve the SFC acceptance ratio and achieve desirable load balancing and scalability.

With the advent of 5G, Mobile Edge Computing (MEC), a promising computing paradigm sits closer to users than cloud computing, is being broadly used in various Internet of Things (IoT) applications, and achieve high-quality user experience. Task offloading, as a critical research issue in MEC, is playing an important role in optimizing computational resources and management. However, many tasks are executed dependent on the computational results of other tasks. Moreover, in the case of offloading tasks with other devices, it is often required to consider the success rate of offloading, since not all users are willing to lend their mobile devices to others for task execution. To address this challenge, by taking social relationships between users into account, this paper intends to combine computational resources of local devices and edge clouds and provide more flexible offloading and execution solutions, for achieving the efficient offloading of dependent tasks with the joint consideration of network latency and energy consumption. This paper develops a dependent task offloading strategy based on Bipartite Graph Matching. Extensive simulations are conducted for validating the effectiveness of our proposed strategy. Experimental results demonstrate that our proposed strategy can significantly minimize the overhead compared with other baseline strategies. In particular, the overhead is reduced 8.2%, compared with the strategy which consider the Device-to-Device (D2D) offloading only.

IoT devices have been widely utilized to detect state transition in the surrounding environment and transmit status updates to the base station for system operations. To guarantee the accuracy of system control, age of information (AoI) is introduced to quantify the freshness of the sensory data and meet the stringent timeliness requirement. Due to the limited computing resources, the status update can be offloaded to the mobile edge computing (MEC) server for execution. Since status updates generated by insufficient sensing operations may be invalid and lead to additional processing time, a joint data sensing and processing optimization problem needs to be considered. Therefore, this work formulates an NP-hard problem that considers the freshness of the status updates and energy consumption of the IoT devices. Subsequently, the problem is decomposed into sampling, sensing, and computation offloading optimization problems. To optimize the system overhead, a multi-variable iterative system cost minimization algorithm is proposed. Simulation results illustrate the efficacy of our method in decreasing the system cost, and indicate the influence of sensing and processing under different scenarios.

Edge caching is a promising approach to reduce duplicate content transmission in Internet-of-Vehicles (IoVs). Several Reinforcement Learning (RL) based edge caching methods have been proposed to improve the resource utilization and reduce the backhaul traffic load. However, they only obtain the local sub-optimal solution, as they neglect the influence from environments by other agents. This paper investigates the edge caching strategies with consideration of the content delivery and cache replacement by exploiting the distributed Multi-Agent Reinforcement Learning (MARL). A hierarchical edge caching architecture for IoVs is proposed and the corresponding problem is formulated with the goal to minimize the long-term content access cost in the system. Then, we extend the Markov Decision Process (MDP) in the single agent RL to the context of a multi-agent system, and tackle the corresponding combinatorial multi-armed bandit problem based on the framework of a stochastic game. Specifically, we firstly propose a Distributed MARL-based Edge caching method (DMRE), where each agent can adaptively learn its best behaviour in conjunction with other agents for intelligent caching. Meanwhile, we attempt to reduce the computation complexity of DMRE by parameter approximation, which legitimately simplifies the training targets. However, DMRE is enabled to represent and update the parameter by creating a lookup table, essentially a tabular-based method, which generally performs inefficiently in large-scale scenarios. To circumvent the issue and make more expressive parametric models, we incorporate the technical advantage of the Deep-$Q$Network into DMRE, and further develop a computationally efficient method (DeepDMRE) with neural network-based Nash equilibria approximation. Extensive simulations are conducted to verify the effectiveness of the proposed methods. Especially, DeepDMRE outperforms DMRE,$Q$-learning, LFU, and LRU, and the edge hit rate is improved by roughly 5%, 19%, 40%, and 35%, respectively, when the cache capacity reaches 1, 000 MB.

Vehicular Edge Computing (VEC) is a computing paradigm that brings Mobile Edge Computing (MEC) to the road and vehicular scenarios by providing low-latency and high-efficiency computation services. One key technology of VEC is task offloading, which allows vehicles to send computation tasks to surrounding Roadside Units (RSUs) for execution, thereby reducing service delay. However, the existing task offloading schemes face the important challenges because the vehicles with time-varying trajectories and limited computing resources need to process massive data with high complexity and diversity. In this paper, we propose a Cooperative Task Qffloading Scheme (CTOS) based on Cybertwin-assisted VEC. Specially, a novel Cybertwin-assisted VEC network architecture is established by applying the combination of the Digital-Twins (DT) and the Generative Adversarial Network (GAN). With the powerful prediction capability of GAN, the data of DT is advanced with the physical entity, which is an effective assistant for task offloading. Then, we leverage the distributed Deep Reinforcement Learning (DRL) to make offloading decisions, which consider the limited resources of RSUs and the cooperation of vehicles. The simulation results demonstrate that the proposed scheme can achieve excellent performance in terms of system stability and efficiency.

Federated learning (FL) is a type of distributed machine learning in which mobile users can train data locally and send the results to the FL server to update the global model. However, the implementation of FL may be prevented by the self-fish nature of mobile users, as they need to contribute considerable data and computing resources for participating in the FL process. Therefore, it is of importance to design the incentive mechanism to motivate the users to join the FL. In this work, with explicit consideration of the impact of wireless transmission, we design an incentive scheme to facilitate the FL process by investigating interactions between the multi-access edge computing (MEC) server and mobile users in a MEC-based FL system. By using a two-stage Stackelberg game model, we explore the transmission power allocation of the users and reward policy of the MEC server, and then analyze the Stackelberg equilibrium. The simulation results show that our model is effective for different parameter settings and the utility of the MEC server can be increased significantly compared to the baseline.

The eye-blink pattern is crucial for drowsy driving diagnostics, which has become an increasingly serious social issue. However, traditional methods (e.g., with EOG, camera, wearable, and acoustic sensors) are less applicable to real-life scenarios due to the disharmony between user-friendliness, monitoring accuracy, and privacy-preserving. In this work, we design and implement BlinkRadar as a low-cost and contact-free system to conduct fine-grained eye-blink monitoring in a driving situation using a customized impulse-radio ultra-wideband (IR-UWB) radar which has superior spatial resolution with the ultra-wide bandwidth. BlinkRadar leverages an IR-UWB radar to achieve contact-free sensing, and it fully exploits the complex radar signal for data augmentation. BlinkRadar aims to single out the eye-blink induced waveforms modulated by body movements and vehicle status. It solves the serious interference caused by the unique characteristics of blinking (i.e., subtle, sparse, and non-periodic) and from the human target itself and surrounding objects. We evaluate BlinkRadar in a laboratory environment and during actual road testing. Experimental results show that BlinkRadar can achieve a robust performance of drowsy driving with a median detection accuracy of 92.2% and eye blink detection of 95.5%.

The combination of 5G and edge computing has been envisioned as a promising paradigm to empower pervasive and intensive computing for the Internet-of-Things (IoT). High deployment cost is one of the major obstacles for realizing 5G edge computing. Most existing works tried to deploy the minimum number of edge servers to cover a target area by avoiding coverage overlaps. However, following this framework, the resource requirement per server will be drastically increased by the peak requirement during workload variations. Even worse, most resources will be left under-utilized for most of the time. To address this problem, we propose CoopEdge, a cost-effective server deployment scheme for cooperative multi-access edge computing. The key idea of CoopEdge is to allow deploying overlapped servers to handle variable requested workloads in a cooperative manner. In this way, the peak demands can be dispersed into multiple servers, and the resource requirement for each server could be greatly reduced. We further propose a two-step incremental algorithm, which jointly decides the server deployment and cooperation policies for fast convergence. We evaluate CoopEdge based on seven real-world edge applications. The results show that compared with the state-of-the-art works, CoopEdge significantly reduces the deployment cost by 38.7% and improves resource utilization by 36.2%.

With the remarkable development of the 5G technologies, more and more real-time and complex computational tasks from the Internet-of-Things (IoT) systems can be fulfilled by 5G edge servers. While the ultradense deployment is required for 5G edge services, in the upcoming era of 6G with an even more limited communication range, it is almost impossible to achieve 6G service coverage with dense deployments. To address this fundamental limit, we propose EdgeGO, a mobile resource-sharing framework that employs mobile edge servers to provide a cost-effective deployment of 6G edge computing, which enables edge resource sharing for massive IoT devices. Unlike traditional mobile cloudlets, EdgeGO exploits the asynchronization between requests receiving and results returning to decouple the stringent delay and resource requirements for edge computing. As a result, the server moving and task processing could be paralleled. Besides, EdgeGO incorporates a two-layer iterative updating algorithm, which jointly optimizes path planning and task scheduling to improve the overall task efficiency. Extensive simulation results show that by careful managing mobility and task execution of the edge servers, EdgeGO is able to drastically increase the resource utilization by 166.67% and decrease the deployment cost of 6G edge computing by 25.58%.

Spatial keyword query has attracted wide-spread academic and industrial concerns due to the popularity of location-based services and Internet of Things. To efficiently support the online query processing, the data owners need to outsource their data to cloud platforms. However, the outsourcing services may raise privacy leaking issues. Moreover, access control, another important security concern, is largely ignored. Therefore, we first propose and formalize the problem of secure boolean spatial keyword query under lightweight access control while guaranteeing the widely acceptedadaptive indistinguishability against chosen keyword attackmodel. Then, we devise a novel hybrid Bloom filter encoding strategy, including a linear embedding and exponent-based transformation schemes and a secure index structure, calledSAGTree. They can maintain both geo-text and access policy information together in a secure way while answering the encrypted queries under access control without decryption. Finally, we present the in-depth security analysis and demonstrate the performance of our proposed algorithms.

The emerging technologies, such assmart sensors, 5G/6G wireless communication, artificial intelligence, etc., have been maturing the future Internet of Things (IoT) by connecting the massive number of devices, which are expected to consistently collect and transmit real-time data to support business intelligence in an efficient and privacy-preserving way. The IoT can afford businesses predictive maintenance, improve field service, asset tracking, and further enhance customer satisfaction and facility management in industrial sectors. However, the privacy concern in IoT is a big challenge in IoT applications and services. This work proposed a lightweight privacy-preserving scheme based on homomorphic encryption in the context of the IoT, in which we investigated and analyzed the privacy issues between the data owners, untrustworthy third-party cloud servers, and the data users. Meanwhile, computationally efficient homomorphic algorithms are proposed to guarantee the privacy protection for the data users. Experimental results demonstrate that the proposed scheme can effectively prevent privacy breaches in IoT.

To provide various onboard entertainment services, the ever-increased Internet contents to be exchanged among remote data centers, roadside units (RSUs), and vehicles demand reliable and fast content dissemination in the vehicular networks. Edge precaching technology is expected to provide flexible and low-latency content dissemination by allowing edge nodes (i.e., RSUs and vehicles) to precache contents. However, the content dissemination process of edge precaching still suffers from high mobility and highly dynamic topology of vehicular networks. The recently proposed platoon-based vehicular network has potentials to mitigate the mobility challenges, but need to deal with multihop wireless content dissemination’s latency and reliability issues. Additionally, the network resources are limited in edge nodes, whereas various onboard Internet services with different Quality-of-Service (QoS) requirements share the same resource pool by the same network resource scheduling policy, thereby decaying the network performance. Based on the above observations, to cope with the challenging content precaching problem under diverse QoS requirements in a platoon-based edge vehicular network, we first abstract two isolated virtual content service slices with different QoS requirements based on network slicing technology to provide on-demand customized services. Then, we propose an intelligent deep reinforcement learning (DRL)-based content precaching scheme, which optimally matches the available communication resources and limited caching capacities in the edge vehicular network. The scheme jointly considers the impacts of content precaching policy and multihop wireless transmission on the content precaching performance. Simulation results show that our proposed DRL-based content precaching scheme achieves a competitive performance of reliability and latency comparing with other state-of-the-art algorithms.

Over the past few years, fog radio access networks (F-RANs) have become a promising paradigm to support the tremendously increasing demands of multimedia services, by pushing computation and storage functionalities toward the edge of networks, closer to users. In F-RANs, distributed edge caching among fog access points (F-APs) can effectively reduce network traffic and service latency as it places popular contents at local caches of F-APs rather than the remote cloud. Due to the limited caching resources of F-APs and spatiotemporally fluctuant content demands from users, many cooperative caching schemes were designed to decide which contents are popular and how to cache them. However, these approaches often collect and analyze the data from Internet-of-Things (IoT) devices at a central server to predict the content popularity for caching, which raises serious privacy issues. To tackle this challenge, we propose a federated learning-based cooperative hierarchical caching scheme (FLCH), which keeps data locally and employs IoT devices to train a shared learning model for content popularity prediction. FLCH exploits horizontal cooperation between neighbor F-APs and vertical cooperation between the baseband unit (BBU) pool and F-APs to cache contents with different degrees of popularity. Moreover, FLCH integrates a differential privacy mechanism to achieve a strict privacy guarantee. Experimental results demonstrate that FLCH outperforms five important baseline schemes in terms of the cache hit ratio, while preserving data privacy. Moreover, the results show the effectiveness of the proposed cooperative hierarchical caching mechanism for FLCH.

With the increasing popularity of the smart grid, huge volumes of data are gathered from numerous sensors. How to classify, store, and analyze massive data sets to facilitate the development of the smart grid has recently attracted much attention. In particular, with the popularity of household smart meters and electricity monitoring sensors, a large amount of data can be obtained to analyze household electricity usage so as to better diagnose the leakage and theft behaviors, identify man-made tampering and data fraud, and detect powerline loss. In this article, the time window method is first proposed to obtain the features and potential periodicity of household electricity data. Combining the denoising ability of the autoencoder and the induction ability of the feedforward neural network, a multilayer hierarchical network (MLHN) is then established to detect anomalies in single sensor data and classify multiple groups of sensor data, respectively. The experimental results show that the accuracy of detecting abnormal data and data classification is significantly improved compared with the presented scheme.

As a powerful architecture for large-scale computation, cloud computing has revolutionized the way that computing infrastructure is abstracted and utilized. Coupled with the challenges caused by Big Data, the rocketing development of cloud computing boosts the complexity of system management and maintenance, resulting in weakened trustworthiness of cloud services. To cope with this problem, a compelling method, i.e., Support Vector Data Description (SVDD), is investigated in this paper for detecting anomalous performance metrics of cloud services. Although competent in general anomaly detection, SVDD suffers from unsatisfactory false alarm rate and computational complexity in time series anomaly detection, which considerably hinders its practical applications. Therefore, this paper proposes a relaxed form of linear programming SVDD (RLPSVDD) and presents important insights into parameter selection for practical time series anomaly detection in order to monitor the operations of cloud services. Experiments on the Iris dataset and the Yahoo benchmark datasets validate the effectiveness of our approaches. Furthermore, the comparison of RLPSVDD and the methods obtained from Twitter, Numenta, Etsy and Yahoo, shows the overall preference for RLPSVDD in time series anomaly detection.

Edge computing is an emerging promising computing paradigm that brings computation and storage resources to the network edge, hence significantly reducing the service latency and network traffic. In edge computing, many applications are composed of dependent tasks where the outputs of some are the inputs of others. How to offload these tasks to the network edge is a vital and challenging problem which aims to determine the placement of each running task in order to maximize the Quality-of-Service (QoS). Most of the existing studies either design heuristic algorithms that lack strong adaptivity or learning-based methods but without considering the intrinsic task dependency. Different from the existing work, we propose an intelligent task offloading scheme leveraging off-policy reinforcement learning empowered by a Sequence-to-Sequence (S2S) neural network, where the dependent tasks are represented by a Directed Acyclic Graph (DAG). To improve the training efficiency, we combine a specific off-policy policy gradient algorithm with a clipped surrogate objective. We then conduct extensive simulation experiments using heterogeneous applications modelled by synthetic DAGs. The results demonstrate that: 1) our method converges fast and steadily in training; 2) it outperforms the existing methods and approximates the optimal solution in latency and energy consumption under various scenarios.

With time-varying workloads and service requests, cloud-based software services necessitate adaptive resource allocation for guaranteeing Quality-of-Service (QoS) and reducing resource costs. However, due to the ever-changing system states, resource allocation for cloud-based software services faces huge challenges in dynamics and complexity. The traditional approaches mostly rely on expert knowledge or numerous iterations, which might lead to weak adaptiveness and extra costs. Moreover, existing RL-based methods target the environment with the fixed workload, and thus they are unable to effectively fit in the real-world scenarios with variable workloads. To address these important challenges, we propose a Prediction-enabled feedback Control with Reinforcement learning based resource Allocation (PCRA) method. First, a novel Q-value prediction model is designed to predict the values of management operations (by Q-values) at different system states. The model uses multiple prediction learners for making accurate Q-value prediction by integrating the Q-learning algorithm. Next, the objective resource allocation plans can be found by using a new feedback-control based decision-making algorithm. Using the RUBiS benchmark, simulation results demonstrate that the PCRA chooses the management operations of resource allocation with 93.7 percent correctness. Moreover, the PCRA achieves optimal/near-optimal performance, and it outperforms the classic ML-based and rule-based methods by 5$\sim$∼7% and 10$\sim$∼13%, respectively.

Identifying the optimal groups of users that are closely connected and satisfy some ranking criteria from an attributed social network attracts significant attention from both academia and industry. Skyline query processing, a multicriteria decision-making optimized technique, is recently embedded into cohesive subgraphs mining in graphs/social networks. However, the existing studies cannot capture the fuzzy property of connections between users in social networks. To fill this gap, in this article, we formulate a novel model of the skyline$(\lambda,k)$-cliques over a fuzzy attributed social network and develop a formal concept analysis (FCA)-based skyline$(\lambda,k)$-cliques identification algorithm. Specifically,$\lambda $can be regarded as a quality control parameter for measuring the stability of the cohesive groups. Extensive experimental results conducted on three real-world datasets demonstrate the effectiveness of the skyline$(\lambda,k)$-clique model in a fuzzy attributed social network. Furthermore, an illustrative example is executed for revealing the usefulness of our model. It is expected that our proposed skyline$(\lambda,k)$-clique model can be widely used in various graph-based computational social systems, such as optimal team formation in crowdsourcing, and group recommendation in social networks.

The wide availability of online social networks (OSNs) facilitates positive information spread and sharing. However, the high autonomy and openness of the OSNs also allow for the rapid spread of negative information, such as unsubstantiated rumors and other forms of misinformation that often elicit widespread public cognitive misleads and huge economic losses. Therefore, how to effectively control the negative information spread accompanied by positive information has emerged as a challenging issue. Unfortunately, this issue still remains largely unexplored to date. To fill this gap, we propose an efficient feedback control mechanism for the simultaneous spread of the positive and negative information in OSNs. Specifically, a novel computational model is first proposed to present the temporal dynamics of the positive and negative information spread. Furthermore, the proposed mechanism restrains the negative information spread with minimal system expenses by devising and performing three synergetic intervention strategies. Technically, this mechanism intensively evaluates the number of seed users performing three intervention strategies. Besides, each seed user performs the received control task independently, and then the control plan for the next time step is adjusted dynamically according to the previous feedback results. Finally, we evaluate the efficiency of the proposed mechanism based on the extensive experimental results obtained from two real-world networks.

The rapid development of the Industrial Internet of Things (IIoT) enables IIoT devices to offload their computation-intensive tasks to nearby edges via wireless base stations and thus relieve their resource constraints. To better guarantee quality-of-service, it has become necessary to cooperate multiple edges instead of letting them work alone. However, the existing solutions commonly use a centralized decision-making manner and cannot effectively achieve good load balancing among massive edges that are widely distributed in IIoT environments. This results in long decision-making time and high communication costs. To address this important problem, in this article, we propose a reinforcement learning (RL)-empowered feedback control method for cooperative load balancing (RF-CLB). First, by integrating RL and machine learning (ML) algorithms, each edge independently schedules tasks and performs load balancing between adjacent edges based on the local information. Next, through feedback control and multiedge cooperation, the objective multiedge load-balancing plan for IIoT can be found. Simulation results demonstrate that the RF-CLB chooses the adjustment operations of load balancing with 96.3% correctness. Moreover, the RF-CLB achieves the near-optimal performance, which outperforms the classic ML-based and rule-based methods by 6–9% and 10–12%, respectively.

Blockchain has recently been regarded as an important enabler for building secure energy trading in microgrid systems because of its inherent features of distributively providing immutable data record, storage, and sharing across networks in a peer-to-peer (P2P) manner. However, designing highly efficient and scalable blockchain-enabled energy trading mechanisms is extremely challenging because of the unique features of microgrid systems, e.g., bandwidth-constrained and high-latency communications and large-scale renewable energy source (RES) integration. To address this challenge, in this article, we propose a novel scalable blockchain-based energy trading framework for cooperative microgrid systems, which include four planes, i.e., data plane, consensus plane, smart plane, and application plane. Different from the existing solutions without consideration of network transmission, these four planes are designed with the capability of perceiving the status of block generation and transmission over interrupted P2P networks, and thus proactively improving the consensus process to guarantee the reliability of energy trading in cooperative microgrids. Meanwhile, built on this framework, a novel redundant data exchange strategy is proposed to improve the scalability of block creation with the presence of large-scale RES penetration and interrupted and dynamic communication links. Simulation results show that the proposed system framework outperforms the benchmark blockchain solutions. Furthermore, we investigate the potential applications of the proposed solutions in the practical microgrid systems to facilitate a clear understanding of the mechanisms of the proposed solutions.

Network slicing has emerged as a promising networking paradigm to provide resources tailored for Industry 4.0 and diverse services in 5G networks. However, the increased network complexity poses a huge challenge in network management due to virtualized infrastructure and stringent quality-of-service requirements. Digital twin (DT) technology paves a way for achieving cost-efficient and performance-optimal management, through creating a virtual representation of slicing-enabled networks digitally to simulate its behaviors and predict the time-varying performance. In this article, a scalable DT of network slicing is developed, aiming to capture the intertwined relationships among slices and monitor the end-to-end (E2E) metrics of slices under diverse network environments. The proposed DT exploits the novel graph neural network model that can learn insights directly from slicing-enabled networks represented by non-Euclidean graph structures. Experimental results show that the DT can accurately mirror the network behaviour and predict E2E latency under various topologies and unseen environments.

The statistical value of latencies between two sets of hosts over a given period, which is referred as to the statistical latency, can benefit many applications in the next-generation networks, for example, Network-in-a-Box-based resource provisioning. However, the existing methods can hardly achieve low measurement cost and high prediction accuracy simultaneously in large-scale scenarios. In this article, we design a light-weight statistical latency measurement platform named DMS (DNS-based statistical latency Measurement platform at Scale). DMS achieves high measurement accuracy by introducing a metric space to select the closest open recursive DNS (Domain Name System) server to a given host, and predicting the end-to-end latency between two hosts via the measured latency between the two corresponding DNS servers. To reduce the overall measurement overhead, DMS clusters the hosts in the metric space with the open recursive DNS infrastructure in the network as the cluster center, thus achieving low measurement cost and good scalability in large scale simultaneously. To evaluate the performance of DMS, we implement a prototype system in the network. Compared to the widely adopted method King, DMS can reduce the relative error by 18.5% for real-time end-to-end latency prediction and 33% for statistical latency prediction.

Temporal information is critical for routing computation in the vehicular network. It plays a vital role in the vehicular network. Till now, most existing routing schemes in vehicular networks consider the networks as a sequence of static graphs. We need to find an appropriate method to process temporal information into routing computation. Thus, in this paper, we propose a routing algorithm based on the Hidden Markov Model (HMM) and temporal graph, namely, Prediction-Based Temporal Graph Routing Algorithm (PT-GROUT). This new algorithm considers the vehicular network as a temporal graph, in which each data transmission as an edge has its specific temporal information. To better capture the temporal information, we select Software-Defined Vehicular Network (SDVN) as our network architecture, which is a preferred architecture for processing the temporal graph regarding the vehicular network since all vehicle statuses can be easily managed. To compute the future routing path accurately and efficiently, the future temporal graph is predicted by applying HMM, in which we model the current vehicular network with dynamic programming and greedy strategies. With the temporal information and reasonable setting of HMM, PT-GROUT can better evaluate the vehicular network and discover the evolution of the internal structure of the network. The optimal routing path can be achieved more efficiently. The simulation results demonstrate that PT-GROUT can substantially improve the computation efficiency and reduce packet loss and delivery delay compared with its counterparts.

As customers take virtual machines (VMs) as their demands, high-efficient placement of VMs is required to reduce the energy consumption in data centers. Existing Virtual Machine placement (VMP) strategies can minimize energy consumption of data centers by optimizing resource allocation in terms of multiple physical resources (e.g., memory, bandwidth, CPU, etc.). However, these strategies ignore the role of heat recirculation in the data center, which can cause a huge energy waste in cooling. To address this problem, we propose a heat-recirculation-aware VMP strategy for reducing the energy consumption of data centers. This novel VMP strategy takes into account heat recirculation coupled with multiple physical resource allocation to reduce the energy consumption of data centers. We design a simulated annealing based algorithm called SABA to lower the energy consumption of data centers where multiple VMs are deployed. SABA remarkably cuts down the energy consumption of physical resources through two salient features. First, it obtains an approximation of the optimum with much fewer iterations than simulated annealing algorithm (SA). Second, it reduces the number of activated servers required for VM tasks. We quantitatively evaluate the performance of SABA in terms of algorithm efficiency, the number of activated servers and the energy-saving. We compare the performance of SABA with state-of-art XINT-GA, PPVMP, TSTD and SA algorithms. Moreover, we evaluate the efficiency of SABA by leveraging a real-world 50 hours trace from practical IBM cloud data centers. Experimental results indicate that our heat-recirculation-aware VM placement strategy provides a powerful solution for improving the energy efficiency of data centers (SABA improves energy efficiency of cooling by up to 13.2% over TSTD, 13.8% over XINT-GA and 45% over PPVMP algorithm).

Contemporary machine learning methods have evolved from conventional algorithms to deep neural networks (DNNs) that are computation- and data- intensive. Thus, they are suitable to be deployed in the cloud that can offer high computational capacity and scalable resources. However, the cloud computing paradigm is not optimal for delay- and energy-sensitive applications. To mitigate these problems, a battery of distributed DNNs have been proposed to allow a fast inference with device-edge-cloud synergy. Furthermore, although distributed deployment of DNNs on real communication networks is an important research topic, the legacy network architecture cannot meet the requirements of these distributed deep neural networks due to the complicated management and manual configuration, etc. To cope with these requirements, we develop a novel and explicit Intelligent Software Defined Networking (ISDN) that aims to manage the bandwidth and computing resources across the network via the SDN paradigm. We first identify the difficulties of deploying distributed intelligent computing in the current network architecture. Then, we explain how to address these problems by introducing the ISDN architecture. Specifically, we develop a dynamic routing method to enable Quality-of-Service (QoS) communication based on the SDN paradigm and propose a Markov Decision Process (MDP) based dynamic task offloading model to achieve the optimal offloading policy of DNN tasks. We develop a simulation platform based on Mininet to measure its performance advantages over traditional architectures. Extensive experimental results show that compared with the traditional network architecture, our architecture based on the SDN paradigm can perform better in terms of both network throughput and resource utilization.

Instantiated containers of an application are distributed across multiple Physical Machines (PMs) to achieve high parallel performance. Container placement plays a vital role in network traffic and the performance of containerized data centers. Existing container placement techniques are inadequate due to the ignorance of container traffic patterns. To solve this issue, we first investigate the network traffic between containers and observe that it exhibits a Zipf-like distribution. Motivated by this finding, we propose a novel container placement approach-Blender-by taking into account the Zipf-like distribution. Blender employs two algorithms calledRefineAlgandSplitAlgto divide containers of applications into blocks, and place these blocks across Virtual Machines (VMs). Blender exhibits two salient features: (i) it minimizes inter-block traffic by arranging the containers that communicate frequently in the same block. (ii) it achieves good load balancing by combining complementary blocks that request different resource types (e.g.,CPU-intensiveandmemory-intensiveblocks) and distributing these blocks across multiple VMs. The experimental results show that Blender significantly reduces communication traffic and network latency. In particular, Blender reduces the traffic of SBP and CA-WFD by 22% and 32%, respectively. Blender decreases network latency by 16% and 26% compared to SBP and CA-WFD. Furthermore, with Blender in place, the physical resources of hosting PMs are well balanced and utilized.

Low-power wireless networks (LPWNs) are of paramount importance for the pervasive deployment of Internet-of-Things (IoT). To deal with the lossy nature of LPWNs, opportunistic routing (OR) and multichannel communications (MC) have received significant research interests. In particular, coupling OR with MC has become an important way to further enhance the communication performance in LPWNs. However, as OR requires nodes in the same channel while MC separates nodes into different channels, the benefits of MC-OR combination are largely under-utilized. To address this problem, we investigate the challenging issue of establishing opportunistic routing in multichannel LPWNs. Different from the existing studies that separately assign channels and select forwarders, we propose a synergistic multichannel and opportunistic routing (SMOpp) approach, which jointly combines the benefits of both OR and MC by considering link correlation. SMOpp explicitly evaluates the routing opportunities of each channel/forwarder set and then employs a forwarder-initiated scheme to select the best combinations of senders, forwarders, and channels. The testbed evaluation shows that compared to the existing methods, SMOpp significantly improves the transmission efficiency for LPWNs.

As an indispensable part of modern critical infrastructures, cameras deployed at strategic places and prime junctions in an intelligent transportation system can help operators in observing traffic flow, identifying any emergency situation, or making decisions regarding road congestion without arriving on the scene. However, these cameras are usually equipped with heterogeneous and turbulent networks, making the real-time smooth playback of traffic monitoring videos with high quality a grand challenge. In this article, we propose a lightweight Deep Reinforcement Learning-based approach, namely, sRC-C (smart bitRate Control with a Continuous action space) , to enhance the quality of real-time traffic monitoring by adjusting the video bitrate adaptively. Distinguished from the existing bitrate adjusting approaches, sRC-C can overcome the bias incurred by deterministic discretization of candidate bitrates by adjusting the video bitrate with more fine-grained control from a continuous action space, thus significantly improving the Quality-of-Service (QoS). With carefully designed state space and neural network model, sRC-C can be implemented on cameras with scarce resources to support real-time live video streaming with low inference time. Extensive experiments show that sRC-C can reduce the frame loss counts and hold time by 24% and 15.5%, respectively, even with comparable bandwidth utilization. Meanwhile, compared to the-state-of-art approaches, sRC-C can improve the QoS by 30.4%.

The ever-expanding scale of cloud datacenters necessitates automated resource provisioning to best meet the requirements of low latency and high energy-efficiency. However, due to the dynamic system states and various user demands, efficient resource allocation in cloud faces huge challenges. Most of the existing solutions for cloud resource allocation cannot effectively handle the dynamic cloud environments because they depend on the prior knowledge of a cloud system, which may lead to excessive energy consumption and degraded Quality-of-Service (QoS). To address this problem, we propose an adaptive and efficient cloud resource allocation scheme based on Actor-Critic Deep Reinforcement Learning (DRL). First, the actor parameterizes the policy (allocating resources) and chooses actions (scheduling jobs) based on the scores assessed by the critic (evaluating actions). Next, the resource allocation policy is updated by using gradient ascent while the variance of policy gradient is reduced with an advantage function, which improves the training efficiency of the proposed method. We conduct extensive simulation experiments using real-world data from Google cloud datacenters. The results show that our method can obtain the superior QoS in terms of latency and job dismissing rate with enhanced energy-efficiency, compared to two advanced DRL-based and five classic cloud resource allocation methods.

Deep Neural Networks (DNNs) have become an essential and important supporting technology for smart Internet-of-Things (IoT) systems. Due to the high computational costs of large-scale DNNs, it might be infeasible to directly deploy them in energy-constrained IoT devices. Through offloading computation-intensive tasks to the cloud or edges, the computation offloading technology offers a feasible solution to execute DNNs. However, energy-efficient offloading for DNN based smart IoT systems with deadline constraints in the cloud-edge environments is still an open challenge. To address this challenge, we first design a new system energy consumption model, which takes into account the runtime, switching, and computing energy consumption of all participating servers (from both the cloud and edge) and IoT devices. Next, a novel energy-efficient offloading strategy based on a Self-adaptive Particle Swarm Optimization algorithm using the Genetic Algorithm operators (SPSO-GA) is proposed. This new strategy can efficiently make offloading decisions for DNN layers with layer partition operations, which can lessen the encoding dimension and improve the execution time of SPSO-GA. Simulation results demonstrate that the proposed strategy can significantly reduce energy consumption compared to other classic methods.

The cloud computing paradigm provides numerous tempting advantages, enabling users to store and share their data conveniently. However, users are naturally resistant to directly outsourcing their data to the cloud since the data often contain sensitive information. Although several fine-grained access control schemes for cloud-data sharing have been proposed, most of them focus on the access control of the encrypted data (e.g., restricting the decryption capabilities of the receivers). Distinct from the existing work, this article aims to address this challenging problem by developing a more practical bidirectional fine-grained access control scheme that can restrict the capabilities of both senders and receivers. To this end, we systematically investigate the access control for cloud data sharing. Inspired by the access control encryption (ACE), we propose a novel data sharing framework that combines the cloud side and the edge side. The edge server is located in the middle of all the communications, checking and preventing illegal communications according to the predefined access policy. Next, we develop an efficient access control algorithm by exploiting the attribute-based encryption and proxy re-encryption for the proposed framework. The experimental results show that our scheme exhibits superior performance in the encryption and decryption compared to the prior work.

Federated Learning (FL) is an emerging approach for collaboratively training Deep Neural Networks (DNNs) on mobile devices, without private user data leaving the devices. Previous works have shown that non-Independent and Identically Distributed (non-IID) user data harms the convergence speed of the FL algorithms. Furthermore, most existing work on FL measures global-model accuracy, but in many cases, such as user content-recommendation, improving individual User model Accuracy (UA) is the real objective. To address these issues, we propose a Multi-Task FL (MTFL) algorithm that introduces non-federated Batch-Normalization (BN) layers into the federated DNN. MTFL benefits UA and convergence speed by allowing users to train models personalised to their own data. MTFL is compatible with popular iterative FL optimisation algorithms such as Federated Averaging (FedAvg), and we show empirically that a distributed form of Adam optimisation (FedAvg-Adam) benefits convergence speed even further when used as the optimisation strategy within MTFL. Experiments using MNIST and CIFAR10 demonstrate that MTFL is able to significantly reduce the number of rounds required to reach a target UA, by up to$5\times$when using existing FL optimisation strategies, and with a further$3\times$improvement when using FedAvg-Adam. We compare MTFL to competing personalised FL algorithms, showing that it is able to achieve the best UA for MNIST and CIFAR10 in all considered scenarios. Finally, we evaluate MTFL with FedAvg-Adam on an edge-computing testbed, showing that its convergence and UA benefits outweigh its overhead.

With the rapid growth of networked multimedia services in the Internet, wireless network traffic has increased dramatically. However, the current mainstream content caching schemes do not take into account the cooperation of different edge servers, resulting in deteriorated system performance. In this paper, we propose a learning-based edge caching scheme to enable mutual cooperation among different edge servers with limited caching resources, thus effectively reducing the content delivery latency. Specifically, we formulate the cooperative content caching problem as an optimization problem, which is proven to be NP-hard. To solve this problem, we design a new learning-based cooperative caching strategy (LECS) that encompasses three key components. Firstly, a temporal convolutional network driven content popularity prediction model is developed to estimate the content popularity with high accuracy. Secondly, with the predicted content popularity, the concept of content caching value (CCV) is introduced to weigh the value of a content cached on a given edge server. Thirdly, an novel dynamic programming algorithm is developed to maximize the overall CCV. Extensive simulation results have demonstrated the superiority of our approach. Compared with the state-of-the-art caching schemes, LECS can improve the cache hit rate by 8.3%-10.1%, and reduce the average content delivery delay by 9.1%-15.1%.

The knowledge of network distances, in the form of delay or latency, for example, is beneficial to a number of distributed applications. Notice that it is difficult and expensive to implement global network measurements to obtain network distance, a feasible idea is to predict unknown distances by introducing network coordinates with limited network measurements. The existing solutions always represent the unknown network distances in a rather unique number. However, research and applications indicate that the real network distances are hard to be accurately figured out and changes subtly in an interval over time with the dynamic network environments. Accordingly, this article proposes a tensor-based network distance prediction (TNDP) approach to represent network distance with confidence intervals, by exploiting the random distance tensor and distributed matrix factorization. With a small set of network measurements among the nodes selected randomly, a distance matrix tensor has been established and factorized into the product of two location matrixes with the adaptive SGD-based learning solution. By introducing the important training determinants, including weight matrix, regularization coefficient, and minibatch gradient descent with the exponential decay rates, the unknown distances among nodes can be accurately inferred in the forms of confidence intervals, with quick convergence and less overfitting. Extensive experimental simulations on a wide variety of available data sets demonstrate that TNDP is superior to other approaches in terms of accuracy for network distance prediction.

Knowledge graph describes entities by numerous RDF data (subject-predicate-object triples), which has been widely applied in various fields, such as artificial intelligence, Semantic Web, entity summarization. With time elapses, the continuously increasing RDF descriptions of entity lead to information overload and further cause people confused. With this backdrop, automatic entity summarization has received much attention in recent years, aiming to select the most concise and most typical facts that depict an entity in brief from lengthy RDF data. As new descriptions of entity are continually coming, creating a compact summary of entity quickly from a lengthy knowledge graph is challenging. To address this problem, this article first formulates the problem and proposes a novel approach of Incremental Entity Summarization by leveraging Formal Concept Analysis (FCA), called IES-FCA. Additionally, we not only prove the rationality of our suggested method mathematically, but also carry out extensive experiments using two real-world datasets. The experimental results demonstrate that the proposed method IES-FCA can save about 8.7 percent of time consumption for all entities than the non-incremental entity summarization approach KAFCA at best. As for the effectiveness, IES-FCA outperforms the state-of-the-art algorithms in terms of$F1-measure$,$MAP$, and$NDCG$.

Implementing federated learning (FL) algorithms in wireless networks has garnered a wide range of attention. However, few works have considered the impact of user mobility on the learning performance. To fill this research gap, we develop a theoretical model to characterize the hierarchical federated learning (HFL) algorithm in wireless networks where the mobile users may roam across edge access points (APs), leading to incompletion of inconsistent FL training. We provide the convergence analysis of conventional HFL with user mobility. Our analysis proves that the learning performance of conventional HFL deteriorates drastically with highly-mobile users. And such a decline in the learning performance will be exacerbated with small number of participants and large data distribution divergences among users’ local data. To circumvent these issues, we propose a mobility-aware cluster federated learning (MACFL) algorithm by redesigning the access mechanism, local update rule, and model aggregation scheme. We also conduct experiments to evaluate the learning performance of conventional HFL, a cluster federated learning (CFL) with simple averaging, and our proposed MACFL. The results show that our MACFL can enhance the learning performance, especially for three different cases: ($i$) the case of users with non-independent and identically distributed (non-IID) data, ($ii$) the case of users with high mobility, and ($iii$) the case with a small number of users.

Instantiated containers of an application are distributed across multiple Physical Machines (PMs) to achieve high parallel performance. Container placement plays a vital role in network traffic and the performance of containerized data centers. Existing container placement techniques do not consider the container traffic pattern, which is inadequate. To resolve this conflict, we investigate network traffic between containers and observe that it exhibits a Zipf-like distribution. We propose a novel container placement approach - Blender - by leveraging the Zipf-like distribution. Based on network traffic correlation, Blender employs RefineAlg and SplitAlg to divide containers of applications into blocks, and place these blocks across virtual machines. Blender exhibits two salient features: (i) it minimizes inter-block traffic by arranging the containers that communicate frequently in the same block. (ii) it achieves good load balancing by combining blocks according to the resource types they require and distributing them across multiple PMs. We compare Blender against two state-of-the-art methods SBP and CA-WFD. The experimental results show that Blender significantly reduces communication traffic. In particular, for the same number of PMs, Blender reduces the traffic of SBP and CA-WFD by 22% and 32%, respectively. Furthermore, with Blender in place, the physical resources of hosting PMs are well balanced and utilized.

Recently, the implementation of federated learning (FL) in wireless networks becomes a hotspot due to its flexible collaborative learning methods and privacy-preserving benefits. However, most of the existing works overlook the impact of user mobility on the learning performance, which is critical. Specifically, the mobile users may roam among multiple edge access points (APs) during the local training procedures, leading to incompletion of inconsistent FL training. In this paper, we theoretically study the impact of user mobility on the FL in hierarchical wireless networks. In our system model, the network consists of one cloud server, several edge APs, and multiple mobile users that have their positions vary over time. During the local training process, users may stay in or move out of the coverage area of the originally attached edge AP. In such a practical context, we analyze the convergence rate of the FL algorithm and provide experiments to evaluate the learning performance under different network parameters. Our results provide insights in further improvements of FL in hierarchical wireless networks.

Offloading decisions in mobile edge computing have been extended with multiple objectives, such as revenue maximization, energy conservation and latency reduction. Revenues of network/service operators, as the realistic and ultimate goal at intensive competitive markets, have not been thoroughly studied under a pricing scheme in combination with offloading decisions, especially with the aims of reducing and restricting energy consumption and latency. To bridge this important gap, this paper studies the revenue maximization of network operators through a pricing scheme in mobile edge computing, by explicitly formulating energy consumption and latency into the offloading strategy. A two-stage game-theory framework based on the Stackelberg game is established, through which the optimal price for both the network operator and the customer can be reached. The offloading data size can be dynamically adjusted according to the agreed price. The existence of equilibrium in the Stackelberg game is proved, and experiments are conducted to verify the effectiveness of our proposed model.

The increasing of group polarization on social media seriously impacts on the health of public discourse and information dissemination. At present, detecting polarized structures in signed networks is well-motivated for studying the group polarization on social media. However, most studies restricted the number of polarized structures to only two, while neglecting the real-world scenario where signed networks consist of multiple polarized structures, that is an unreasonable assumption. To conquer the limitations of the existing work, in this paper, we present a novel cohesive subgraph model based on structural clusterable theory, named maximal multipolarized clique (MMC), which can be partitioned into k polarized subcliques such that the edges in subcliques are positive and the edges between subcliques are negative. This paper formulates the problem of Maximal Multipolarized Cliques Search (MMCS) in signed networks which is proved to be NP-hard. To address this problem, we first devise powerful pruning rules to reduce the signed network significantly and further develop an efficient algorithm to search all maximal multipolarized cliques in the reduced signed network. The experimental results on real-world signed networks demonstrate the efficiency and effectiveness of our algorithm.

Evolutionary Algorithms (EA) are known to suffer from the curse of dimensionality resulting in poor performances when handling large-scale problems. Cooperative coevolution aims to overcome these issues in a divide and conquer approach by decomposing the original problem into several lower-dimensional sub-problems. For each sub-problem a chosen EA is applied for a defined number of function evaluations. This is repeated in a round robin like fashion until a terminating condition is met. A recently proposed area in the evolutionary computation field is the evolutionary multitask optimization (EMTO) framework. By jointly optimising several tasks, EMTO aims to exploit beneficial information across multiple tasks to improve the performance compared to optimising each task in isolation. In this paper, we consider a large-scale problem as a multi-task optimization problem by considering each sub-problem as an independent task. Applying an EMTO algorithm, knowledge transfer across sub-problems is carried out explicitly to improve the optimization of each sub-problem. We evaluate the effectiveness of our proposed algorithms empirically on a suite of separable and non-separable benchmark problems of varying dimensions.

Summary Mobile edge computing (MEC) necessitates cost‐effective deployment for executing scientific workflows with different tasks and datasets, which provides computing, storage and network control at the network edge. However, the execution of scientific workflows in MEC results in heavy costs of data placement including data transmission and data storage. Although there are solutions for data placement in traditional cloud computing, they cannot effectively respond to the latency‐sensitive property of scientific workflows, which leads to the excessive costs of data placement. To cope with this problem, we combine the advantages of MEC and cloud computing and propose a genetic algorithm particle swarm optimization (GAPSO) based method to explore the optimal strategy of data placement for scientific workflows in MEC. First, a unified model of data placement is designed to explore a cost‐effective strategy, which considers the different characteristics between MEC and cloud computing as well as the impact of latency constraint on transmission costs. Next, the advantages of genetic algorithm (GA) and particle swarm optimization (PSO) are integrated to optimize the proposed model, which utilities the fast convergence of PSO and the crossover and mutation operations of GA. Simulations using real‐world scientific workflows show the effectiveness of the proposed method for reducing data placement costs in MEC.

Abstract One of the main challenges in computer science and image processing is 2D human pose estimation. Specifically, occlusion and in particular occlusion of human joints caused by camera angle are of paramount importance. In this paper, a new highly accurate network was proposed that can estimate 2D human poses in video images using deep learning. We employ the Single Shot MultiBox Detector network to detect the centre position of each human within a video frame and then use the stacked hourglass network to estimate the 2D human pose. We approximate the human motion as a linear motion between different frames in a certain period; and optimize the human centres based on the local outlier factor and Kalman filters. The same method is applied to optimize the human pose estimations in video, which can address the inaccurate prediction caused by human joints occlusion. The proposed adaptive network is tested using the two well‐known benchmarks for human pose estimation (MPII and Joint‐annotated Human Motion Data Base datasets), and we also generate some 2D human pose estimating qualitative results of single and multiple people in Internet videos. The experimental results show that the proposed network has strong practicability and can achieve high accuracy on adaptive estimating the 2D human pose in video.

Energy costs have dramatically increased in data center networks as an increasing number of large-scale Internet applications are used. In software-defined vehicular networks (SDVN), the communication delay between two vehicles and between vehicles and the controller will dramatically climb up as the number of vehicles increases. This requires more controllers to provide communication service to minimize the latency. More controllers lead to high energy costs. Therefore, the number of controllers and their placement, the so-called controller placement problem (CPP), should be addressed. The appropriate placement of controllers can decrease the energy cost, enabling green communication in SDVN. Although CPP has been studied for static networks, it has not been effectively solved in highly dynamic and complex networks. In this article, a novel cost-effective CPP scheme for SDVN is proposed. First, our proposed minimum controller selection mechanism (MOSA) can reduce the number of controllers and guarantee the coverage of the area. Besides, an improved multiobjective artificial bee colony algorithm (IMABC) is proposed based on the original artificial bee colony algorithm. The IMABC can judge which controller should be switched on for data transmission based on real-time traffic flow. A route computation mechanism is proposed to evaluate the performance of our CPP scheme. The experimental results confirm that compared to other existing CPP schemes, our scheme can achieve a higher packet delivery ratio while greatly reducing energy consumption and latency.

Cellular communications have been regarded as promising approaches to deliver high-broadband communication links for unmanned aerial vehicles (UAVs), which have been widely deployed to conduct various missions, e.g., precision agriculture, forest monitoring, and border patrol. However, the unique features of aerial UAVs, including high-altitude manipulation, 3-D mobility, and rapid velocity changes, pose challenging issues to realize reliable cellular-enabled UAV communications, especially with the severe intercell interference generated by UAVs. To deal with this issue, we propose a novel position-based robust beamforming algorithm through complementarily integrating the navigation information and wireless channel information to improve the performance of cellular-enabled UAV communications. Specifically, in order to achieve the optimal beam weight vector, the navigation information of the UAV system is innovatively exploited to predict the changes of the direction-of-Arrival (DoA) angle. To fight against the high mobility of UAV operations, an optimization problem is formed by considering the tapered surface of DoA angle and solved to correct the inherent position error. Comprehensive simulation experiments are conducted and the results show that the proposed robust beamforming algorithm could achieve over 90% DoA estimation error reduction and up to 14-dB SINR gain compared with five benchmark beamforming algorithms, including linearly constrained minimum variance (LCMV), position-based beamforming, diagonal loading (DL), robust capon beamforming (RCB), and robust LCMV algorithm.

The epoch of the Internet of Things (IoT) has come by enabling almost everything to gather and share electronic information. Considering the unreliable factors of public IoT, how to outsource huge amounts of indispensable stream data generated by the nodes to the remote storage (RS) efficiently and securely is one of the most challenging issues. In this article, we propose a secure lightweight stream data outsourcing framework for IoT based on identity and blockchain. Taking advantage of identity-based cryptography and blockchain, for public IoT containing untrusted communication channels, nodes, RS, and even verifiers, we introduce a private mobile network and multiple verifiers to ensure that the stream data are stored intact and updated correctly, without the costs and risks brought by the public-key infrastructures (PKI). Meanwhile, the framework can also achieve privacy-preserving checking, by revealing no data to the other entities besides the RS, even in the blockchains. Our comprehensive analysis and experiments demonstrate that the proposed framework is suitable for lightweight devices and practical for IoT.

Prediction of the future location of vehicles and other mobile targets is instrumental in intelligent transportation system applications. In fact, networking schemes and protocols based on machine learning can benefit from the results of such accurate trajectory predictions. This is because routing decisions always need to be made for the future scenario due to the inevitable latency caused by the processing and propagation of the routing request and response. Thus, to predict the high-precision trajectory beyond the state of the art, we propose a generative adversarial network (GAN)-based vehicle trajectory prediction method, GAN-VEEP, for urban roads. The proposed method consists of three components: 1) vehicle coordinate transformation for data set preparation; 2) neural network prediction model trained by GAN; and 3) vehicle turning model to adjust the prediction process. The vehicle coordinate transformation model is introduced to deal with the complex spatial dependence in the urban road topology. Then, the neural network prediction model learns from the behavior of vehicle drivers. Finally, the vehicle turning model can refine the driving path based on the driver’s psychology. Compared with its counterparts, the experimental results show that GAN-VEEP exhibits higher effectiveness in terms of the average accuracy, mean absolute error, and root-mean-squared error.

Network function virtualization (NFV) is critical to the scalability and flexibility of various network services in the form of service function chains (SFCs), which refer to a set of Virtual Network Functions (VNFs) chained in a specific order. However, the NFV performance is hard to fulfill the ever-increasing requirements of network services mainly due to the static orchestrations of SFCs. To tackle this issue, a novel Scalable SFC Orchestration (SSCO) scheme is proposed in this paper for NFV-enabled networks via federated reinforcement learning. SSCO has three remarkable characteristics distinguishing from the previous work: (1) A federated-learning-based framework is designed to train a global learning model, with time-variant local model explorations, for scalable SFC orchestration, while avoiding data sharing among stakeholders; (2) SSCO allows for parameter update among local clients and the cloud server just at the first and last epochs of each episode to ensure that distributed clients can make model optimization at a low communication cost; (3) SSCO introduces an efficient deep reinforcement learning (DRL) approach, with the local learning knowledge of available resources and instantiation cost, to map VNFs into networks flexibly. Furthermore, a loss-weight-based mechanism is proposed to generate and exploit reference samples in replay buffers for future training, avoiding the strong relevance of samples. Simulation results obtained from different working scenarios demonstrate that SSCO can significantly reduce placement errors and improve resource utilization ratio to place time-variant VNFs compared with the state-of-the-art mechanisms. Furthermore, the results show that the proposed approach can achieve desirable scalability.

To build energy-efficient datacenters, one widely used way is to dynamically manipulate the quantity of available hardware resources on demand. However, when bursty workloads appear, additional time overhead is required for resource gearing, thus incurring a performance degradation. To explore this problem, we present an intelligible analysis on the request handing in a VM. From the analysis, we find that, when workloads are overloaded (i.e., peak loads appear), the number of QoS guaranteed requests can be greatly increased by deferring the scheduling of a few requests. Inspired by this finding, we propose a Peak Load Scheduling Control (PLSC) method to promote the Quality of Service (QoS) of peak loads for modern energy-efficient datacenters. However, peak loads are usually difficult to identify. To overcome this difficulty, PLSC tracks the number of requests residing in a VM by leveraging a two-tier request queue maintained by it. When the number exceeds the capability of the VM, it means that peak loads appear. In this case, PLSC adds some delay-tolerant requests to the secondary queue. The scheduling of requests in the secondary queue is controlled with a lower priority than that of requests in the primary queue. Sequentially, with critical requests maintained in the primary queue, PLSC shortens the response time of critical requests. In addition, PLSC expands the number of QoS-guaranteed requests. Comprehensive experiments are conducted to attest the effectiveness of PLSC, by simulating a typical energy-efficient datacenter. The experimental results show that PLSC significantly promotes the QoS of workloads with a negligible impact on energy saving.

Cloud has become an important platform for executing numerous deadline-constrained scientific applications generally represented by workflow models. It provides scientists a simple and cost-efficient method of running workflows on their rental Virtual Machines (VMs) anytime and anywhere. Since pay-as-you-go is a dominating pricing solution in clouds, extensive research efforts have been devoted to minimizing the monetary cost of executing workflows by designing tailored VM allocation mechanisms. However, most of them assume that the task execution time in clouds is static and can be estimated in advance, which is impractical in real scenarios due to performance fluctuation of VMs. In this paper, we propose an onliNe multi-workflOwSchedulingFramework, named NOSF, to schedule deadline-constrained workflows with random arrivals and uncertain task execution time. In NOSF, workflow scheduling process consists of three phases, including workflow preprocessing, VM allocation and feedback process. Built upon the new framework, a deadline-aware heuristic algorithm is then developed to elastically provision suitable VMs for workflow execution, with the objective of minimizing the rental cost and improving resource utilization. Simulation results demonstrate that the proposed algorithm significantly outperforms two state-of-the-art algorithms in terms of reducing VM rental costs and deadline violation probability, as well as improving the resource utilization efficiency.

Federated learning (FL) has been employed for numerous privacy-sensitive applications, where distributed devices collaboratively train a global model. In industrial Internet of things (IIoT) systems, training latency is the key performance metric as the automated manufacture usually requires timely processing. The existing works increase the number of effective devices to accelerate the training. However, devices in IIoT systems are usually deployed densely; increasing the number of clients can potentially cause serious interference and prolonged training latency. In this article, we propose a resource allocation scheme for FL, namely RaFed. We formulate the problem of reducing training latency as an optimization problem, which is proved to be NP-hard. We propose a heuristic algorithm to select appropriate devices for achieving a good tradeoff between the interference and convergence time. We conduct experiments using an RGB-D dataset in an IIoT system. The results show that RaFed significantly reduces the latency by 29.9%, compared to the state-of-the-art works.

5G networks are expected to provide cost-efficient, reliable, and flexible services for industrial productions and applications potentially, by introducing emerging network technologies like blockchain and network functions virtualization (NFV), which virtualizes network functions and runs them on standard infrastructure rather than customized hardware. However, how to deal with the emerging security challenges and fulfil the requirement of ultra-reliable and low-latency communications (URLLC) has not been fully resolved. In this article, we present an NFV-enabled 5G paradigm for the industry with the guarantee of URLLC through service chain acceleration and dynamic blockchain-based spectrum resource sharing among a variety of industry applications running in NVF-based equipment. First, we elaborate the benefits and shortcomings of NFV for industry, by executing an industry application experiment in virtualized and nonvirtualized data center networks. Then, we illustrate an NFV-enabled 5G paradigm for URLLC in detail, with a special focus on the service chain acceleration and spectrum sharing built on NFV, blockchain, software-defined networking, and mobile edge computing. Finally, we establish a mathematical model to study the worst-cast transmission latency of NFV-enabled 5G with the input of the bursty traffic. The proposed model can be exploited to support the plan, management, and optimization of NFV-enabled 5G URLLC systems for industry.

Internet of Things (IoT) has become one of the fastest-growing technologies and has been broadly applied in various fields. IoT networks contain millions of devices with the capability of interacting with each other and providing functionalities that were never available to us before. These IoT networks are designed to provide friendly and intelligent operations through big data analysis of information generated or collected from an abundance of devices in real time. However, the diversity of IoT devices makes the IoT networks’ environments more complex and more vulnerable to various web attacks compared to traditional computer networks. In this article, we propose a novel ensemble deep learning based web attack detection system (EDL-WADS) to alleviate the serious issues that IoT networks faces. Specifically, we have designed three deep learning models to first detect web attacks separately. We then use an ensemble classifier to make the final decision according to the results obtained from the three deep learning models. In order to evaluate the proposed WADS, we have performed experiments on a public dataset as well as a real-word dataset running in a distributed environment. Experimental results show that the proposed system can detect web attacks accurately with low false positive and negative rates.

The last few decades have witnessed an explosive growth of the Internet-of-Things (IoT) systems, which provide ubiquitous sensing and computing services. When adopted in industrial and manufacturing environments, IoT is referred to as the industrial IoT (IIoT), which has attracted increasing research attention. Energy efficiency is one of the most important research topics in green IIoT, as 1) the limited resource can significantly affect the lifetime of IIoT systems and 2) massive sensors, devices, machines keep consuming a considerable amount of energy, and increasing the carbon footprint. In this article, we present a comprehensive survey on energy-efficient communications and computation mechanisms in IIoT systems (such as smart grids). We categorize the existing works, review, discuss, and compare the works to explore their pros and cons. We also discuss the open issues and research challenges, considering the recent 5G communications and edge computing trends.

With the massive deployment of 5G cellular infrastructures, traffic prediction has become an indispensable part of the cellular resource management system in order to provide reliable and fast communication services that can meet the increasing quality-of-service requirements of smart city. A promising approach for handling this problem is to introduce intelligent methods to implement a highly effective and efficient cellular traffic prediction model. Meanwhile, integrating the multiaccess edge computing framework in 5G cellular networks facilitates the application of intelligent traffic prediction models by enabling their implementation at the network edge. However, the data shortage and privacy issues may still be obstacles for training a robust and accurate prediction model at the edge. To address these issues, we propose a data-augmentation-based cellular traffic prediction model (ctGAN-S2S), where an effective data augmentation submodel based on generative adversarial networks is proposed to improve the prediction performance while protecting data privacy, and a long-short-term-memory-based sequence-to-sequence submodel is used to achieve the flexible multistep cellular traffic prediction. The experimental results on a real-world city-scale cellular traffic dataset reveal that our ctGAN-S2S model achieves up to 48.49% improvement of the prediction accuracy compared to four typical reference models.

Content Caching at the edge of vehicular networks has been considered as a promising technology to satisfy the increasing demands of computation-intensive and latency-sensitive vehicular applications for intelligent transportation. The existing content caching schemes, when used in vehicular networks, face two distinct challenges: 1) Vehicles connected to an edge server keep moving, making the content popularity varying and hard to predict. 2) Cached content is easily out-of-date since each connected vehicle stays in the area of an edge server for a short duration. To address these challenges, we propose a Mobility-aware Proactive edge Caching scheme based on Federated learning (MPCF). This new scheme enables multiple vehicles to collaboratively learn a global model for predicting content popularity with the private training data distributed on local vehicles. MPCF also employs a Context-aware Adversarial AutoEncoder to predict the highly dynamic content popularity. Besides, MPCF integrates a mobility-aware cache replacement policy, which allows the network edges to add/evict contents in response to the mobility patterns and preferences of vehicles. MPCF can greatly improve cache performance, effectively protect users' privacy and significantly reduce communication costs. Experimental results demonstrate that MPCF outperforms other baseline caching schemes in terms of the cache hit ratio in vehicular edge networks.

With the explosive data growth, an enormous number of computing and networking components (e.g., servers, switches, and wires) are continuously being augmented to data centers. Data center networks (DCNs) - maintaining a high network capacity - must be cost efficient, incrementally scalable, and fault-tolerant. To address these challenges, we propose in this study a new type of DCN architecture referred to asCriso. Different from the existing network architectures,Crisois designed hierarchically and recursively by employing two ports servers and commodity switches.Crisois constructed based on numerous isomorphicpods, each of which leverages external interfaces supplied by switches to connect with neighboring pods. Additionally, apod-based and fault-tolerant routing algorithm is designed to handle multiple failures.Crisohas an array of promising features, including being cost-efficient and delivering a high-network capacity that can be extended to millions of nodes. The analytic results demonstrate thatCrisois significantly superior to the four state-of-the-art data center structures in terms of network capacity, scalability, cost, power consumption, and other static characteristics. Furthermore, the experimental results unveil thatCrisosatisfies the fault-tolerant demands of modern data centers. Compared to the four existing topologies (i.e.,DCell,BCube,FiConn,Fat-Tree) that have been widely investigated,Crisois adroit at maintaining a balanced performance in terms of throughput and latency.

Multi-access edge computing (MEC) aims to extend cloud service to the network edge to reduce network traffic and service latency. A fundamental problem in MEC is how to efficiently offload heterogeneous tasks of mobile applications from user equipment (UE) to MEC hosts. Recently, many deep reinforcement learning (DRL)-based methods have been proposed to learn offloading policies through interacting with the MEC environment that consists of UE, wireless channels, and MEC hosts. However, these methods have weak adaptability to new environments because they have low sample efficiency and need full retraining to learn updated policies for new environments. To overcome this weakness, we propose a task offloading method based on meta reinforcement learning, which can adapt fast to new environments with a small number of gradient updates and samples. We model mobile applications as Directed Acyclic Graphs (DAGs) and the offloading policy by a custom sequence-to-sequence (seq2seq) neural network. To efficiently train the seq2seq network, we propose a method that synergizes the first order approximation and clipped surrogate objective. The experimental results demonstrate that this new offloading method can reduce the latency by up to 25 percent compared to three baselines while being able to adapt fast to new environments.

Mobile social networks (MSNs) provide real-time information services to individuals in social communities through mobile devices. However, due to their high openness and autonomy, MSNs have been suffering from rampant rumors, fraudulent activities, and other types of misuses. To mitigate such threats, it is urgent to control the spread of fraud information. The research challenge is: how to design control strategies to efficiently utilize limited resources and meanwhile minimize individuals' losses caused by fraud information? To this end, we model the fraud information control issue as an optimal control problem, in which the control resources consumption for implementing control strategies and the losses of individuals are jointly taken as a constraint called total cost, and the minimum total cost becomes the objective function. Based on the optimal control theory, we devise the optimal dynamic allocation of control strategies. Besides, a dynamics model for fraud information diffusion is established by considering the uncertain mental state of individuals, we investigate the trend of fraud information diffusion and the stability of the dynamics model. Our simulation study shows that the proposed optimal control strategies can effectively inhibit the diffusion of fraud information while incurring the smallest total cost. Compared with other control strategies, the control effect of the proposed optimal control strategies is about 10% higher.

To provide efficient networking services at the edge of Internet-of-Vehicles (IoV), Software-Defined Vehicular Network (SDVN) has been a promising technology to enable intelligent data exchange without giving additional duties to the resource constrained vehicles. Compared with conventional centralized SDVNs, hybrid SDVNs combine the centralized control of SDVNs and self-organized distributed routing of Vehicular Ad-hoc NETworks (VANETs) to mitigate the burden on the central controller caused by the frequent uplink and downlink transmissions. Although a wide variety of routing protocols have been developed, existing protocols are designed for specific scenarios without considering flexibility and adaptivity in dynamic vehicular networks. To address this problem, we propose an efficient online sequential learning-based adaptive routing scheme, namely, Penicillium reproduction-based Online Learning Adaptive Routing scheme (POLAR) for hybrid SDVNs. By utilizing the computational power of edge servers, this scheme can dynamically select a routing strategy for a specific traffic scenario by learning the pattern from network traffic. Firstly, this paper applies Geohash to divide the large geographical area into multiple grids, which facilitates the collection and processing of real-time traffic data for regional management in controller. Secondly, a new Penicillium Reproduction Algorithm (PRA) with outstanding optimization capabilities is designed to improve the learning effectiveness of Online Sequential Extreme Learning Machine (OS-ELM). Finally, POLAR is deployed in control plane to generate decision-making model (i.e., routing policy). Based on the real-time featured data, this scheme can choose the optimal routing strategy for a specific area. Extensive simulation results show that POLAR is superior to a single traditional routing protocol in terms of packet delivery ratio and latency.

The ever increasing demand for computing resources has led to the creation of hyperscale datacentres with tens of thousands of servers. As demand continues to rise, new technologies must be incorporated to ensure high quality services can be provided without the damaging environmental impact of high energy consumption. Virtualisation technology such as network function virtualisation (NFV) allows for the creation of services by connecting component parts known as virtual network functions (VNFs). By optimising the placement and routing of VNFs this technique can be used to maximally utilise available datacentre resources, to maintain a high quality of service whilst minimising energy consumption. Current research on this problem has focussed on placing VNFs and considered routing as a secondary concern. In this work we argue that the opposite approach, a routing-led approach is preferable. We propose a novel routing-led algorithm and analyse each of the component parts over a range of different topologies on problems with up to 16000 variables and compare its performance against a traditional placement based algorithm. Empirical results show that our routing-led algorithm can produce significantly better solutions to large problem instances on a range of datacentre topologies.

Mobile Cloud Computing (MCC) is regarded as a promising method to increase the data storage and enhance the processing power of mobile devices. Technologies such as Software Defined Networking (SDN) and Network Function Virtualisation (NFV) will be deployed in MCC to simplify the network management and accelerate mobile service deployment. In order to achieve a deeper understanding of future MCC, we developed a comprehensive analytical model to investigate the performance of MCC in the presence of both NFV service chains and SDN networks. The model is capable of capturing the interactions between SDN and NFV when they share the same underlying physical infrastructure. The end-to-end latency is derived for different scales of service deployments and network configurations. Comprehensive simulation experiments are conducted and the results demonstrate that the proposed analytical model corresponds well with the simulation experiments. In addition, we show how the analytical model can be a useful tool to investigate the impact of centralised SDN control on the performance of NFV traffic transmission.

Hashing technique has been widely applied to large-scale image retrieval due to its efficacy in storage and retrieval. However, due to the explosive growth of multimedia data on the web, existing hashing approaches can hardly achieve satisfactory performance on the newly-emerging images of new classes. In this paper, we propose a novel Semantic Augmentation Hashing (SAH) for zero-shot image retrieval. The class semantic embeddings are used as an intermediate space between visual features and binary codes to align visual features to corresponding class semantics and to transfer knowledge from seen classes to unseen classes simultaneously. Extensive experiments conducted on two datasets with different scales demonstrate the superiority of our method as compared against the state-of-the-arts.

Instant delivery has been one of the essential location-based services in modern society. In order to achieve timely and efficient instant delivery, the present works often formulate the problem as a Traveling Salesman Problem and use delivery programming to find a near-optimal solution to the problem. The corresponding solutions, while achieving high efficiency, may leave little room for unexpected delays in each delivery task. Because of the strict deadline requirement for instant delivery, such design may lead to delivery overdue, especially with dynamic traffic and unexpected occasions during the delivery. In this paper, we propose a delay-tolerant Dynamic Scheduling scheme for Instant Delivery (D-SID). By explicitly accounting unexpected delays and exploiting opportunistic relays, the scheme can improve the delivery reliability under dynamic environments. The simulation results show that with D-SID, the overdue delivery ratio is significantly reduced compared to the traditional scheduling that maximizes the number of tasks.

LoRa has attracted much research attention due to its long communication range and low power consumption on end devices. In LoRa networks, the energy consumption on the end devices can be unfair, because some end devices have to use large spreading factors (leading to long transmission time) or large transmission power to reach a far-away gateway, and their energy consumption can be quite different. As a result, these end devices will run out of their batteries much faster, which may significantly reduce the network lifetime. The existing works have focused on the static resource allocation in LoRa networks to achieve energy fairness. However, due to the dynamic wireless environment, the static allocation can be inefficient in practice. In this paper, we develop AdapLoRa, a lifetime-aware dynamic network resource allocation system, to maximize the network lifetime of LoRa networks. AdapLoRa periodically adapts the resource allocation according to the link quality of end devices. A fine-grained network model is developed to capture the link quality variations and network interference. Finally, by considering the adaptation overhead (e.g., energy consumed by end devices to receive the configuration commands), we propose to gradually improve the network lifetime by periodically estimating network lifetime with different resource allocations. We implement AdapLoRa on a LoRa testbed, and the experimental results reveal that AdapLoRa improves the network lifetime by 23.7% compared with the state-of-the-art works.

To cope with the increasing content requests from emerging vehicular applications, caching contents at edge nodes is imperative to reduce service latency and network traffic on the Internet-of-Vehicles (IoV). However, the inherent characteristics of IoV, including the high mobility of vehicles and restricted storage capability of edge nodes, cause many difficulties in the design of caching schemes. Driven by the recent advancements in machine learning, learning-based proactive caching schemes are able to accurately predict content popularity and improve cache efficiency, but they need gather and analyse users' content retrieval history and personal data, leading to privacy concerns. To address the above challenge, we propose a new proactive caching scheme based on peer-to-peer federated deep learning, where the global prediction model is trained from data scattered at vehicles to mitigate the privacy risks. In our proposed scheme, a vehicle acts as a parameter server to aggregate the updated global model from peers, instead of an edge node. A dual-weighted aggregation scheme is designed to achieve high global model accuracy. Moreover, to enhance the caching performance, a Collaborative Filtering based Variational AutoEncoder model is developed to predict the content popularity. The experimental results demonstrate that our proposed caching scheme largely outperforms typical baselines, such as Greedy and Most Recently Used caching.

The rapidly expanding number of Internet of Things (IoT) devices is generating huge quantities of data, but public concern over data privacy means users are apprehensive to send data to a central server for machine learning (ML) purposes. The easily changed behaviors of edge infrastructure that software-defined networking (SDN) provides makes it possible to collate IoT data at edge servers and gateways, where federated learning (FL) can be performed: building a central model without uploading data to the server. FedAvg is an FL algorithm which has been the subject of much study, however, it suffers from a large number of rounds to convergence with non-independent identically distributed (non-IID) client data sets and high communication costs per round. We propose adapting FedAvg to use a distributed form of Adam optimization, greatly reducing the number of rounds to convergence, along with the novel compression techniques, to produce communication-efficient FedAvg (CE-FedAvg). We perform extensive experiments with the MNIST/CIFAR-10 data sets, IID/non-IID client data, varying numbers of clients, client participation rates, and compression rates. These show that CE-FedAvg can converge to a target accuracy in up to 6× less rounds than similarly compressed FedAvg, while uploading up to 3× less data, and is more robust to aggressive compression. Experiments on an edge-computing-like testbed using Raspberry Pi clients also show that CE-FedAvg is able to reach a target accuracy in up to 1.7× less real time than FedAvg.

Driven by the tremendous application demands, the Internet of Things (IoT) systems are expected to fulfill computation-intensive and latency-sensitive sensing and computational tasks, which pose a significant challenge for the IoT devices with limited computational ability and battery capacity. To address this problem, edge computing is a promising architecture where the IoT devices can offload their tasks to the edge servers. Current works on task offloading often overlook the unique task topologies and schedules from the IoT devices, leading to degraded performance and underutilization of the edge resources. In this article, we investigate the problem of fine-grained task offloading in edge computing for low-power IoT systems. By explicitly considering: 1) the topology/schedules of the IoT tasks; 2) the heterogeneous resources on edge servers; and 3) the wireless interference in the multiaccess edge networks, we propose a lightweight yet efficient offloading scheme for multiuser edge systems, which offloads the most appropriate IoT tasks/subtasks to edge servers such that the expected execution time is minimized. To support the multiuser offloading, we also propose a distributed consensus algorithm for low-power IoT devices. We conduct extensive simulation experiments and the results show that the proposed offloading algorithms can effectively reduce the end-to-end task execution time and improve the resource utilization of the edge servers.

Edge computing is a promising technology to empower the Internet of Things (IoT) by providing additional processing ability, where the tasks can be offloaded to the edge servers for efficient computing. To enable easy management and improve the resource utilization of edge computing, network function virtualization (NFV) is often employed to quickly deploy the requested network functions (NFs) for serving front-end devices. Considering that the edge servers are close to the front-end users, the time-varying geographical distribution of users has a significant influence on the NF deployment in the network of edge servers. Based on this observation, we propose a deep-reinforcement-learning (DRL)-based approach for the NF deployment, which has the following two salient features. First, we employ DRL to estimate the underlying wireless features affected by user mobility, which has a direct impact on the task performance in the edge-IoT systems. Second, we implicitly utilize the multiaccess opportunity to deploy the NFs, considering the estimated features and user requests. Compared to the existing works, the proposed work can significantly improve the resource utilization of edge servers as well as the computational efficiency of IoT tasks. The evaluation results obtained from extensive simulation experiments show that our approach can be well adapted to the time-varying user geodistributions and achieve improved performance in terms of both resource utilization of edge servers and task executions of the IoT devices.

Storm surge hazard annually costs hundreds of lives and billions of dollars for damages in coastal countries. Simulating the storm surge events and alerting flood areas in advance is essential to guarantee the safety of citizens and urban infrastructure. However, due to the complexity of the urban environment, the accuracy of simulation faces challenges. By leveraging the facility of the Internet-of-Things (IoT) technique, the urban flood simulation procedure under storm surge hazard can be improved. In this article, targeting a coastal city usually under the threat of the storm surge, a deep-reinforcement-learning-based storm surge flood simulation approach is proposed to simulate the flood situation under the specific level of the storm surge. By analyzing real-time urban flood data and weather data collected by the IoT system, the model of the urban flood can be constructed and refined. A case study based on storm surge took place on July 1, 2019 in Shenzhen and was conducted to evaluate the effectiveness of the proposed model. The results demonstrate that the proposed method can effectively simulate the storm surge flood, and the achieved accuracy is up to 97.22%.

Vehicular edge computing (VEC) is a new computing paradigm that has great potential to enhance the capability of vehicle terminals (VTs) to support resource-hungry in-vehicle applications with low latency and high energy efficiency. In this article, we investigate an important computation offloading scheduling problem in a typical VEC scenario, where a VT traveling along an expressway intends to schedule its tasks waiting in the queue to minimize the long-term cost in terms of a tradeoff between task latency and energy consumption. Due to diverse task characteristics, dynamic wireless environment, and frequent handover events caused by vehicle movements, an optimal solution should take into account both where to schedule (i.e., local computation or offloading) and when to schedule (i.e., the order and time for execution) each task. To solve such a complicated stochastic optimization problem, we model it by a carefully designed Markov decision process (MDP) and resort to deep reinforcement learning (DRL) to deal with the enormous state space. Our DRL implementation is designed based on the state-of-the-art proximal policy optimization (PPO) algorithm. A parameter-shared network architecture combined with a convolutional neural network (CNN) is utilized to approximate both policy and value function, which can effectively extract representative features. A series of adjustments to the state and reward representations are taken to further improve the training efficiency. Extensive simulation experiments and comprehensive comparisons with six known baseline algorithms and their heuristic combinations clearly demonstrate the advantages of the proposed DRL-based offloading scheduling method.

Network slicing, as a key 5G enabling technology, is promising to support with more flexibility, agility, and intelligence towards the provisioned services and infrastructure management. Fulfilling these tasks is challenging, as nowadays networks are increasingly heterogeneous, dynamic and large-dimensioned. This contradicts the dominant network slicing solutions that only customize immediate performance over one snapshot of the system in the literature. Instead, this paper first presents a two-stage slicing optimization model with time-averaged metrics to safeguard the network slicing in the dynamical networks, where prior environmental knowledge is absent but can be partially observed at runtime. Directly solving an off-line solution to this problem is intractable since the future system realizations are unknown before decisions. Therefore, we propose a learning augmented optimization approach with deep learning and Lyapunov stability theories. This enables the system to learn a safe slicing solution from both historical records and run-time observations. We prove that the proposed solution is always feasible and nearly optimal, up to a constant additive factor. Finally, we demonstrate up to 2.6× improvement in the simulation when compared with three state-of-the-art algorithms.

This paper investigates efficient transmission design in a class of multi-user cooperation networks, in which multiple information sources intend to distribute their messages to a sufficient proportion of ambient destinations with the assistance of multiple relays. We apply a relaying scheme that combines non-orthogonal transmission with network coding techniques to balance channel consumption and inter-user interference. The sources and relays are divided into clusters, terminals within each of which are allowed to non-orthogonally access the same channel. A class of finite-field network codes are adopted in the relays. We provide the methods to derive the system transmission error probability and diversity-multiplexing tradeoff (DMT), over Nakagami-m fading channels. Through error probability and finite-SNR DMT analysis for certain clustering strategies, and infinite-SNR DMT analysis for general situations, we show that the considered relaying scheme can notably improve system performance over the conventional approach that demands only orthogonal transmission in network-coded cooperation networks.

The ultimate goal of multiobjective optimization is to help a decision maker (DM) identify solution(s) of interest (SOI) achieving satisfactory tradeoffs among multiple conflicting criteria. This can be realized by leveraging DM's preference information in evolutionary multiobjective optimization (EMO). No consensus has been reached on the effectiveness brought by incorporating preference in EMO (either a priori or interactively) versus a posteriori decision making after a complete run of an EMO algorithm. Bearing this consideration in mind, this article: 1) provides a pragmatic overview of the existing developments of preference-based EMO (PBEMO) and 2) conducts a series of experiments to investigate the effectiveness brought by preference incorporation in EMO for approximating various SOI. In particular, the DM's preference information is elicited as a reference point, which represents her/his aspirations for different objectives. The experimental results demonstrate that preference incorporation in EMO does not always lead to a desirable approximation of SOI if the DM's preference information is not well utilized, nor does the DM elicit invalid preference information, which is not uncommon when encountering a black-box system. To a certain extent, this issue can be remedied through an interactive preference elicitation. Last but not the least, we find that a PBEMO algorithm is able to be generalized to approximate the whole PF given an appropriate setup of preference information.

Multichannel communication is an important means to improve the reliability of low-power Internet-of-Things (IoT) networks. Typically, data transmissions in IoT networks are often required to be delivered before a given deadline, making deadline-driven channel allocation an essential task. The existing works on time-division multiple access often fail to establish channel schedules to meet the deadline requirement, as they often assume that transmissions can be successful within one transmission slot. Besides, the allocation and link estimation incur considerable overhead for the IoT nodes. In this article, we propose an edge-based channel allocation (ECA) for unreliable IoT networks. In ECA, we explicitly consider the impact of allocation sequences and employ a recurrent-neural-network-based channel estimation scheme. We utilize link quality and retransmission opportunities to maximize the packet delivery ratio before deadline. The allocation algorithms are executed on edge servers such that: 1) the channel allocation can be updated more frequently to deal with the wireless dynamics; 2) the allocation results can be obtained in real time; and 3) channel estimation can be more accurate. Extensive evaluation results show that ECA can significantly improve the reliability of deadline-driven IoT networks.

This article extends the promising software-defined networking technology to wireless sensor networks to achieve two goals: 1) reducing the information exchange between the control and data planes, and 2) counterbalancing between the sender's waiting-time and the duplicate packets. To this end and beyond the state-of-the-art, this work proposes an SDN-based architecture, namely MINI-SDN, that separates the control and data planes. Moreover, based on MINI-SDN, we propose MINI-FLOW, a communication protocol that orchestrates the computation of flows and data routing between the two planes. MINI-FLOW supports uplink, downlink and intra-link flows. Uplink flows are computed based on a heuristic function that combines four values, the hops to the sink, the Received Signal Strength (RSS), the direction towards the sink, and the remaining energy. As for the downlink flows, two heuristic algorithms are proposed, Optimized Reverse Downlink (ORD) and Location-based Downlink(LD). ORD employs the reverse direction of the uplink while LD instantiates the flows based on a heuristic function that combines three values, the distance to the end node, the remaining energy and RSS value. Intra-link flows employ a combination of uplink/downlink flows. The experimental results show that the proposed architecture and communication protocol perform and scale well with both network size and density, considering the joint problem of routing and load balancing.

Knowledge of node locations is essential to Wireless Sensor Networks (WSNs) in a wide range of potential applications and their function-dependent network protocols. A number of localization approaches have already been proposed to fulfill this requirement, but few of them can be applicable to mobile sensor networks, due to their low-dimensional embeddings, Euclidean distance representation limitations, frequent node mobility and additional measurement overhead in the network. In this paper, a resilient range-based d-dimensional localization (RRDL) approach is proposed for mobile WSNs to resolve the issues. RRDL distinguishes itself from previous work with three remarkable characteristics: (1) it works for mobile networks embedded in d-dimensional Non-Euclidean space; (2) it allows static ordinary nodes with pre-known locations to act as the alternative anchor nodes, thus tolerating the motion of the original anchor nodes to ensure that other ordinary nodes can obtain their locations in an efficient manner; and (3) it introduces an efficient path-learning approach, with the knowledge of the existing paths, to represent the real network distances as far as possible, thereby eliminating additional measurement overhead and tolerating node mobility in localization. With these characteristics, RRDL exploits the iterative factorization of the random distance matrix, formed by the distances to and from a set of k-hop static neighbors, to assign each current node d-dimensional Non-Euclidean coordinate in a distributed manner. Simulation results demonstrate that RRDL achieves higher localization accuracy with a moderate communication cost in mobile sensor networks.

The sustainable growth of bandwidth has been an inevitable tendency in current Data Center Networks (DCN). However, the dramatic expansion of link capacity offers a remarkable challenge to the transport layer protocols of DCN, i.e., how to converge fast and enable data flow to utilize the high bandwidth effectively. Meanwhile, the new protocol should be compatible to the traditional TCP because the applications with old TCP versions are still widely deployed. Therefore, it is important to achieve a trade-off between the aggressiveness and TCP-friendliness in protocol design. In this article, we first empirically investigate why the existing typical data center TCP variants naturally fail to guarantee both fast convergence and TCP friendliness. Then, we design a new transport protocol for DCN, namely Fast and Friendly Converging (FFC), which makes independent decisions and self-adjustment through retrieving the two-dimensional congestion notification from both RTT and ECN. We further present a mathematic model to analyze its competing behavior and converging process. The results from simulation experiments and real implementation show that FFC can achieve fast convergence, thus benefiting the flow completion time. Moreover, when coexisting with the traditional TCP, FFC also presents a moderate behavior, while introducing trivial deployment overhead only at the end-hosts.

Network simulation is a fundamental service for performance testing and protocol design in wireless networks. Due to the wireless dynamics, it is highly challenging to provide repeatable and reliable simulation results that are comparable to the empirical experimental results. To achieve repeatability for simulation, the existing works focus on reproducing the behaviors on individual links. However, as observed in recent works, individual link behaviors alone are far from enough to characterize the protocol-level performance. As a result, even if the link behaviors can be simulated very closely, these works often fail to simulate the protocol performance with high reliability. In this article, we propose a novel performance-aware simulation approach which can preserve not only the link-level behaviors but also the performance-level behaviors. We first combine the spatial-temporal link diversity to devise an accurate performance model. Based on the model, we then propose a Performance Aware Hidden Markov Model (PA-HMM), where the protocol performance is directly fed into the Markov state transitions. Compared to the existing works, PA-HMM is able to simulate both link-level behaviors and high-level protocol performance. We conduct extensive testbed and simulation experiments with broadcast and anycast protocols. The results show that 1) the proposed model is able to accurately characterize communication performance for both broadcast and anycast and 2) the protocol performance is closely simulated as compared to the empirical results and the PA-HMM based simulation is more repeatable compared to the existing works.

Resource provisioning for cloud computing necessitates the adaptive and accurate prediction of cloud workloads. However, the existing methods cannot effectively predict the high-dimensional and highly-variable cloud workloads. This results in resource wasting and inability to satisfy service level agreements (SLAs). Since recurrent neural network (RNN) is naturally suitable for sequential data analysis, it has been recently used to tackle the problem of workload prediction. However, RNN often performs poorly on learning long-term memory dependencies, and thus cannot make the accurate prediction of workloads. To address these important challenges, we propose a deep Learning based Prediction Algorithm for cloud Workloads (L-PAW). First, a top-sparse auto-encoder (TSA) is designed to effectively extract the essential representations of workloads from the original high-dimensional workload data. Next, we integrate TSA and gated recurrent unit (GRU) block into RNN to achieve the adaptive and accurate prediction for highly-variable workloads. Using real-world workload traces from Google and Alibaba cloud data centers and the DUX-based cluster, extensive experiments are conducted to demonstrate the effectiveness and adaptability of the L-PAW for different types of workloads with various prediction lengths. Moreover, the performance results show that the L-PAW achieves superior prediction accuracy compared to the classic RNN-based and other workload prediction methods for high-dimensional and highly-variable real-world cloud workloads.

Understanding the statistical latency between two groups of hosts in a period of time is of great significance to a wide variety of Internet applications and services, such as Service-Level Agreement (SLA) compliance monitoring and Virtual Network Function (VNF) placement. However, direct latency measurement methods are not always applicable to large-scale situations while the existing indirect methods often incur extra deployment costs or security problems. To address this challenge, we design an indirect method based on widely-distributed clients calledSSL(Surrogate-based method for large-scale Statistical Latency measurement).SSLestimates the latency between two arbitrary hosts using the measured latencies from several selected clients near one end host, which are called the host's surrogates, to the other end host. To overcome the limited capacity of the volatile clients with unstable CPU, memory, and bandwidth resources, we propose an innovative two-step measurement task assignment mechanism forSSLthat can achieve high accuracy measurement results while satisfying the resource constraints simultaneously. Moreover,SSLadopts a sampling technique to reduce the overhead in large-scale measurements, and a resampling technique to determine the confidence interval. Simulation experiments show thatSSLcan achieve more than 90 percent accuracy in most situations with 10 percent client density and 15 percent sampling rate.

The ten papers in this special section are devoted to the most recent developments and research outcomes addressing the related theoretical and practical aspects of computational intelligence solutions in sustainable computing and aims at presenting latest innovative ideas targeted at the corresponding key challenges, either from a methodological or from an application perspective.

Drones can be used for many assistance roles in complex communication scenarios and play as the aerial relays to support terrestrial communications. Although a great deal of emphasis has been placed on the drone-assisted networks, existing work focuses on routing protocols without fully exploiting the drones superiority and flexibility. To fill this gap, this paper proposes a collaborative communication scheme for multiple drones to assist the urban vehicular ad-hoc networks (VANETs). In this scheme, drones are distributed regarding the predicted terrestrial traffic condition in order to efficiently alleviate the inevitable problems of conventional VANETs, such as building obstacle, isolated vehicles, and uneven traffic loading. To effectively coordinate multiple drones, this issue is modeled as a multimodal optimization problem to improve the global performance on a certain space. To this end, a succinct swarm-based optimization algorithm, namely Multimodal Nomad Algorithm (MNA) is presented. This algorithm is inspired by the migratory behavior of the nomadic tribes on Mongolia grassland. Based on the floating car data of Chengdu China, extensive experiments are conducted to examine the performance of the MNA-optimized drone-assisted VANET. The results demonstrate that our scheme outperforms its counterparts in terms of hop number, packet delivery ratio, and throughput.

To achieve better network performance, the cloud service providers are widely deploying the ECN-based transport protocols (i.e., DCTCP) in their data center networks (DCN). In multi-tenant environment, however, the newly introduced ECN-enabled TCP greatly impairs the performance of applications with out-dated and miscon figured TCP stacks. The reason is that the ECN-enabled datacenter switch fails to treat the mixed TCP traffic fairly, causing the distinguished performance gap between the ECN-enabled and ECN-disabled TCPs. This paper proposes DDT (Dual Dynamic Thresholds), an active queue management algorithm (AQM) that aims to achieve the flow-level fairness when the heterogeneous TCP traffic coexists. DDT monitors the switch queue in real time, and dynamically tunes the distance between ECN-marking and packet-dropping thresholds to mitigate the competitiveness difference between the ECN-enabled and ECN-disabled TCP. Our preliminary real implementations and testing results show that DDT elegantly fills the competitiveness gap of heterogeneous TCP traffic without disturbing their own control loops, while only introducing acceptable deployment overhead at the switch.

The last decade has witnessed the rapid development of Internet of Things (IoT). The IoT applications are becoming more and more computation-intensive and latency-sensitive, which pose severe challenges for the resource-constrained IoT devices. To empower the computational ability of the IoT systems, edge computing emerges as a promising approach which allows the resource-constrained devices to offload their tasks to edge servers. A major challenge, which has been overlooked by most existing works on task offloading, is the dependencies among tasks and subtasks, which can have a significant impact on the offloading decisions. Besides, the existing works often consider offloading tasks to specific edge servers, which may underutilize the edge resources in the ultra-dense edge networks. In this paper, we investigate the problem of dependency-aware task offloading in ultra-dense edge networks. Specifically, we explicitly analyze the task dependency as directed acyclic graphs (DAGs) and establish full parallelism between edge servers and IoT devices. We further formulate task offloading as a joint optimization problem for minimizing both task latency and energy consumption. We prove the problem is NP-hard and propose a heuristic algorithm, which guarantees the dependency among subtasks and improves the task efficiency. Simulation experiments demonstrate that the proposed work can effectively reduce the task latency in ultra-dense edge networks.

Vehicular networking is potentially an effective solution to the problems in today's transportation system. However, realizing efficient communications among vehicles with satisfactory reliability and latency requirements is challenging, especially when diverse applications are taken into consideration. In this paper, we investigate a cross-layer energy- efficient transmission design for a class of vehicular communication networks, in which two pairs of vehicle-to-vehicle links non-orthogonally share the available spectrum. Each link desires to deliver two types of messages that can support different delay-limited applications. The periodically- generated heartbeat messages should be transmitted subject to a reliability requirement, and the randomly-appeared sensing messages should be delivered with finite latency. We propose a power control strategy to achieve high energy efficiency, while ensuring the expected quality-of-service requirements, based on both channel state information in the physical layer and queue state information in the media access control layer. Simulation results show that our proposed method notably outperforms conventional methods.

Inspired by mobile edge computing (MEC), vehicular edge computing (VEC) enables vehicle terminals to support resource-hungry on-vehicle applications with significantly lower latency and less energy consumption. In this paper, we investigate the computation offloading problem in a typical VEC scenario, where a vehicle offloads its computation tasks to the VEC servers deployed in the road side unit (RSU) to minimize its long-term user cost. The mobility of the vehicle coupled with the high dynamics of the environment makes the problem particularly difficult. To tackle this challenge, a deep reinforcement learning (DRL) based offloading method is proposed, which approximates the offloading policy (OP) by a deep neural network (DNN) and trains the DNN with the proximal policy optimization (PPO) algorithm without a priori knowledge of the environment dynamics. Extensive simulation experiments and comprehensive comparison with six baseline algorithms demonstrate that it can achieve the lowest user cost in most cases.

In this paper, we propose a novel video coding scheme to significantly reduce the coding complexity and enhance overall coding efficiency in videos acquired by high mobility devices such as unmanned aerial vehicles (UAVs). In order to reduce the encoded data bits and encoding time to facilitate real-time data transmission, as well as minimize the image distortion caused by the jitter of onboard camera, a sensor-assisted global motion estimation (GMV) algorithm is designed to calculate perspective transformation model and global motion vectors, which are used in both the inter-frame coding to improve the coding efficiency and intra-frame coding to reduce block search complexity. We conducted comprehensive simulation experiments on official HM-16.10 codec and the performance results show the proposed method can achieve faster block search by 50% to 60% speedup and lower bitrate by 15% to 30% compared with standard HEVC coding software.

In Software Defined Vehicular Networks (SDVNs), most existing studies of routing consider the vehicular network as a static graph and compute the flow table based on static information. However, a static graph could only contain partial network data. Routing computation based on the static graph could be inefficient because vehicular networks are temporal graphs. Thus, in this paper, we propose a novel routing algorithm based on the Markov model and the temporal graph. Unlike conventional routing algorithms, the proposed algorithm adopts the concept of the temporal graph where every edge has its specific temporal information. We apply the Markov model to predict the future routing of the network and adopt prediction data to get the optimal routing by running the temporal graph optimal path algorithm. A benefit of our proposal is, the proposed algorithm searched on the temporal graph of SDVNs can avoid generating additional routing overhead. Besides, based on the information of the vehicular network which is collected from the data plane, the controller can enhance the Markov model as time flows. By applying the above mechanisms, the flow table (route) could be calculated more precisely to enable efficient vehicular communication. The simulation experiments demonstrate the superiority of the proposed algorithm over its counterparts in high-density vehicular networks.

Software-Defined Vehicular Networks (SDVNs) technology has been attracting significant attention as it can make Vehicular Ad Hoc Network (VANET) more efficient and intelligent. SDVN provides a flexible architecture which can decouple the network management from data transmission. Compared to centralized SDVN, hybrid SDVN is even more flexible and has less overhead. This hybrid technology can eliminate the burden on the central controller by moving regional routing tasks from the central controller to local controllers or vehicular nodes. In the literature, different routing protocols have been reported for SDVNs. However, these existing routing protocols lack flexibility and adaptive approaches to deal with changing and dynamic traffic conditions. Thus, this paper proposes a new software-defined routing method, namely, Novel Adaptive Routing and Switching Scheme (NARSS), deployed in the controller. This adaptive method can dynamically select routing schemes for a specific traffic scenario. To achieve this, this paper firstly presents a method for collecting road network information to describe traffic condition where the method extracts the feature data used to generate the routing scheme switching model. Secondly, we train the feature data through an artificial neural network with high training speed and accuracy. Finally, we use the model as a basis for establishing the NARSS and deploy it in the controller. Simulation results show that the proposed scheme outperforms the single traditional routing protocol in terms of both packet delivery ratio and end-to-end delay.

Due to the ever-changing system states and various user demands, resource allocation in cloud data center is faced with great challenges in dynamics and complexity. Although there are solutions that focus on addressing this problem, they cannot effectively respond to the dynamic changes of system states and user demands since they depend on the prior knowledge of the system. Therefore, it is still an open challenge to realize automatic and adaptive resource allocation in order to satisfy diverse system requirements in cloud data center. To cope with this challenge, we propose an advantage actor-critic based reinforcement learning (RL) framework for resource allocation in cloud data center. First, the actor parameterizes the policy (allocating resources) and chooses continuous actions (scheduling jobs) based on the scores (evaluating actions) from the critic. Next, the policy is updated by gradient ascent and the variance of policy gradient can be significantly reduced with the advantage function. Simulations using Google cluster-usage traces show the effectiveness of the proposed method in cloud resource allocation. Moreover, the proposed method outperforms classic resource allocation algorithms in terms of job latency and achieves faster convergence speed than the traditional policy gradient method.

Unmanned Aerial Vehicles (UAVs) have demonstrated exceptional capabilities in many real-world applications such as remote sensing, emergency medicine delivery and precision agriculture. LTE networks are regarded as key candidates to offer high performance broadband wireless services to support UAV applications and safe deployment. However, the unique features of aerial UAVs including high-altitude manipulation, three-dimension (3D) mobility and rapid velocity changes, pose challenging issues for optimising LTE wireless communications to support UAVs, especially under the severe inter-cell interference generated by UAVs in the sky. To deal with this issue, we propose a novel position-based robust beamforming algorithm to improve the performance of LTE networks to serve UAVs. For obtaining optimal weight vectors that could tolerate Direction-of-Arrival (DoA) estimation errors, we propose a hybrid method to integrate the channel information and UAV flight information to accurately estimate the DoA angle range. In order to validate the performance of the proposed robust beamforming algorithm, we conduct comprehensive simulation experiments under practical configurations. The results show that the proposed robust beamforming algorithm outperforms benchmark Linearly Constrained Minimum Variance (LCMV) beamforming and GPS-based beamforming algorithms.

LoRa has recently become one of the most promising networking technologies for the Internet of Things applications. Distant end devices have to use a low data rate to reach a LoRa gateway, which can cause long in-the-air transmission time and high energy consumption. Compared with the end devices using high data rate, they will drain the batteries much earlier and the network may be broken. Such an energy unfairness can be mitigated by deploying more gateways, since it allows end devices to reach closer gateways with higher data rates. However, multiple gateways may not solve the energy unfairness problem efficiently due to the collision problem caused by the chirp spread spectrum modulation of LoRa networks. Spreading factors of LoRa links can determine both data rate and multiplexing of different transmissions. With more gateways, more end devices may choose low spreading factors and reach closer gateways, which increase the collision probability. In this paper, we propose a networking solution for LoRa networks named EF-LoRa that can achieve fair energy consumption among end devices by carefully allocating different network resources, including frequency channels, spreading factors and transmission power, to achieve fair energy consumption among end devices in LoRa networks. We develop a LoRa network model to study the energy consumption of all the end devices in a network by considering the unique features of LoRa networks, such as LoRaWAN MAC protocol, spreading factors, interference, and the capacity limitation of a LoRa gateway. We formulate the energy fairness problem as an optimization problem and finally propose a greedy resource allocation algorithm to achieve the max-min fairness of energy efficiency in the LoRa networks. Simulation results show that the proposed solution EF-LoRa can improve the energy fairness of legacy LoRa networks by 177.8%.

In order to provide high-quality services, wireless network providers deploy a large number of base stations per unit area and maintain these base stations operating over a long period of time invariably. This situation resulted in tremendous energy waste and economic cost to service providers. Owing to the conflict between energy consumption and economic benefits, simply reducing energy consumption may cut the profits of network providers. In order to effectively balance the Quality-of-Service (QoS), energy consumption, and profits of wireless networks, we propose a new sleeping scheme for base stations by using Tullock Contest. In the proposed game-theoretical framework, each player is a base station which competes for service revenue by providing services while consuming energy. The stations are classified into two categories, running mode and sleeping mode. The eventual sleeping strategy can be obtained by applying Nash equilibrium. The proposed scheme adjusts the number of sleeping stations to balance the energy consumption and profits of wireless network providers with the premise of ensuring user QoS. The performance of the proposed scheme is evaluated and compared under different system configurations and user traffic patterns.

With the various emerging innovative applications, the Internet-of-Things (IoT) systems are expected to fulfill more computation-intensive and latency-sensitive sensing and computational tasks, which pose huge challenges for the IoT devices with limited computational ability and battery capacity. To address this problem, edge computing is a promising architecture where the IoT devices can offload their tasks to the edge servers. Current works on task offloading often overlook the unique task topologies and schedules from the IoT devices, leading to degraded performance and underutilization of the edge resources. In this paper, we investigate the problem of fine-grained task offloading in edge computing for low-power IoT systems. By explicitly considering 1) the topology/schedules of the IoT tasks, 2) the heterogeneous resources on edge servers and 3) the wireless interference in the multi-access edge networks, we propose a lightweight yet efficient offloading scheme for multi-user Edge systems, which offloads the most appropriate IoT tasks/subtasks to edge servers such that the expected execution time is minimized. Both centralized and distributed algorithms are devised in both sparse and dense network scenarios. We conduct extensive simulation experiments and the results show that the proposed offloading algorithms can effectively reduce the end-to-end task execution time and improve the resource utilization of the edge servers.

The openness of indoor WiFi networks makes it prone to spoofing attacks and password leakage/sharing, where undesired users may be able to access the network resources. The fundamental reason is that the actual communication range is much larger than the valid authentication range, leaving undesired users the same chance to access the network from invalid authentication ranges. The existing works exploit various features of wireless signals to identify legitimate/undesired users. Either frequent measurement/learning of signal features or hardware modifications are required. In this paper, we identify visible light (VL) as a good indicator to distinguish the positions of the accessing users due to its frequency diversity. Based on this observation, we propose VL-Auth, a novel Authentication framework based on VL for indoor WiFi networks, which uses the VL features as credentials to authenticate WiFi users. VL-Auth can be easily installed on commercial-off-the-shelf (COTS) devices and do not require frequent measurement/learning of the VL features. We implement VL-Auth with OpenWrt and Android devices. The evaluation results show that compared to the existing works, VL-Auth can accurately identify legitimate/undesired users and the connection delay is also reduced.

Recent advances in traffic engineering offer a series of techniques to address the network problems due to the explosive growth of Internet traffic. In traffic engineering, dynamic path planning is essential for prevalent applications, e.g., load balancing, traffic monitoring and firewall. Application-specific methods can indeed improve the network performance but can hardly be extended to general scenarios. Meanwhile, massive data generated in the current Internet has not been fully exploited, which may convey much valuable knowledge and information to facilitate traffic engineering. In this paper, we propose a learning-based network path planning method under forwarding constraints for finer-grained and effective traffic engineering. We form the path planning problem as the problem of inferring a sequence of nodes in a network path and adapt a sequence-to-sequence model to learn implicit forwarding paths based on empirical network traffic data. To boost the model performance, attention mechanism and beam search are adapted to capture the essential sequential features of the nodes in a path and guarantee the path connectivity. To validate the effectiveness of the derived model, we implement it in Mininet emulator environment and leverage the traffic data generated by both a real-world GEANT network topology and a grid network topology to train and evaluate the model. Experiment results exhibit a high testing accuracy and imply the superiority of our proposal.

Mobile edge computing (MEC) is providing a promising solution for augmenting the computing and storage capacity of mobile devices by exploiting the available resources at the network edge. Among the various Internet of Things (IoT) applications, MEC could help us to narrow the gap between the requirements of IoT applications and the limited resources of IoT devices and to achieve the energy-efficient communication and computing. Importantly, the upper and edge infrastructure of cloud computing should effectively collaborate for executing the complex tasks which are requested by mobile users. In particular, community cloud computing, as a novel computational model for a specific community with common concerns (such as security, compliance, and jurisdiction), can make full use of the spare resources of networked computers to provide the facilities so that the community gains services from them. However, how to allocate the subtasks into community clouds and edge community clouds (cloudlets) is becoming a critical challenge. To tackle this challenge, this paper first proposes a two-layer multi-community-cloud/cloudlet social collaborative paradigm, called 2L-MC3for MEC. Further, we formulate a problem on tasks allocation in community clouds/cloudlets by jointly taking task offloading, tasks and clouds profiles into account. To address this problem, we devise a bi-level programming model for tasks allocation. Extensive simulations are conducted for demonstrating that the proposed approach can achieve the relative global performance for satisfying the each metric comparing to the other approaches.

As the prevalence of computing-intensive and delay-sensitive Internet of Things (IoT) applications, IoT service providers (SP) begin to deploy micro data centers in the edge and offload functions to them. However, more and more complex IoT applications require an ordered sequence of services across geographically distributed infrastructure to fulfil their functions, which poses grand challenges for IoT SP to deploy applications with low costs and high efficiency. To the best of our knowledge, no existing works have studied the deployment for an application with multilevel services (referred to as application deployment with multilevel services (ADMS) problem). To fill in the gap, we formulate the ADMS problem as an optimization problem with the aim of minimizing the overall deployment cost under the latency/computation/storage/bandwidth requirements and the infrastructure capacity limitations. We design a workflow-based heuristic algorithm called AMS, which can determine how many virtual machines (VMs) should be placed for each type of service and where to place them. AMS supports the services to scale up or scale down on demand in real time. Simulation experiments based on real network measurement demonstrate that AMS can reduce the number of deployed VMs by 28.4% and the deployment cost by 33.9% subject to comparable satisfied user ratio.

With the explosive growth of multimedia applications, heterogeneous cellular networks (HetNets) are widely deployed to meet the increasingly impressing demands on communication capacity. However, supporting the massive real-time traffic generated by always-on multimedia applications in HetNets causes enormous energy consumptions. The tradeoff between energy consumptions and profits of service providers while maintaining satisfied quality-of-service (QoS) has become a significant objective. To this end, this paper proposes a novel framework of power rationing in HetNets to achieve maximal profit and guaranteed service performance. A dynamic power rationing strategy that employs Tullock contest is developed to model the power control of multiple cells into a game and solve the contradiction of profits and energy consumption as the tradeoff between QoS and cost. Two principal challenges in gaming, incomplete information, and the curse of dimensionality are resolved by the designed virtual repeated game that adopts the Monte-Carlo method and particle swarm optimization (PSO) to obtain the Nash equilibrium. The equilibrium of power rationing balances the energy consumptions and profits of cells, which ensures the optimal solution for the multimedia service providers and HetNets operators. The experimental results demonstrate that the developed model can serve as an efficient tool for power rationing in multimedia HetNets.

Network function virtualization (NFV) has been considered as a promising technology for future Internet to increase the network flexibility, accelerate the service innovation, and reduce the Capital Expenditures and Operational Expenditures costs through migrating network functions from dedicated network devices to commodity hardware. Recent studies reveal that although this migration of network function brings the network operation unprecedented flexibility and controllability, NFV-based architecture suffers from serious performance degradation compared with traditional service provisioning on dedicated devices. In order to achieve a comprehensive understanding of the service provisioning capability of NFV, this paper proposes a novel analytical model based on Stochastic Network Calculus (SNC) to quantitatively investigate the end-to-end performance bound of the NFV networks. To capture the dynamic and on-demand NFV features, both the non-bursty traffic, e.g., the Poisson process, and the bursty traffic, e.g., the Markov Modulated Poisson Process, are jointly considered in the developed model to characterize the arriving traffic. To address the challenges of resource competition and end-to-end NFV chaining, the property of convolution associativity and leftover service technologies of SNC are exploited to calculate the available resources of the Virtual Network Function nodes in the presence of multiple competing traffic and transfer the complex NFV chain into an equivalent system for performance derivation and analysis. Both the numerical analysis and extensive simulation experiments are conducted to validate the accuracy of the proposed analytical model. Results demonstrate that the analytical performance metrics match well with those obtained from the simulation experiments and numerical analysis. In addition, the developed model is used as a practical and cost-effective tool to investigate the strategies of the service chain design and resource allocations in the NFV networks.

The emerging deployment of large-scale cloud applications incurs significant inter-datacenter traffic, which makes the scarce wide-area bandwidth across data centers become the performance bottleneck. To achieve the desirable network performance, bandwidth guarantee should be provided for the resulting inter-datacenter traffic. However, the existing bandwidth allocation methods mainly focus on intra-datacenter traffic, and cannot achieve the cost-minimizing bandwidth guarantee for inter-datacenter traffic. In this paper, we focus on the bandwidth guarantee problem for inter-datacenter traffic and present a novel bandwidth allocation model. Our model can ensure the bandwidth guarantee, minimize the resulting network cost, and efficiently avoid the potential traffic overload on low cost links. To solve the large-scale optimization problem in our model, we are motivated to develop a distributed algorithm by blending the advantages of alternating direction method of multipliers (ADMM) and the auxiliary variable method. Specifically, we efficiently decompose the optimization problem into many small sub-problems, which are allowed to be processed in a large-scale computing environment, where each server solves a few small sub-problems. We further present a theoretically proved globally, asymptotically stable algorithm to solve these sub-problems. Extensive evaluation results demonstrate that our bandwidth allocation method can effectively realize the bandwidth guarantee for inter-datacenter traffic with reduced network cost and outperforms the prior method PS-L. In particular, the total network cost is reduced by 59.57 percent on average.

Depression is becoming a serious global health problem worldwide, with an increasing number of patients suffering from anxiety and other disorders. Our work aims to provide the appropriate social support (SS) to the prevention of depression for highly anxious undergraduates. We used 1425 undergraduates from 18 universities in China via a cluster random sampling method for the survey on the self-rating anxiety scale, the self-rating depression scale, and the SS scale for anxiety and depression. Based on the collected questionnaire data, we first reveal that the distribution of both anxiety data and depression data follows a Gaussian distribution. Then, a Gaussian mixture model is adopted for clustering these data in terms of anxiety index and depression index. According to the observations extracted from the clusters, the correlation among anxiety, depression, and SS is investigated by a correlation analysis method. Finally, the corresponding moderating effect of SS between anxiety and depression is figured out via the hierarchical multiple regression analysis. The detailed analysis indicates that the high-level SS, such as the help and support from individual's friends or family members, could reduce the risk for depression from highly anxious undergraduates.

The decentralized nature of blockchain technologies can well match the needs of integrity and provenances of evidences collecting in digital forensics (DF) across jurisdictional borders. In this paper, a novel blockchain-based DF investigation framework in the Internet of Things (IoT) and social systems environment is proposed, which can provide proof of existence and privacy preservation for evidence items examination. To implement such features, we present a block-enabled forensics framework for IoT, namely, IoT forensic chain (IoTFC), which can offer forensic investigation with good authenticity, immutability, traceability, resilience, and distributed trust between evidential entitles as well as examiners. The IoTFC can deliver a guarantee of traceability and track provenance of evidence items. Details of evidence identification, preservation, analysis, and presentation will be recorded in chains of block. The IoTFC can increase trust of both evidence items and examiners by providing transparency of the audit train. The use case demonstrated the effectiveness of the proposed method.

Recent advances in microelectronic technologies have enabled the design and proliferation of low-power wireless networks for autonomously monitoring and control of wireless healthcare systems. In order to control and update the network nodes (e.g., bug fixing, command distribution, software update) in the healthcare system, reliable and efficient data dissemination is one of the key building blocks. However, traditional data dissemination relies mainly on the Internet of Things (IoT) nodes and thus much energy is wasted. With the development of 5G communication technologies, especially the mobile edge computing (MEC), it is believed that the edge server will become promising and more pervasively deployed. Despite computational offloading, the edge servers are also capable of communicational offloading. Therefore, to achieve data dissemination in an efficient way, we propose an edge-aided data dissemination system, in which the mobile edge servers are used to disseminate different segments of data objects. After that, IoT nodes exchange segments with each other to collect the entire data objects. In our work, we design the installation mechanism and data propagation protocol to not only ensure integrality of the data objects transmitted but also avoid the transmission conflicts. Furthermore, we design an adaptive protocol to achieve efficient data dissemination for heterogeneous IoT networks. We conduct extensive experiments and large-scale simulations. The results demonstrate that with the help of mobile edge servers, the energy efficiency is significantly improved compared to traditional dissemination approaches.

Data integrity, a core security issue in reliable cloud storage, has received much attention. Data auditing protocols enable a verifier to efficiently check the integrity of the outsourced data without downloading the data. A key research challenge associated with existing designs of data auditing protocols is the complexity in key management. In this paper, we seek to address the complex key management challenge in cloud data integrity checking by introducing fuzzy identity-based auditing, the first in such an approach, to the best of our knowledge. More specifically, we present the primitive of fuzzy identity-based data auditing, where a user's identity can be viewed as a set of descriptive attributes. We formalize the system model and the security model for this new primitive. We then present a concrete construction of fuzzy identity-based auditing protocol by utilizing biometrics as the fuzzy identity. The new protocol offers the property of error-tolerance, namely, it binds with private key to one identity which can be used to verify the correctness of a response generated with another identity, if and only if both identities are sufficiently close. We prove the security of our protocol based on the computational Diffie-Hellman assumption and the discrete logarithm assumption in the selective-ID security model. Finally, we develop a prototype implementation of the protocol which demonstrates the practicality of the proposal.

Special Issue on Intelligent Edge Computing for Cyber Physical and Cloud SystemsCyber Physical Systems (CPS) and Cloud Computing have received tremendous research interest and efforts from both academia and industry.Cloud computing extends the computing and storage ability of CPS and leads to a new paradigm-Cyber Physical and Cloud Systems (CPCS), which is a product of combining CPS and Cloud Computing together.It enables a new breed of applications and services, such as industrial process control, video surveillance, structural health monitoring, and intelligent agriculture, and can fundamentally change the way that people interact with the physical world.However, CPCS face many important challenges.First, the Cloud can neither manage CPS devices directly nor satisfy requirements of real-time.Second, communication bottleneck exists between CPS and the Cloud.Third, new security challenges need to be overcome to accelerate the development of these integrated applications.In particular, edge computing, acting as a new computing scheme, is a promising technology to address these challenges.It extends the Cloud Computing paradigm to the edge of the network.For example, edge computing devices, which are capable of intelligent computing, can reduce the network latency by enabling computation and storage capacity at the edge network.These so-called edge devices can bridge the gap between CPS and Cloud.The intelligent computing and storage on edge devices offer the potential to solve the communication problem, real-time problem, and security problem.The accepted papers represent the urgent needs to be considered in developing an intelligent computing for edge devices and to fill the gap between CPS and Cloud.Moreover, the outcome of this special section exhibits the latest research achievements and state-of-art research results to solve intelligent computing issues for CPCS. INTELLIGENT COMPUTING FOR EDGE DEVICES IN CYBER PHYSICAL AND CLOUD SYSTEMSThrough a peer-review process, we have accepted 10 submissions, and each selected article has received at least two rounds of rigorous reviews.The accepted articles represent activities in areas around the world and propose various theoretical research results and applications on applying Intelligent Edge Computing for Cyber Physical and Cloud Systems in industrial informatics.A brief introduction is provided to each of the articles as follows:The first three articles introduce intelligent computing for edge devices in Cyber Physical and Cloud Systems.In "Deep Reinforcement Learning for Vehicular Edge Computing: An Intelligent Offloading System," Zhaolong Ning et al. construct an intelligent offloading system for vehicular edge computing in the development of smart vehicles, bringing a comfortable and safe environment to drivers and passengers.In this research, the author has investigated two-sided matching scheme and a deep reinforcement learning to solve sub-optimization problems.Numerical results demonstrate that the matching algorithm in the first module can reach 95% of the exhaustive algorithm in different network scenarios and decrease the execution time by more than 90%.For the

The increasing popularization of large-scale online social networks (OSNs) facilitates information sharing. Users are able to diffuse positive and negative information independently owing to the high openness of the OSNs. Due to the intervention of user’s emotions and social relationships, the positive and negative information diffusion exhibits a complicated dynamic coupling diffusion process, in which the negative information diffusion can cause social panic and confusion. However, prior works mainly focus on the diffusion of single type of information. To fill this gap, this paper aims to investigate the dynamic diffusion process of the positive and negative information and control the negative information diffusion timely. Specifically, we first establish a coupling diffusion model to characterize the dynamic diffusion process under the coexistence of positive and negative information, then derive the critical condition for the negative information diffusion and certify the stability of the diffusion model. Furthermore, we propose two collaborative control strategies to persuade and guide users to diffuse the positive information simultaneously. Then, the issue of minimizing the total system costs is transformed to an optimal control problem. Finally, we prove the existence and uniqueness of optimal control solutions and obtain the dynamic distribution of optimal control strategies over time to minimize system costs. The experimental results obtained from two real-world datasets verify the effectiveness of our model and the high efficiency of the collaborative control strategies.

Webpage segmentation is the basic building block for a wide range of webpage analysis methods. The rapid development of Web technologies results in more dynamic and complex webpages, which bring new challenges to this area. To improve the performance of webpage segmentation, we propose a two-stage segmentation method that can combine visual, logic, and semantic features of the contents on a webpage. Specifically, we devise a new model to measure the similarities of the elements on webpages based on both visual layout and logic organization in the first stage, and we propose a novel block regrouping method using semantic statistics and visual positions in the second stage. This two-stage method can effectively conduct webpage segmentation on complicated and dynamic webpages. The performance and accuracy of the method are verified by comparing with two existing webpage segmentation methods. The experiment results show that the proposed method significantly outperforms the existing state of the art in terms of higher precision, recall, and accuracy.

As the volume of data keeps growing rapidly, more and more storage devices, servers and network devices are continuously added into data centers to store, manage and analyze the data. The industry experience indicates that, instead of a huge number of servers added at a time, the data center network also expands gradually by adding a small number of servers from time to time. As a result, how to achieve an incremental scalability is becoming a very important challenge in designing modern data center network architectures in order to maintain the topological properties unchanged when the size of data centers grows. In this paper, we propose a new type of data center network architecture named HSDC (High Scalability Data Center Network Architecture) based on the hypercube network. The HSDC is constructed by using $m$m-port switches and 2-port servers. The fault-tolerant routing algorithm designed in this paper for HSDC can be executed on any vertex and is able to construct a path between any pair of vertices. In order to achieve an incremental scalability, we further propose three types of incomplete HSDC structures that allow gradually adding servers into the structures, while maintaining all the topological properties. The simulation experiments and performance results demonstrate that the throughput of HSDC is comparable to that of Fat-Tree, BCube and DCell. Furthermore, the analysis results indicate that HSDC strikes a good balance among diameter, bisection width, incremental scalability, cost and energy consumption in contrast to the state-of-the-art data center network architectures.

This abstract proposes a time series anomaly detector which 1) makes no assumption about the underlying mechanism of anomaly patterns, 2) refrains from the cumbersome work of threshold setting for good anomaly detection performance under specific scenarios, and 3) keeps evolving with the growth of anomaly detection experience. Essentially, the anomaly detector is powered by the Recurrent Neural Network (RNN) and adopts the Reinforcement Learning (RL) method to achieve the self-learning process. Our initial experiments demonstrate promising results of using the detector in network time series anomaly detection problems.

Simultaneous wireless information and power transfer (SWIPT) offers novel designs that could enhance the sustainability and resilience of communication systems. Due to the very limited receiving power from radio frequency (RF) signals, optimal splitting strategies play an essential role for many SWIPT systems. This paper investigates optimal power splitting from the outage perspective by formulating the power, information and joint outage performance using a Markov chain, and studying the boundary conditions for achieving an energy- neutral state. Our results show that: 1)the power splitting factor is the key factor of intrinsic trade-off between power and information outage; and 2) the proposed polynomial method can obtain the optimal power splitting factor which leads to the minimum joint outage probability.

Content caching is a promising approach in edge computing to cope with the explosive growth of mobile data on 5G networks, where contents are typically placed on local caches for fast and repetitive data access. Due to the capacity limit of caches, it is essential to predict the popularity of files and cache those popular ones. However, the fluctuated popularity of files makes the prediction a highly challenging task. To tackle this challenge, many recent works propose learning based approaches which gather the users' data centrally for training, but they bring a significant issue: users may not trust the central server and thus hesitate to upload their private data. In order to address this issue, we propose a Federated learning based Proactive Content Caching (FPCC) scheme, which does not require to gather users' data centrally for training. The FPCC is based on a hierarchical architecture in which the server aggregates the users' updates using federated averaging, and each user performs training on its local data using hybrid filtering on stacked autoencoders. The experimental results demonstrate that, without gathering user's private data, our scheme still outperforms other learning-based caching algorithms such as m-epsilon-greedy and Thompson sampling in terms of cache efficiency.

The dramatic expansion of link capacity in current data center network causes remarkable challenges to the design of new transport layer protocol, that is, how to converge as fast as possible to help data flow effectively utilize the high bandwidth. Meanwhile, the new protocol should be friendly to the traditional TCP because the non-cooperating applications with old TCP versions are widely existing. Therefore, it is important to achieve a trade-off between the aggressiveness and TCP-friendliness in protocol design. In this paper, we first empirically study why the existing typical data center TCP variants naturally fail to guarantee both fast convergence and TCP friendliness. Then, we design FFC, a transport protocol that makes independent decisions and self-adjustment through retrieving the two-dimensional congestion notification from the RTT and ECN. The results of simulation experiments and real implementations show that the fast convergence of FFC leads to the lower flow completion time compared with DX and DCTCP. Meanwhile, when coexisting with the traditional TCP, FFC also presents a moderate competitiveness, while introducing trivial deployment overhead only at the end hosts.

Convex hull analysis is a key research tool under the broad umbrella of machine learning and finds applications in various domains. However, due to the fact that traditional convex hull analysis usually targets low-dimensional space and just roughly estimates the shape of a dataset, its capability in describing general datasets is greatly limited. In this paper, we investigate the problem of convex hull approximation in high-dimensional space and propose to approximate the convex hull through Semi-Nonnegative Matrix Factorization (Semi-NMF). The novel problem formulation enables the utilization of the kernel trick and makes convex hull analysis readily applicable to general data description tasks, such as one-class classification and clustering. The empirical experiments show that our method successfully describes the convex hull with the approximated extreme points and achieves competitive results in both one-class classification and clustering tasks.

Wireless network simulation is a fundamental service aiming at providing controlled and repeatable environment for protocol design, performance testing, etc. The existing simulators focus on reproducing the packet behaviors on individual links. However, as observed in some recent works, individual link behaviors alone are not enough to characterize the protocol performance. As a result, while the existing works can mimic the link behaviors very closely, they often fail to simulate protocol level performance. In this paper, we propose a novel performance-aware simulation approach which can preserve not only the link-level behaviors but also the performance-level behaviors. We first devise an accurate performance model by combining link quality and the spatial-temporal link correlation. Based on the performance modeling, we then propose a Performance Aware Hidden Markov Model (PA-HMM), where the protocol performance is directly fed into the Markov state transitions. PA-HMM is able to simulate both link-level behaviors and high-level protocol performance. We conduct extensive testbed and simulation experiments with broadcast and anycast protocols. The results show that compared to the state-of-the-art work, 1) the performance model is able to accurately characterize wireless communication performance and 2) the protocol performance is closely simulated as compared to the empirical results.

The recent advances in microelectronics and communications have led to the development of large-scale Internet of Things (IoT) networks, where tremendous sensory data is generated and needs to be processed. To support realtime processing for large-scale IoT, deploying edge servers with storage and computational capability is a promising approach. In this paper, we carefully analyze the impacting factors and key challenges for edge node (EN) deployment. We then propose a novel three-phase deployment approach which considers both traffic diversity and the wireless diversity of IoT. The proposed work aims at providing real-time processing service for the IoT network and reducing the required number of ENs. We conducted extensive simulation experiments, the results show that compared to the existing works that overlooked the two kinds of diversities, the proposed work greatly reduces the number of ENs and improves the throughput between IoT and ENs.

As a key enabling technology for 5G network softwarization, network function virtualization (NFV) provides an efficient paradigm to optimize network resource utility for the benefits of both network providers and users. However, the inherent network dynamics and uncertainties from 5G infrastructure, resources, and applications are slowing down the further adoption of NFV in many emerging networking applications. Motivated by this, in this paper, we investigate the issues of network utility degradation when implementing NFV in dynamic networks, and design a proactive NFV solution from a fully stochastic perspective. Unlike existing deterministic NFV solutions, which assume given network capacities and/or static service quality demands, this paper explicitly integrates the knowledge of influential network variations into a two-stage stochastic resource utilization model. By exploiting the hierarchical decision structures in this problem, a distributed computing framework with two-level decomposition is designed to facilitate a distributed implementation of the proposed model in large-scale networks. The experimental results demonstrate that the proposed solution not only improves 3~5 folds of network performance, but also effectively reduces the risk of service quality violation.

With the rapidly increasing popularity of economic activities, a large amount of economic data is being collected. Although such data offers super opportunities for economic analysis, its low-quality, high-dimensionality and huge-volume pose great challenges on efficient analysis of economic big data. The existing methods have primarily analyzed economic data from the perspective of econometrics, which involves limited indicators and demands prior knowledge of economists. When embracing large varieties of economic factors, these methods tend to yield unsatisfactory performance. To address the challenges, this paper presents a new framework for efficient analysis of high-dimensional economic big data based on innovative distributed feature selection. Specifically, the framework combines the methods of economic feature selection and econometric model construction to reveal the hidden patterns for economic development. The functionality rests on three pillars: (i) novel data pre-processing techniques to prepare high-quality economic data, (ii) an innovative distributed feature identification solution to locate important and representative economic indicators from multidimensional data sets, and (iii) new econometric models to capture the hidden patterns for economic development. The experimental results on the economic data collected in Dalian, China, demonstrate that our proposed framework and methods have superior performance in analyzing enormous economic data.

We investigate the achievable sum degrees of freedom (DoF) in a class of single-antenna multi-user multi-hop relay networks. The networks consist of multiple information sources and destinations, without direct signal propagation link between them, so that multiple layers of relays are deployed to assist in information delivery. We consider the situation that relays are unable to shield their receptions from the harmful self-interference and from the interference generated by other relays. Hence, ideal full-duplex relaying is not applicable. Utilizing half-duplex decode-and-forward relays, a cluster successive relaying (CSR) transmission scheme is adopted to conduct message transmission. The CSR scheme divides each layer of relays into two successively activated relay clusters to compensate the extra channel consumption demanded by the half-duplex operation. We propose two interference alignment strategies to deal with the interference issues. By properly clustering the relays in each layer, we find the asymptotically achievable sum DoF, subject to time-varying and frequency-selective fading, respectively. These results can lead to new lower bounds for the available DoF in the considered class of multi-user multi-hop networks.

Rather than a whole Pareto-optimal front, which demands too many points (especially in a high-dimensional space), the decision maker (DM) may only be interested in a partial region, called the region of interest (ROI). In this case, solutions outside this region can be noisy to the decision-making procedure. Even worse, there is no guarantee that we can find the preferred solutions when tackling problems with complicated properties or many objectives. In this paper, we develop a systematic way to incorporate the DM's preference information into the decomposition-based evolutionary multiobjective optimization methods. Generally speaking, our basic idea is a nonuniform mapping scheme by which the originally evenly distributed reference points on a canonical simplex can be mapped to new positions close to the aspiration-level vector supplied by the DM. By this means, we are able to steer the search process toward the ROI either directly or interactively and also handle many objectives. Meanwhile, solutions lying on the boundary can be approximated as well given the DM's requirements. Furthermore, the extent of the ROI is intuitively understandable and controllable in a closed form. Extensive experiments on a variety of benchmark problems with 2 to 10 objectives, fully demonstrate the effectiveness of our proposed method for approximating the preferred solutions in the ROI.

Small to medium enterprises (SMEs), particularly those whose business is focused on developing innovative produces, are limited by a major bottleneck in the speed of computation in many applications. The recent developments in GPUs have been the marked increase in their versatility in many computational areas. But due to the lack of specialist GPUprogramming skills, the explosion of GPU power has not been fully utilized in general SME applications by inexperienced users. Also, the existing automatic CPU-to-GPU code translators are mainly designed for research purposes with poor user interface design and are hard to use. Little attentions have been paid to the applicability, usability, and learnability of these tools for normal users. In this paper, we present an online automated CPU-to-GPU source translation system (GPSME) for inexperienced users to utilize the GPU capability in accelerating general SME applications. This system designs and implements a directive programming model with a new kernel generation scheme and memory management hierarchy to optimize its performance. A web service interface is designed for inexperienced users to easily and flexibly invoke the automatic resource translator. Our experiments with nonexpert GPU users in four SMEs reflect that a GPSME system can efficiently accelerate real-world applications with at least 4× and have a better applicability, usability, and learnability than the existing automatic CPU-to-GPU source translators.

Effectively monitoring maritime environments has become a vital problem in maritime applications. Traditional methods are not only expensive and time consuming but also restricted in both time and space. More recently, the concept of an industrial wireless sensor network (IWSN) has become a promising alternative for monitoring next-generation intelligent maritime grids, because IWSNs are cost-effective and easy to deploy. This paper focuses on solving the issue of 3-D IWSN deployment in a 3-D engine room space of a very large crude-oil carrier and also considers numerous power facilities. To address this 3-D IWSN deployment problem for maritime applications, a 3-D uncertain coverage model is proposed that uses a modified 3-D sensing model and an uncertain fusion operator. The deployment problem is converted into a multiobjective optimization problem that simultaneously addresses three objectives: coverage, lifetime, and reliability. Our goal is to achieve extensive coverage, long network lifetime, and high reliability. We also propose a distributed parallel cooperative coevolutionary multiobjective large-scale evolutionary algorithm for maritime applications. We verify the effectiveness of this algorithm through experiments by comparing it with five state-of-the-art algorithms. Numerical results demonstrate that the proposed method performs most effectively both in optimization performance and in minimizing the computation time.

Cyber-physical Internet of things system (CPIoTS), as an evolution of Internet of things (IoT), plays a significant role in industrial area to support the interoperability and interaction of various machines (e.g., sensors, actuators, and controllers) by providing seamless connectivity with low bandwidth requirement. The fifth generation (5G) is a key enabling technology to revolutionize the future of industrial CPIoTS. In this paper, a communication framework based on 5G is presented to support the deployment of CPIoTS with a central controller. Based on this framework, multiple sensors and actuators can establish communication links with the central controller in full-duplex mode. To accommodate the signal data in the available channel band, the resource allocation problem is formulated as a mixed integer nonconvex programming problem, aiming to maximize the sum energy efficiency of CPIoTS. By introducing the transformation, we decompose the resource allocation problem into power allocation and channel allocation. Moreover, we consider an energy-efficient power allocation algorithm based on game theory and Dinkelbach's algorithm. Finally, to reduce the computational complexity, the channel allocation is modeled as a three-dimensional matching problem, and solved by iterative Hungarian method with virtual devices (IHM-VD). A comparison is performed with well-known existing algorithms to demonstrate the performance of the proposed one. The simulation results validate the efficiency of our proposed model, which significantly outperforms other benchmark algorithms in terms of meeting the energy efficiency and the QoS requirements.

Traffic management in roads is one of the major challenges faced in developing efficient intelligent transportation systems. Recently, wireless networks have received significant attention for tackling this challenge. However, wireless technologies face the well-known spectrum scarcity problem due to the explosive demand for radio resources. To overcome this challenge, this study presents a novel intelligent traffic control system, utilizing the unused spectrum. Unlike existing works, the spectrum owners in this study hire free spectrum to drivers. The hired spectrum is deployed to build a short-range cost-effective wireless communication for monitoring traffic and enabling drivers to exchange warning messages, and thus enhancing road safety. Our objectives include minimizing crash probability, utilizing unused spectrum, and enabling spectrum owners to generate extra revenue. Numerical analysis demonstrates the capability of our approach to minimize the crash probability among vehicles under different operating road conditions.

Geographic routing has been considered as an attractive approach for resource-constrained wireless sensor networks (WSNs) since it exploits local location information instead of global topology information to route data. However, this routing approach often suffers from the routing hole (i.e., an area free of nodes in the direction closer to destination) in various environments such as buildings and obstacles during data delivery, resulting in route failure. Currently, existing geographic routing protocols tend to walk along only one side of the routing holes to recover the route, thus achieving suboptimal network performance such as longer delivery delay and lower delivery ratio. Furthermore, these protocols cannot guarantee that all packets are delivered in an energy-efficient manner once encountering routing holes. In this paper, we focus on addressing these issues and propose an energy-aware dual-path geographic routing (EDGR) protocol for better route recovery from routing holes. EDGR adaptively utilizes the location information, residual energy, and the characteristics of energy consumption to make routing decisions, and dynamically exploits two node-disjoint anchor lists, passing through two sides of the routing holes, to shift routing path for load balance. Moreover, we extend EDGR into threedimensional (3D) sensor networks to provide energy-aware routing for routing hole detour. Simulation results demonstrate that EDGR exhibits higher energy efficiency, and has moderate performance improvements on network lifetime, packet delivery ratio, and delivery delay, compared to other geographic routing protocols in WSNs over a variety of communication scenarios passing through routing holes. The proposed EDGR is much applicable to resource-constrained WSNs with routing holes.

In the current cloud business environment, the cloud provider (CP) can provide a means for offering the required quality of service (QoS) for multiple classes of clients. We consider the cloud market where various resources such as CPUs, memory, and storage in the form of Virtual Machine (VM) instances can be provisioned and then leased to clients with QoS guarantees. Unlike existing works, we propose a novel Service Level Agreement (SLA) framework for cloud computing, in which a price control parameter is used to meet QoS demands for all classes in the market. The framework uses reinforcement learning (RL) to derive a VM hiring policy that can adapt to changes in the system to guarantee the QoS for all client classes. These changes include: service cost, system capacity, and the demand for service. In exhibiting solutions, when the CP leases more VMs to a class of clients, the QoS is degraded for other classes due to an inadequate number of VMs. However, our approach integrates computing resources adaptation with service admission control based on the RL model. To the best of our knowledge, this study is the first attempt that facilitates this integration to enhance the CP's profit and avoid SLA violation. Numerical analysis stresses the ability of our approach to avoid SLA violation while maximizing the CP's profit under varying cloud environment conditions.

With continually increased attention on electric vehicles (EVs) due to environment impact, public charging stations (CSs) for EVs will become common. However, due to the limited electricity of battery, EV drivers may experience discomfort for long charging waiting time during their journeys. This often happens when a large number of (on-the-move) EVs are planning to charge at the same CS, but it has been heavily overloaded. With this concern, in an EV charging management system, we focus on CS-selection decision making and propose a scheme to manage EVs' charging plans, to minimize drivers' trip duration through intermediate charging at CSs. The proposed scheme jointly considers EVs' anticipated charging reservations (including arrival time and expected charging time) and parking duration at CSs. Furthermore, by tackling mobility uncertainty that EVs may not reach their planned CSs on time (due to traffic jams on the road), a periodical reservation updating mechanism is designed to adjust their charging plans. Results under the Helsinki city scenario with realistic EV and CS characteristics show the advantage of our proposal, in terms of minimized drivers' trip duration, as well as charging performance at the EV and CS sides.

Internet of Things (IoT) technology offers opportunities to monitor lifelogging data by a variety of assets, like wearable sensors, mobile apps, etc. But due to heterogeneity of connected devices and diverse human life patterns in an IoT environment, lifelogging personal data contains huge uncertainty and are hardly used for healthcare studies. Effective validation of lifelogging personal data for longitudinal health assessment is demanded. In this paper, lifelogging physical activity (LPA) is taken as a target to explore how to improve the validity of lifelogging data in an IoT enabled healthcare system. A rule-based adaptive LPA validation (LPAV) model, LPAV-IoT, is proposed for eliminating irregular uncertainties (IUs) and estimating data reliability in IoT healthcare environments. A methodology specifying four layers and three modules in LPAV-IoT is presented for analyzing key factors impacting validity of LPA. A series of validation rules are designed with uncertainty threshold parameters and reliability indicators and evaluated through experimental investigations. Following LPAV-IoT, a case study on a personalized healthcare platform myhealthavatar connecting three state-of-the-art wearable devices and mobile apps are carried out. The results reflect that the rules provided by LPAV-IoT enable efficiently filtering at least 75% of IU and adaptively indicating the reliability of LPA data on certain condition of IoT environments.

With high variability and correlation in arrival rates and packet sizes, multimedia traffic places a great strain on Wireless Local Area Networks (WLANs) towards provision of satisfactory Quality- of-Service (QoS). Most existing performance models for wireless networks are restricted to unrealistic assumptions where specific traffic characteristics of burstiness, correlation and self-similarity are ignored. This paper proposes an original analytical model as a cost-effective tool to evaluate the performance of WLANs in the presence of heterogeneous multimedia traffic, capturing the burstiness, correlation and self- similarity characteristics using Batch Markovian Arrival Process (BMAP). The model derives important QoS metrics in terms of throughput, end- to-end delay and frame loss probability. Analytical results validated through extensive simulations reveal the degrading effect of burstiness, correlation and heterogeneity of traffic sources on the QoS performance of WLANs.

Information-centric networking (ICN) is an emerging paradigm that decouples content from the host to achieve fast and cost-efficient communication and content distribution in the future Internet. A key feature of ICN is the deployment of ubiquitous in-network caching to speed up service delivery and improve network resource utilisation. ICN caching has been widely studied in terms of caching strategies and caching performance. However, the economic aspect of ICN has received marginal consideration so far, although it is vital to understand the potential cost- efficiency of ICN before its wide deployment in service provider network. To address this issue, we propose a cost-aware caching scheme to study the Quality-of-Service (QoS) and cost of ICN and investigate the inner association between them. Two new models are designed to characterise the cost and QoS of ICN with arbitrary topology under heterogeneous bursty content requests. A multi- objective evolution algorithm is adopted to find the optimal cache resource allocation. Numerical results show the effectiveness of the proposed scheme in achieving cost- efficiency and QoS guarantee in ICN caching.

Summary Monitoring video of city surveillance camera plays an important role in public security and disaster relief, which is often used by first responder teams, such as firefighters and police officers. The first responders in emergency situations require consistent connection with one another and request the remote real‐time monitoring video for effective cooperation and coordination. However, the capacity and privacy of public wireless networks fail to satisfy the requirements in many emergency scenarios, which often leads to exceptionally high traffic loads and insecurity. Device‐to‐device (D2D) communications have been deemed a key solution for this problem, as responders can use D2D links for traffic offloading and secure communications. To investigate the D2D‐based solution for public safety video sharing, this paper focuses on the Focus Geographical Area (FGA) video consisting of multiple camera streams requiring higher bandwidth consumption than that of the traditional single‐camera stream, which attracts a large number of contents delivery requests in emergency situations. This paper develops a new Traffic Burden Switching Markovian (TBSM) model to evaluate the performance of transmitting real‐time FGA video in wireless networks with D2D communications. First, a novel D2D area model is introduced to characterize link‐switching in wireless D2D communication networks. Based on the proposed D2D area model, the state and transition matrix of TBSM model are then derived by jointly considering user mobility, link‐switching, and FGA video view‐switching. Thereafter, some key performance metrics including system offloading ratio, D2D link‐switching ratio, and view‐switching ratio are derived on the basis of coverage probability and ergodic rate. The performance results show the significant varying performance among D2D areas with different geographical locations in D2D enabled wireless networks, which is referred to as multi‐D2D‐area diversity. The excellent match between simulation and model results validates the accuracy of the TBSM model, which can be used to provide guidelines for the deployment and optimization of future wireless video networks with D2D communications.

Twitter spam has become a critical problem nowadays. Recent works focus on applying machine learning techniques for Twitter spam detection, which make use of the statistical features of tweets. In our labeled tweets data set, however, we observe that the statistical properties of spam tweets vary over time, and thus, the performance of existing machine learning-based classifiers decreases. This issue is referred to as “Twitter Spam Drift”. In order to tackle this problem, we first carry out a deep analysis on the statistical features of one million spam tweets and one million non-spam tweets, and then propose a novel Lfun scheme. The proposed scheme can discover “changed” spam tweets from unlabeled tweets and incorporate them into classifier's training process. A number of experiments are performed to evaluate the proposed scheme. The results show that our proposed Lfun scheme can significantly improve the spam detection accuracy in real-world scenarios.