The integrated satellite-terrestrial network (ISTN) with inter-satellite free space optical (FSO) links and satellite-to-ground (S2G) radio frequency (RF) links is becoming an important enabler for the Internet of Things (IoT). However, investigating the performance of the ISTN remains several challenges, i.e., the high mobility and long propagation delays of S2G links, and the highly correlated line-of-sight S2G channels. To address these challenges, we propose a hybrid RF/FSO cooperative satellite-terrestrial communication system that integrates the space time block code with cooperative transmission to enhance the coverage probability and communication reliability of satellite downlink transmission. We model the inter-satellite FSO channels by considering pointing and tracking errors, and the S2G RF channels using the shadowed-Rician fading model. Subsequently, we derive the probability density function and cumulative distribution function for both RF/FSO signal-to-noise ratio (SNR) under channel estimation errors and the sum of two RF SNRs from the same distribution family. Finally, for the proposed system, closed-form expressions of the outage probability (OP) and the upper bound for the average bit error probability (BEP) are derived. The proposed system outperforms SISO and MISO systems by reducing average BEP, outage probability, and robustness to channel estimation errors.

In this paper, we propose a novel generative artificial intelligence (GAI)-aided approach to address the quality of experience (QoE)-aware resource allocation for reconfigurable intelligent surface (RIS)-assisted digital twin (DT) interactions with uncertain evolutions. In the considered system, mobile users interact with a DT model, referring to the high-fidelity and interactive virtual counterpart of a physical entity, hosted by a DT server deployed on a wireless base station via the assistance of an RIS, for gaining DT services, such as real-time monitoring and predictive analytics. Noted that DT interactions involve round-trip communications with both uplink and downlink, and concern not only objective performance but also subjective experience. As such, we formulate an optimization problem for RIS-assisted DT interactions, aiming to maximize the sum of all mobile users' mixed objective and subjective QoE, by jointly determining the phase shift marix, receive/transmit beamforming matrices, feedback signal rendering resolution and computing resource configuration. Further taking into account the DT model's uncertain evolutions and the resulted variations of the DT scene that mobile users engage in, we extend the resource allocation problem to a series of scene-specific ones. To obtain a generalized approach with low complexity, avoiding to re-solve each scene-specific problem whenever the engaged DT scene changes, we develop a GAI-aided approach, called prompt-guided decision transformer integrated with zero-forcing optimization (PG-ZFO). Specifically, in PG-ZFO, we first reformulate each scene-specific problem into a Markov decision process (MDP). Then, we design a “decision-making trajectory” based prompt to capture the scene-specific information and extend the traditional decision transformer to a prompt-guided decision transformer with strong generalization. On top of that, a zero-forcing (ZF)-based optimization algorithm is integrated to help derive high-dimensional decisions, i.e., beamforming matrix, along with the offline training and online execution of PG-ZFO. Simulations show the effectiveness of the proposed approach, and demonstrate its superiority over counterparts, i.e., rigid optimization method and decision transformer without prompt.

Aiming to provide high-fidelity and real-time virtual replicas, a digital twin (DT) model must be dynamically updated to precisely characterize the evolution of physical objects. Unlike the existing work, this paper studies a novel edge-cloud collaborative DT update framework with adaptive model splitting and reliable crowdsourcing under uncertain data distortions. Specifically, we consider that a global DT model can be split into arbitrary subsets of its elementary components (DT units), re-forming disjoint partial-DTs. Each partial-DT is constructed on distributed edge servers (ESs) by model training using the locally collected feature data. To enhance the system reliability, being more robust against uncertain data distortions that widely occur in practice, we further improve partial-DT constructions via crowdsourcing. In other words, each partial-DT is simultaneously trained by multiple ESs, i.e., an ES crowd, with one coordinator ES intermediately aggregating all models from participating ESs into a unified one. Then, the cloud collects and integrates partial-DTs from ES crowds to update the global DT. We formulate an online joint optimization problem to adaptively determine partial-DT splitting and ES crowdsourcing across different DT evolution periods or frames, with the objective of maximizing the long-term physical-virtual mapping accuracy. To this end, we first study a simplified short-term problem in each frame, modeled as a Bayesian coalition formation game (BCFG). We then develop an uncertainty-aware crowd formation algorithm based on a particularly established believe function to solve the BCFG for short-term optimal partial-DT assignment and coordinator ES selection, given any partial-DT splitting decisions. Moreover, we modify the BCFG to accommodate dynamic settings and design a deep reinforcement learning-based algorithm integrated with this modified BCFG, called DBC. The DBC algorithm extends the short-term solution to a long-term one, which jointly and dynamically optimizes partial-DT splitting and ES crowdsourcing, thereby addressing the original problem. Simulations show the effectiveness of the introduced dynamic DT update framework, and demonstrate the superiority of the proposed DBC algorithm over counterparts in terms of increasing the average DT update accuracy while reducing the associated costs.

Although Federated Learning (FL) can enable advanced autonomous driving via leveraging massive distributed data in vehicular networks, vehicle mobility causes frequent connection interruptions, hindering the FL process. In this paper, we propose a novelMobility-AwareVehicularFL(MAVFL) scheme, which can accelerate the training process in dynamic vehicular networks via adaptive vehicle selection and sparse training. Specifically, the MAVFL dynamically selects participating vehicles based on their locations and training loss. By incorporating adaptive model sparsification, the proposed scheme dynamically proceeds with sparse masks during vehicle local training, thereby reducing communication overhead while preserving model accuracy. We conduct a rigorous convergence analysis to uncover how vehicle mobility and model sparsification affect convergence rate. Furthermore, we formulate an optimization problem to accelerate the training process, which jointly optimizes vehicle selection, sparsification ratio, and bandwidth allocation to minimize training delay. To solve the problem, we employ the Lyapunov optimization method to decouple the long-term problem into a series of instantaneous subproblems. Next, a generalized Benders decomposition method structures the original problem into a master subproblem for vehicle selection and a primal subproblem for bandwidth allocation and sparsification ratio selection. The optimal solutions are derived via alternating iterations between these problems. Extensive simulation results based on the SUMO simulator demonstrate that the MAVFL accelerates model convergence by up to 14% and reduces communication overhead by up to 26% while preserving model accuracy, as compared to the state-of-the-art benchmarks.

The increasing deployment of mobile robots in dynamic outdoor environments necessitates robotic systems capable of maintaining reliability amidst fluctuating wireless connectivity. While the Robot Operating System (ROS) has established itself as the de facto standard for such networked robotics, its abstraction of communication as an opaque, besteffort utility creates a critical bottleneck: it fails to leverage physical layer (PHY) information, resulting in degraded performance and unreliable execution in fluctuating networks. To address this, this paper presents MobileROS, a wireless-native robot operating system that transforms wireless communication from an external service into a core system resource. Grounded in the Symbiotic Paradigm, MobileROS establishes a bidirectional exchange where network conditions inform robotic decisions and mission requirements guide network resource allocation. Based on service mesh principles and domain-driven design, our architecture implements a Hub-Engines-Cells (HEC) model. It features a central Hub for global optimization, three specialized engines (the Radio Information Engine, the Cross Domain Engine, and the Physical Adaptive Engine) for crosslayer intelligence, and distributed Cells as functional units. A key mechanism, Application-Driven Bidirectional Dynamic Slicing, allows robots to actively reconfigure network resources based on semantic urgency, transforming the robot from a passive observer into an active network controller. We systematically evaluate MobileROS across three cities (London, Hong Kong, and Shenzhen) in five scenarios: distributed visual SLAM, cross-domain LiDAR perception, V2X autonomous driving, hybrid multi-robot collaboration against WebRTC baselines, and partition recovery validating CAP-theorem-aware failsafe mechanisms. Results demonstrate that MobileROS maintains significantly more stable performance than standard ROS in mobile wireless deployments.We provide implementation details athttps://github.com/MobileROS.

In this paper, we investigate task offloading and computing in an urban mobile edge computing (MEC) system assisted by an aerial intelligent reflecting surface (AIRS). To enhance information freshness while saving energy, we formulate a joint optimization problem to minimize the weighted sum of average age of information (AoI) and total energy consumption by jointly optimizing task offloading decisions, resource allocation, and AIRS configuration including its deployment position, phase shifts, and panel size, subject to offloading quality and computing deadline constraints. To tackle the resulting mixed-integer and nonconvex problem, we develop a hierarchical optimization framework based on the objective priority and variable coupling relations. Under this framework, the problem is solved in two stages using quadratic penalty, numerical analysis, and convex optimization techniques. Specifically, an AoI-aware task offloading policy is first designed to maximize information freshness; subsequently, given the obtained offloading policy, an AIRS configuration and resource allocation scheme is proposed to minimize energy consumption. Simulation results demonstrate that the proposed approach significantly outperforms benchmark schemes in reducing both AoI and energy consumption, while exhibiting superior convergence performance.

To enable large model (LM) based edge intelligent service provisioning, on-device fine-tuning with locally personalized data allows for continuous and privacy-preserving LM customization. In this paper, we propose RingAda, a collaborative training framework designed for fine-tuning transformer-based LMs on edge devices. Particularly, RingAda performs parameterefficient adapter fine-tuning across a set of interconnected edge devices, forming a ring topology for per-batch training by sequentially placing frozen transformer blocks and their trainable adapter modules on the devices. RingAda follows a novel pipeline-parallel training mechanism with top-down adapter unfreezing, allowing for early-stopping of backpropagation at the lowest unfrozen adapter layer, thereby accelerating the finetuning process. Extensive experimental results demonstrate that RingAda significantly reduces fine-tuning time and memory costs while maintaining competitive model performance compared to its peer designs.

In this paper, we propose a novel road side unit (RSU)-assisted cooperative sensing scheme for connected autonomous vehicles (CAVs), with the objective to reduce completion time of sensing tasks. Specifically, LiDAR sensing data of both RSU and CAVs are selectively fused to improve sensing accuracy, and computing resources therein are cooperatively utilized to process tasks in real time. To this end, for each task, we decide whether to compute it at the CAV or at the RSU and allocate resources accordingly. We first formulate a joint task placement and resource allocation problem for minimizing the total task completion time while satisfying sensing accuracy constraint. We then decouple the problem into two subproblems and propose a two-layer algorithm to solve them. The outer layer first makes task placement decision based on the Gibbs sampling theory, while the inner layer makes spectrum and computing resource allocation decisions via greedy-based and convex optimization subroutines, respectively. Simulation results based on the autonomous driving simulator CARLA demonstrate the effectiveness of the proposed scheme in reducing total task completion time, comparing to benchmark schemes.

Cross-view geo-localization is a crucial task with diverse applications, yet it remains challenging due to the significant variations in viewpoints and visual appearances between images from different perspectives. While recent advancements have been made, existing methods often suffer from high model complexity, excessive resource consumption, and the impact of sample learning difficulty on optimization. To overcome these limitations, we optimize the Vision Mamba (Vim) model, built on a State Space Model (SSM) architecture, by replacing the traditional classification head with Channel Group Pooling (CGP) for efficient feature integration. This optimization reduces model parameters by 1.5% and computational complexity by 0.4%. Additionally, we propose a novel Dynamic Weighted Batch-tuple Loss (DWBL) to dynamically adjust the weighting of negative samples, improving model performance. By combining CGP and DWBL, we develop an efficient end-to-end network, VimGeo, which achieves state-of-the-art performance with enhanced computational efficiency. Specifically, VimGeo achieves a Recall@1 of 81.67% on the CVACT_test dataset, outperforming prior approaches. Extensive experiments on CVUSA, CVACT, and VIGOR datasets validate VimGeo's effectiveness and competitiveness in cross-view geo-localization tasks, achieving the leading results among sequence modeling-based methods. The implementation is available at: https://github.com/VimGeoTeam/VimGeo.

Deploying and executing large model inference on edge devices is challenging due to their limited computational power and memory resources. To address this challenge, we present a novel Split-and-Pipeline, a collaborative inference scheme that partitions a large model into multiple submodels and executes them across distributed edge devices in a pipelined manner. The scheme parallelizes data transfer across multiple CPU cores to avoid transmission bottlenecks. We build a real-world testbed using NVIDIA Jetson series edge devices to demonstrate the proposed scheme, achieving 1.2×–3.0× throughput improvement over state-of-the-art baselines.

The proliferation of Internet of Things (IoT)-generated distributed personal data enables user-specific large language model (LLM) adaptation at the edge. The split federated learning (SFL) facilitates collaborative learning and reduces memory footprint by model splitting, which necessitates the transmission of intermediate activations, rendering it susceptible to reconstruction attacks and privacy breaches. In this paper, we present a privacy-aware SFL scheme addressing the accuracy-efficiency-privacy trilemma in LLM fine-tuning over heterogeneous IoT devices. Particularly, we develop a privacy quantification metric based on Fisher information to assess layer-wise privacy risks in smashed data transmission. Guided by this metric, we establish an analytical model that captures the intricate relationships between privacy leakage, fine-tuning convergence time, and device energy consumption. To optimize these three aspects, we formulate a multi-objective mixed-integer programming problem. Then, an -constraint-based block coordinate descent (BCD) algorithm is proposed to jointly determine the optimal LLM split layer, transmit power, and bandwidth allocation for IoT devices under their memory and network constraints. Extensive simulation results demonstrate the proposed scheme’s effectiveness in achieving 24% faster convergence, 40% lower energy consumption, and 7% reduced privacy leakage compared to baseline approaches, while maintaining competitive model accuracy.

With the proliferation of edge computing, efficient artificial intelligence inference on edge devices has become essential for intelligent applications, such as autonomous vehicles and virtual/augmented reality. In this context, we address the problem of efficient remote object recognition by optimizing feature transmission between mobile devices and edge servers. We propose an optimization framework to tackle the challenges posed by dynamic channel conditions and device mobility in end-to-end communication systems. Our approach builds upon existing methods by leveraging a semantic knowledge base to drive multilevel feature transmission, accounting for temporal factors, state transitions, and dynamic elements throughout the transmission process. Additionally, we enhance the multilevel feature transmission policy by introducing an additional fifth-level edge-assisted semantic communication, which maximizes recognition performance by leveraging a large semantic knowledge base on the edge server. Formulated as an online optimization problem, our framework aims to simultaneously minimize semantic loss and adhere to specified transmission latency thresholds. To achieve this, we design a soft actor-critic-based deep reinforcement learning system with a carefully designed reward structure for real-time decision making. This approach overcomes the optimization difficulty of the NP-hard problem while fulfilling the optimization objectives. Numerical results showcase the superiority of our approach compared to traditional greedy methods across various system setups using open-source datasets.

In this article, we investigate a novel covert transmission scheme for satellite communication systems. Specifically, the satellite employs a rate-splitting multiple access technique to covertly transmit messages to multiple users and simultaneously transmit jamming signals, thereby enhancing the covert rate and robustness while avoiding detection by a warden. Due to the long propagation delay and lack of the warden’s precise location information, acquiring perfect channel state information (CSI) between the satellite, covert users, and the warden is difficult. To this end, we establish a dual-CSI uncertainty model, which incorporates phase and norm-bounded uncertainty for the covert and wiretap channels to characterize the actual CSI. In addition, we formulate a stochastic optimization problem with the objective of maximizing the minimum covert rate while adhering to covert communication constraints. The optimization problem is nonconvex and difficult to solve directly due to the dual-CSI uncertainty and the coupled nature of the variables. To solve the problem, we reformulate the original problem into a series of convex optimization problems by utilizing semidefinite relaxation, fractional programming, and the S-procedure methods. Then, we propose a robust common rate allocation and beamforming (CRAB) algorithm to obtain near-optimal solutions for the beamforming vectors and common rate allocation. Extensive simulation results demonstrate that the proposed algorithm significantly outperforms baseline schemes in terms of both covert rate and robustness.

The objective of this article is to investigate an update scheduling issue in the satellite-based network for time-sensitive marine Internet of Things (marine IoT) applications. In this particular scenario, multiple gateways capture updates from surrounding marine IoT sensors and make online decisions regarding task scheduling for orbital processing by a specific satellite. A hybrid low earth orbit and geosynchronous earth orbit (hybrid GEO-LEO) satellite architecture shows promise in achieving timely update delivery. However, the limited communication and orbital processing resources create significant challenges for ensuring timely task scheduling in the hybrid network. To address this challenge, we model the age-optimal scheduling issue as a collaborative gateway association and resource management problem. We first transform it into two corresponding subproblems: 1) resource management and 2) scheduling decision making. Subsequently, we employ the Lagrange multiplier algorithm to achieve optimal resource allocation results while utilizing deep reinforcement learning techniques to determine the scheduling decisions intelligently. Extensive simulation results demonstrate that our designed intelligent task scheduling scheme with optimal resource management outperforms state-of-the-art schemes in terms of peak-age, thereby highlighting the effectiveness of hybrid GEO-LEO networks for time-sensitive marine IoT applications.

Autonomous aerial vehicles (AAVs) can collect data from industrial Internet of Things (IoT) devices that experience poor channel conditions caused by the obstruction of large industrial equipment. However, due to the mobility of AAVs and stochastic industrial data generation, extreme events with significantly high latency may occur during data collection, resulting in unreliable communication. Besides, AAV speed variation brings challenges to achieving green communication and reliable data collection. In this article, we propose a dynamic AAV-assisted resource allocation scheme to collect data reliably for green industrial IoT. Specifically, the queue tail distribution is adopted to characterize the occurrence probability of extreme events, which indicates the reliability of the queue length. Then, given the impact of AAV speed on energy consumption and queue reliability, we aim to minimize energy consumption constrained by tail distribution and optimize AAV speed to ensure reliable data collection. Furthermore, the device access, bandwidth allocation, power control, and AAV speed are jointly optimized for minimizing the long-term energy consumption of AAVs and industrial IoT devices, constrained by the tail distribution of the queue length. The formulated problem is intractable due to intricately coupled variables and stochastic characteristics. To resolve it, we propose a novel algorithm, namely JDBPS, which can achieve reliable data collection and green communication. Simulation results demonstrate that the proposed JDBPS algorithm can constrain tail distribution while reducing transmit power of industrial IoT devices by 15.7% compared with the fixed AAV speed scheme.

With constrained resources, the industrial Internet of Things (IIoT) craves for lightweight and robust access authentication protocols to secure the network. Existing physical unclonable functions (PUFs)-based cryptographic protocols face privacy threats from wireless environments and semitrusted participants, while physical-layer authentication (PLA) is costly as a complementary protocol to upper layer. Therefore, in this article we propose a cross-layer mutual authentication with the key agreement protocol based on PUFs for IIoT. The proposed protocol integrates PUFs’ challenge-response pairs (CRPs) into low-complexity cryptographic primitives and signal phases of subcarriers, employs a newly designed authentication decision methodology, and achieves excellent authentication performance while reducing protocol redundancy. Our protocol also provides device anonymity, dynamic updates, and storage-free CRPs to defend against potential insider threats. The security of the proposed protocol has been formally and informally verified. The performance analysis results show that our protocol provides better security and privacy performance with low computation and communication cost. The simulation results show the protocol can obtain great authentication performance in the indoor factory (InF) wireless scenario of the 3GPP TR 38.901 standard.

In this paper, we propose an efficient model training scheme, namedGroup-basedHierarchicalSplitLearning (GHSL), which can accelerate the artificial intelligence (AI) training process in edge networks in a “first-sequential-then-parallel” manner. Specifically, the proposed scheme hierarchically splits an AI model into a user-side and server-side model, while dividing a number of users into multiple groups. Users in each group train user-side models with the interaction of the shared server-side model sequentially; different groups perform the above training process parallelly; the AI models of each group are aggregated into a global model. We also carry out the convergence analysis for the proposed scheme over non-independent and identically distributed data, which reveals that the convergence rate depends on user grouping. Furthermore, we propose a data-driven two-stage user grouping algorithm to minimize the overall training delay, taking user resource heterogeneity and the black-box training process into account. The proposed algorithm first utilizes the Gaussian process regression approach to determine the number of groups, and then employs the coalition game theory to determine the optimal user grouping decision. Comprehensive simulation results demonstrate that the proposed scheme can reduce training delay, user-side computational workload, and communication overhead by up to 19%, 53%, and 54%, respectively, comparing to state-of-the-art benchmarks.

Network slicing emerges as a promising solution for accommodating diverse services with varying quality of service (QoS) requirements. This paper delves into the problem of achieving energy-efficient network slicing in heterogeneous wireless networks. We first introduce a novel performance metric to evaluate the energy efficiency of slice. In order to reduce energy consumption and enhance energy efficiency, an adaptive slice switching mechanism is proposed, which enables slices to dynamically switch on and off based on real-time network traffic. Furthermore, we formulate a two-timescale optimization problem that jointly addresses slice switching and resource allocation to maximize long-term slice average energy efficiency while guaranteeing service delay requirements. To solve the joint problem, we decouple the problem into two subproblems in different timescales and develop a learning-based two-layer slice switching and resource allocation (SWEET) algorithm to make decisions in an online manner. Specifically, the long-timescale slice switching decisions are determined via a reinforcement learning algorithm in an outer layer, while the short-timescale resource allocation decisions are determined via leveraging coalition game and convex optimization in an inner layer. Extensive simulation results based on real-world datasets demonstrate that the SWEET algorithm yields an average improvement of 16.45% in slice energy efficiency, as well as adapts to network dynamics.

A Digital Twin (DT) is a software agent of a physical entity in virtual space, transcending the limitations imposed by physical constraints to enable intelligent services. The emergence of the Internet of Digital Twins (IoDT), by connecting DTs as a network, provides a reliable solution for streamlining the sharing of extensive real-time data among DTs. However, ensuring the security and efficiency of highly sensitive DT data remains a significant challenge in the distributed and dynamic IoDT storage environment. In this paper, we propose a comprehensive scheme that integrates blockchain, Distributed Hash Table (DHT), and Attribute-Based Encryption (ABE) to establish an IoDT data-sharing system. First, we introduce an ABE scheme to achieve data confidentiality and fine-grained access control. By implementing a key generation protocol, we address key escrow concerns in ABE. Second, to ensure bidirectional data confidentiality in data sharing without revealing the identities of DTs, the DHT, and blockchain are jointly applied to achieve resource registration and discovery. Through an XOR mapping operation mechanism, DT data are distributed across different DHT network nodes, reducing DT nodes’ storage consumption and effectively addressing the scalability issue of IoDT storage. Finally, we provide performance evaluations to demonstrate the reliability and efficiency of our proposed scheme. Our scheme strikes a balance between efficiency and security, exhibiting efficient performance in IoDT data sharing compared to other ABE and blockchain schemes.

We propose a digital twin-assisted adaptive preloading scheme to reduce bandwidth waste as well as enhance user quality of experience (QoE) for short video streaming. Though preloading video content can reduce rebuffering and improve user QoE, non-sequential playback of short videos induced by user swipe can result in substantial bandwidth wastage in mobile networks. To tackle this problem, we first model the short video streaming system and carry out preloading threshold analysis. We then construct a digital twin-assisted adaptive preloading framework for short video streaming. By collecting and analyzing the user's historical throughput and tracking swipe timing information, a throughput prediction model and a probabilistic model can be constructed to accurately predict future throughput and user swipe behavior, respectively. Utilizing the predicted information and real-time running status data from a short video application, we design a preloading strategy to enhance bandwidth efficiency while achieving high user QoE. Simulation results demonstrate the effectiveness of our proposed scheme compared with the state-of-the-art schemes.

The open radio access network (O-RAN) architecture is a promising RAN virtualization solution which provides interfaces for various timescale RAN intelligent control (RIC) schemes, thus achieving AI-based, cross layer resource scheduling. However, obtaining sufficient data to train AI models is difficult and costly. Digital twin (DT) technology can create high fidelity virtual world, which can not only be used to generate high-quality training data, but also provide an interactive platform for trial and error algorithms such as reinforcement learning (RL) to reduce the cost of interacting with real systems. Therefore, in this paper, we introduce our scheme that integrating DT and RL techniques to achieve cross layer resource scheduling in O-RAN system. We focus on the following two issues: i) how to reduce the gap between virtual and reality, ii) how to continuously evolve AI models to cope with unseen scenarios, and our preliminary ideas are also presented.

In this paper, we propose a joint sensing and communication framework for virtual reality (VR) applications in Metaverse. Although millimeter-wave (mmWave) communication can achieve multi-Gbps wireless transmission data rate, a slight movement of the VR headset can result in a significant drop in transmission rate. This significantly deteriorates user’s experience in Metaverse applications. By characterizing the relationship between mmWave beam gain and beam width, we find that adaptively turning off part of antennas can improve the overall transmission performance for mobile Metaverse. To this end, we formulate a problem with the objective of adaptively configuring receiver’s phase shift, and adjusting the beam width to cope with the variation in VR user’s viewpoints in Metaverse services. By revealing the correlation between power consumption and signal-to-noise ratio of VR headset, the proposed dual method based on meta reinforcement learning enables reliable and energy-efficient mmWave communication for VR. Based on the sensing information collected from VR users, the beamforming strategy is continuously updated by reshaping the reward of learning process, which minimizes the power consumption while meeting transmission requirements of Metaverse applications. Extensive experimental results demonstrate that the adaptability of the proposed framework outperforms the existing benchmarks in various VR scenarios, which ensures the applicability of mmWave communication to Metaverse applications.

In this paper, we investigate a dynamic resource allocation problem for remote Internet of things (IoT) data collection in space-air-ground integrated networks (SAGIN), in which the aerial platforms are deployed to bridge the communications between IoT nodes and satellites. To obtain an efficient resource allocation strategy that accommodates the stochastic data arrivals of IoT nodes and the dynamic network topology due to the high mobility of non-geostationary orbit (NGSO) satellites, we first formulate a resource allocation problem with queue stability constraints. Our objective is to maximize the long-term network utility, ensuring a balance between throughput and fairness among the IoT nodes. The formulated long-term problem is challenging to solve due to the unknown future network states and the coupling between continuous and integer variables. Therefore, we adopt the Lyapunov optimization theory to transform the problem into a deterministic problem in each time slot. Moreover, an online resource allocation algorithm is proposed to dynamically determine data admission, subchannel assignment, and power control in each time slot based on the current network status and data backlog. In addition, theoretical analysis indicates that there is an [O(1/V ), O(V)] trade-off between network utility and data backlog with control parameter V. Numerical results demonstrate that the proposed algorithm can greatly enhance the system throughput and reduce data queue backlog as well as preserve queue stability as compared with the benchmarks.

Timely and energy-efficient task offloading and computing can be challenging in mobile edge computing (MEC) networks when the communication links between devices and edge servers are unreliable. In this paper, we apply multiple aerial intelligent reflective surfaces (AIRSs) to assist devices in offloading computing tasks to the edge server in a timely and reliable manner in the MEC network with poor offloading environments. To evaluate the timeliness of offloading and computing, we derive the evolution process of age-of-information (AoI) under the random arrival of the computing tasks. The association between devices and AIRSs, offloading order of computing tasks, design of IRS phase shift, and allocation of communication and computing resources are jointly optimized to minimize the average AoI and system energy consumption given computing requirements. To solve the formulated minimization problem, we propose an efficient problem-solving framework to cope with the challenge of variable coupling. Firstly, we derive a closed-form optimal IRS phase shift to provide a reliable offloading environment. Then, we optimize the association between devices and AIRSs while reducing the offloading complexity and balancing the number of devices associated with each AIRS. Finally, we develop a low-complexity task offloading and resource allocation algorithm based on convex optimization to attain a good enough solution. Simulation results indicate the proposed solution outperforms benchmarks in timeliness and energy saving.

Mobile-edge computing can help enable low-latency and accurate video analytics. However, it is difficult to make efficient utilization of limited edge resources because of the diverse requirements of video queries. In this article, we investigate edge coordination for resource-efficient video query processing, in order to accommodate real-time queries on end cameras, edge nodes, or the cloud, with accuracy guarantee. This problem is challenging because: 1) video queries are with unpredictable arrivals and different resource demands; 2) the decision space of both query scheduling and resource allocation varies over time; and 3) it is critical to maintain long-term accurate analytics for all arrived queries. This problem boils down to making scheduling and resource allocation decisions, which is formulated as a mixed-integer nonlinear programming with a long-term accuracy constraint. Observing that both the scheduling and resource allocation of each query have the Markovian property, the Markov decision process and Lyapunov optimization are adopted to decompose the problem into sequential subproblems. An adaptive reinforcement learning-based approach relying on edge coordination is proposed. Extensive experimental results show that our proposal outperforms other benchmarks on latency and accuracy at a higher level of resource utilization efficiency in real-world data sets.

Recently, mobile crowdsensing (MCS) has emerged as a promising solution for traffic state estimation (TSE), which provides real-time and accurate traffic information for supporting diversified intelligent transportation systems (ITS) applications. However, the prohibitive overhead of collecting massive data in vehicular networks limits the available data amount, while the sparsification of MCS data incurs instability and degrades TSE accuracy. To this end, this paper proposes a novel sparse MCS framework to facilitate cost-effective TSE, which utilizes a small number of vehicular MCS participants distributed across all regions as data sources. By utilizing spatial and temporal correlations of traffic flow, an innovative spatiotemporal deep learning model, namely Transformer Graph Attentional Sample and Aggregate neural network (TGASA), is proposed to improve the TSE accuracy with sparse MCS data. Specifically, we design an incorporated graph neural network (GNN) to aggregate the spatial correlation by taking both node features and edge properties into account. And, the transformer neural network architecture is applied to capture the temporal correlation. Extensive simulation results based on real-world datasets demonstrate that the proposed framework can significantly address the instability incurred by the sparsification of MCS data and effectively achieve a more accurate TSE.

Federated Learning (FL) requires frequent exchange of model parameters, which leads to long communication delay, especially when the network environments of clients vary greatly. Moreover, the parameter server needs to wait for the slowest client (i.e., straggler, which may have the largest model size, lowest computing capability or worst network condition) to upload parameters, which may significantly degrade the communication efficiency. Commonly-used client selection methods such as partial client selection would lead to the waste of computing resources and weaken the generalization of the global model. To tackle this problem, along a different line, in this paper, we advocate the approach of model parameter dropout instead of client selection, and accordingly propose a novel framework of Federated learning scheme with Differential parameter Dropout (FedDD). FedDD consists of two key modules: dropout rate allocation and uploaded parameter selection, which will optimize the model parameter uploading ratios tailored to different clients' heterogeneous conditions and also select the proper set of important model parameters for uploading subject to clients' dropout rate constraints. Specifically, the dropout rate allocation is formulated as a convex optimization problem, taking system heterogeneity, data heterogeneity, and model heterogeneity among clients into consideration. The uploaded parameter selection strategy prioritizes on eliciting important parameters for uploading to speedup convergence. Furthermore, we theoretically analyze the convergence of the proposed FedDD scheme. Extensive performance evaluations demonstrate that the proposed FedDD scheme can achieve outstanding performances in both communication efficiency and model convergence, and also possesses a strong generalization capability to data of rare classes.

In this paper, we investigate the joint device activity and data detection in massive machine-type communications (mMTC) with a one-phase non-coherent scheme, where data bits are embedded in the pilot sequences and the base station simultaneously detects active devices and their embedded data bits without explicit channel estimation. Due to the correlated sparsity pattern introduced by the non-coherent transmission scheme, the traditional approximate message passing (AMP) algorithm cannot achieve satisfactory performance. Therefore, we propose a deep learning (DL) modified AMP network (DL-mAMPnet) that enhances the detection performance by effectively exploiting the pilot activity correlation. The DL-mAMPnet is constructed by unfolding the AMP algorithm into a feedforward neural network, which combines the principled mathematical model of the AMP algorithm with the powerful learning capability, thereby benefiting from the advantages of both techniques. Trainable parameters are introduced in the DL-mAMPnet to approximate the correlated sparsity pattern and the large-scale fading coefficient. Moreover, a refinement module is designed to further advance the performance by utilizing the spatial feature caused by the correlated sparsity pattern. Simulation results demonstrate that the proposed DL-mAMPnet can significantly outperform traditional algorithms in terms of the symbol error rate performance.

Cooperative perception (CP) is a key technology to facilitate consistent and accurate situational awareness for connected and autonomous vehicles (CAVs). To tackle the network resource inefficiency issue in traditional broadcast-based CP, unicast-based CP has been proposed to associate CAV pairs for cooperative perception via vehicle-to-vehicle transmission. In this paper, we investigate unicast-based CP among CAV pairs. With the consideration of dynamic perception workloads and channel conditions due to vehicle mobility and dynamic radio resource availability, we propose an adaptive cooperative perception scheme for CAV pairs in a mixed-traffic autonomous driving scenario with both CAVs and human-driven vehicles. We aim to determine when to switch between cooperative perception and stand-alone perception for each CAV pair, and allocate communication and computing resources to cooperative CAV pairs for maximizing the computing efficiency gain under perception task delay requirements. A model-assisted multi-agent reinforcement learning (MARL) solution is developed, which integrates MARL for an adaptive CAV cooperation decision and an optimization model for communication and computing resource allocation. Simulation results demonstrate the effectiveness of the proposed scheme in achieving high computing efficiency gain, as compared with benchmark schemes.

In this paper, we propose a value of information (VoI)-based packet scheduling scheme (VBPS) in autonomous underwater vehicle (AUV)-assisted underwater acoustic sensor networks (UASNs), where AUVs act as mobile sensor nodes to collect data from areas not accessible to static nodes and then relay data via static nodes. VoI is a performance metric to measure the importance of data packets with different levels of urgency. The proposed scheme aims to avoid collision with the ongoing packet transmission of static nodes without their accurate global information. In specific, the static node localization stage and the topology construction stage are carried out to obtain the local information. Furthermore, the transmission scheduling stage is implemented to avoid packet collision and formulates a combinatorial optimization problem maximizing VoI under the constraint of packet collision avoidance. To solve this complicated problem, a low-complexity distributed search algorithm is proposed, which exploits the spatial-temporal reuse to establish data packet collision constraints and then determines the next-hop node and data transmission time for AUVs. In addition, a collaborative search algorithm is proposed to avoid packet collision among different AUVs by enabling collaboration among AUVs. Extensive simulation results under various scenarios demonstrate the superior performance of the proposed scheme.

In this paper, we propose the multi-autonomous underwater vehicle (AUV) collaborative data collection in integrated underwater acoustic communication and detection networks (UCDNs). Specifically, multiple AUVs collaboratively traverse the sensor nodes to collect data while detecting the environment to avoid obstacles along the trajectory. We first propose a time division multiple access (TDMA)-based packet transmission and active bistatic sonar detection strategy for UCDNs to transmit the sensor data and detect the unknown environment. Furthermore, we formulate the collaborative data collection problem as a mixed combinatorial and sequential quadratic optimization problem to minimize the trajectory length of multiple AUVs. To solve this problem, we decouple it into two subproblems, i.e., the node traversal subproblem and the trajectory planning subproblem. The former subproblem is converted into the multi-traveling salesman problem (MTSP), which is solved by the Q-learning-based algorithm to improve the robustness. The latter subproblem is optimally planning each AUV's trajectory while avoiding obstacles, which is solved by the soft actor-critic (SAC) algorithm to online make continuous trajectory decisions. Simulation results demonstrate that the proposed scheme outperforms benchmarks in terms of energy consumption and overall trajectory length.

In this paper, we propose a digital twin (DT)-assisted cloud-edge collaborative transcoding scheme to enhance user satisfaction in live streaming. We first present a DT-assisted transcoding workload estimation (TWE) model for the cloud-edge collaborative transcoding. Particularly, two DTs are constructed for emulating the cloud-edge collaborative transcoding process by analyzing spatial-temporal information of individual videos and transcoding configurations of transcoding queues, respectively. Two light-weight Bayesian neural networks are adopted to fit the TWE models in DTs, respectively. Moreover, we formulate a transcoding-path selection problem to maximize long-term user satisfaction within an average service delay threshold, taking the dynamics of video arrivals and video requests into account. The problem is transformed into a standard Markov decision process by using the Lyapunov optimization, which is further solved by a deep reinforcement learning algorithm. Simulation results based on the real-world dataset demonstrate that the proposed scheme can effectively enhance user satisfaction compared with benchmark schemes.

In this paper, we study the abnormal behaviors detection and the corresponding data poisoning attacks in digital twin (DT)-based networks. We first analyze the abnormal behaviors existing in the DT-based networks, including environment anomalies, hardware and software faults, and network attacks. Specially, we design a machine learning (ML)-based anomaly detector to identify network attacks. Furthermore, due to the strong dependency of ML models on training data, in which the outputs of the trained ML models can be affected by the poisoned samples. We design a data poisoning attack scheme against the proposed ML-based anomaly detector, in which attackers can effectively compromise the output of anomaly detectors. Extensive experimental results adopting three commonly used ML-based models demonstrate that the attack can compromise these detectors with over 80% probability.

This paper studies autonomous underwater vehicles (AUV)-assisted underwater acoustic sensor networks (UASNs), where AUVs act as mobile sensor nodes to collect information from areas not accessible to static nodes and then relay data via static nodes. Due to the difficulty of obtaining the accurate global information of all the static nodes, we propose a novel packet scheduling scheme by utilizing local information obtained by AUVs. In the proposed scheme, the localization of static nodes stage and the topology construction stage are carried out beforehand to obtain the local information, based on which the transmission scheduling stage is implemented. Furthermore, in the transmission scheduling stage, we design a value of information (VoI)-based packet transmission scheduling (VBPS) strategy to avoid packet collision. Specifically, we introduce a performance metric, i.e., VoI, to measure the importance of data packets with different levels of urgency. Then, we formulate a combinatorial optimization problem to maximize VoI taking packet collision avoidance into consideration. A low-complexity distributed search algorithm is proposed to solve the problem, which exploits the spatial-temporal reuse to establish data packet collision constraints and then determines the next-hop node and data transmission time for AUVs. Extensive simulations under various scenarios are carried out to evaluate the performance of the proposed algorithm.

In this paper, we propose a digital twin (DT)-assisted resource demand prediction scheme to enhance prediction accuracy for multicast short video streaming. Particularly, we first construct user DTs (UDTs) for collecting real-time user status, including channel condition, location, watching duration, and preference. A reinforcement learning-empowered K-means++ algorithm is developed to cluster users based on the collected user status in UDTs. We then analyze users' watching duration and preferences in each multicast group to obtain the swiping probability distribution and recommended videos, respectively. The obtained information is utilized to predict radio and computing resource demand of each multicast group. Initial simulation results demonstrate that the proposed scheme can accurately predict resource demand.

In this paper, we propose a novel distributed learning scheme, named group-based split federated learning (GSFL), to speed up artificial intelligence (AI) model training. Specifically, the GSFL operates in a split-then-federated manner, which consists of three steps: 1) Model distribution, in which the access point (AP) splits the AI models and distributes the client-side models to clients; 2) Model training, in which each client executes forward propagation and transmit the smashed data to the edge server. The edge server executes forward and backward propagation and then returns the gradient to the clients for updating local client-side models; and 3) Model aggregation, in which edge servers aggregate the server-side and client-side models. Simulation results show that the GSFL outperforms vanilla split learning and federated learning schemes in terms of overall training latency while achieving satisfactory accuracy.

Virtual reality technology is rapidly evolving towards providing immersive user experience. By predicting user’s field-of-view (FoV) in advance, only transmitting content viewed by the user can help to meet the stringent requirements of delivering enhanced video quality. In this paper, a predictive and robust FoV selection algorithm is devised to dynamically identify a subset of video tiles, guided by the prediction error due to user’s stochastic head movement. Considering that the required data size to cover actual FoV is positively correlated with the prediction error, we construct a context space represented by the prediction error. A partition method of context space is exploited to discretize continuous context, where the prediction errors are classified effectively, and adaptive tile selection can be carried out. Then, a padding strategy is proposed by estimating the transmission gain of each tile in different prediction context, which improves the coverage of transmitted content around the true FoV at less bandwidth cost. Experimental results based on a real-world dataset demonstrate that the proposed algorithm can achieve dynamic FoV adjustment, and effectively improve user’s quality of experience.

In this paper, we propose a novel traffic prediction scheme for multiple radio access technology (multi-RAT) heterogeneous network. The scheme is named user-Cybertwin asynchronous learning (UCAL), which aims to extract meaningful patterns from noisy network traffic measurements and mitigate the impact of highly nonstationary measurements for ensuring the prediction accuracy. Specifically, we design a pattern extraction method that minimizes the Frobnius norm between the collected measurements and the expected k-rank approximation of the measurements in order to extract useful information. Then, by transforming the conventional long short term memory (LSTM) model into a nonlinear state space and incorporating Gaussian noise, we develop an online LSTM algorithm to adapt fast to changing environments. As a result, the parameter updating of the new online LSTM model can keep up with data changes while capturing complicated and nonlinear relationships among measurements. We consider both the surrounding environment conditions on the mobile user side and end-to-end link conditions on the Cybertwin side, and iteratively update the model parameters in both Cybertwin and MU. Simulation results demonstrate that the proposed UCAL scheme can achieve high traffic prediction accuracy in comparison to existing schemes. It can also significantly improve the efficiency in maintaining the prediction accuracy even when the dimension of traffic measurements increases.

In this paper, we propose an imaging scheme for unmanned aerial vehicle (UAV)-Enabled integrated sensing and communication (ISAC), where the UAV serves as a flexible communication auxiliary and a versatile sensing platform with the cooperation of a ground base station (GBS). To guarantee the performance of both sensing and communication, the proposed imaging scheme is based on the orthogonal frequency division modulation (OFDM) ISAC waveform and bistatic communication-assisted sensing strategy, which can be divided into three steps. Firstly, the UAV transmits OFDM ISAC signal, which contains the UAV position information to enable the communication-assisted sensing strategy. Secondly, the GBS receives the line-of-sight (LoS) ISAC signal from the UAV and the reflected ISAC signal from targets, in which the bistatic sensing architecture is designed to process data frequently and bypass the self-interference problem. Thirdly, the GBS preprocesses the received signal and reconstructs the image based on polar format algorithm (PFA) with the knowledge of UAV positions to relax the constraint of UAV trajectory. Numerical simulations are carried out to validate and evaluate the proposed UAV-enabled ISAC imaging scheme.

In this article, we propose an integrated satellite–terrestrial network (ISTN) architecture to support delay-sensitive task offloading for remote Internet of Things (IoT), in which satellite networks serve as a complement to terrestrial networks by providing additional communication resources, backhaul capacities, and seamless coverage. Under this architecture, we investigate how to jointly make offloading link selection and bandwidth allocation decisions for BSs and IoT users. Considering the differentiated decision-making time granularities, we formulate a two-timescale stochastic optimization problem to minimize the overall task offloading delay. To accommodate the two-timescale network dynamics and characterize state–action relations, we establish a hierarchical Markov decision process (H-MDP) framework with two separate agents tackling two-timescale network management decisions, and two evolved MDP-based subproblems are formulated accordingly. To efficiently solve the subproblems, we further develop a hybrid proximal policy optimization (H-PPO)-based algorithm. Specifically, a hybrid actor–critic architecture is designed to deal with the mixed discrete and continuous actions. In addition, an action mask layer and an action shaping function are designed to sample feasible task offloading decisions from the time-variant action set. Extensive simulation results have validated the superiority of the proposed ISTN architecture and the H-PPO-based algorithm, especially, in scenarios with scarce spectrum resources and heavy traffic loads.

Aerial intelligent reconfigurable surface (IRS) is a promising technology to enhance channel quality in data delivery. In this article, we study an aerial IRS deployment problem to enable timely and reliable data delivery in a remote Internet of Things (IoT) scenario, in which an IRS mounted on an unmanned aerial vehicle (UAV) is adopted as a mobile relay to assist devices in uploading data to the base station (BS). The objective is to minimize the average Age of Information (AoI) of the data received by the BS over time by jointly determining the aerial IRS deployment position and phase shift, transmit power of devices, and data uploading time. Under the requirements of peak AoI (PAoI) and communication reliability, we formulate an average AoI minimization problem. Since the nonlinear relations among optimization variables make the formulated problem nonconvex and intractable to solve, we propose a block coordinate descent (BCD)-based iterative algorithm which decomposes the formulated problem into several subproblems. The variables are optimized in each subproblem individually in an alternately iterative manner to attain a near-optimal solution. Simulation results demonstrate the superiority of the proposed algorithm in improving the information freshness compared with the benchmark schemes.

The advances in artificial intelligence (AI) and edge computing enable edge intelligence to support pervasive intelligent Internet of Things (IoT) applications in the future wireless networks. We focus on deep neural network (DNN)-based classification tasks, and investigate how to improve the confidence level and delay performance of DNN inference via device-edge collaboration. We first develop a stochastic cumulative DNN inference scheme that aggregates multiple random DNN inference results and generates a cumulative DNN inference result with improved confidence level. Then, based on a computation-efficient DNN model deployment strategy with shared computation between a locally deployed fast DNN model and a full DNN model partitioned between the device and edge, a closed-loop adaptive device-edge collaboration scheme is developed to support cumulative DNN inference for multiple devices. We adaptively determine how to offload DNN inference computation to the edge and how to allocate transmission and edge-computing resources among multiple devices, for Quality-of-Service (QoS) satisfaction in terms of both confidence level and inference delay with resource and energy efficiency. A reinforcement learning (RL) approach is used for adaptive offloading decision, which relies on a resource allocation solution for reward calculation. Simulation results demonstrate the effectiveness of the adaptive device-edge collaboration scheme for cumulative DNN inference, in terms of confidence level improvement, delay violation minimization, network resource efficiency, and device energy efficiency.

Split learning (SL) is a collaborative learning framework, which can train an artificial intelligence (AI) model between a device and an edge server by splitting the AI model into a device-side model and a server-side model at a cut layer. The existing SL approach conducts the training process sequentially across devices, which incurs significant training latency especially when the number of devices is large. In this paper, we design a novel SL scheme to reduce the training latency, namedCluster-basedParallelSL(CPSL) which conducts model training in a “first-parallel-then-sequential” manner. Specifically, the CPSL is to partition devices into several clusters, parallelly train device-side models in each cluster and aggregate them, and then sequentially train the whole AI model across clusters, thereby parallelizing the training process and reducing training latency. Furthermore, we propose a resource management algorithm to minimize the training latency of CPSL considering device heterogeneity and network dynamics in wireless networks. This is achieved by stochastically optimizing the cut layer selection, device clustering, and radio spectrum allocation. The proposed two-timescale algorithm can jointly make the cut layer selection decision in a large timescale and device clustering and radio spectrum allocation decisions in a small timescale. Extensive simulation results on non-independent and identically distributed data demonstrate that the proposed solution can greatly reduce the training latency as compared with the existing SL benchmarks, while adapting to network dynamics.

This paper studies an unmanned aerial vehicle (UAV)-assisted wireless powered sensor network (WPSN), where sensor nodes of multiple types can simultaneously harvest radio-frequency energy from the UAV and then transmit sensing data by using harvested energy. A joint distributed beamforming (DBF) and backscattering scheme is designed, in which the sensor nodes of one type can perform DBF while the sensor nodes of other types perform distributed backscattering (DBS) to improve the received signal strength. A sum-throughput maximization problem is formulated by jointly optimizing DBF phases, DBS phases, and time allocation (TA), subject to the received signal-to-noise ratio constraints. Since the formulated problem is difficult to be solved due to the tightly coupled optimizing variables, the problem is decoupled into a TA subproblem and a phase optimization subproblem, and then a two-step algorithm is proposed to solve them. Firstly, the closed-form solution for the TA subproblem is derived according to Karush-Kuhn-Tucker conditions. Secondly, based on iterative optimization and one-dimensional search methods, a centralized algorithm is proposed to obtain the optimal solution for the phase optimization subproblem. Moreover, a decentralized algorithm that obtains the suboptimal solution is proposed to reduce the computational complexity. Extensive simulation results validate the effectiveness of the proposed scheme on throughput enhancement.

In this paper, we present a digital twin (DT)-assisted adaptive video streaming scheme to enhance personalized quality-of-experience (PQoE). Since PQoE models are user-specific and time-varying, existing schemes based on universal and time-invariant PQoE models may suffer from performance degradation. To address this issue, we first propose a DT-assisted PQoE model construction method to obtain accurate user-specific PQoE models. Specifically, user DTs (UDTs) are respectively constructed for individual users, which can acquire and utilize users' data to accurately tune PQoE model parameters in real time. Next, given the obtained PQoE models, we formulate a resource management problem to maximize the overall long-term PQoE by taking the dynamics of users' locations, video requests, and buffer statuses into account. To solve this problem, a deep reinforcement learning algorithm is developed to jointly determine segment version selection, and communication and computing resource allocation. Simulation results on the real-world dataset demonstrate that the proposed scheme can effectively enhance PQoE compared with benchmark schemes.

Camera-based monitoring is becoming increasingly popular, as multi-objective detection tasks can be enabled by video analytics over captured frames. Yet, video frames have to be delivered to computation-capable edge nodes for further processing, because the amount of required resources exceeds the capacity of built-in hardware of video cameras. In this paper, observing that video resolution directly determines the subsequent bandwidth and computing resource consumption, as well as the analytic accuracy, we propose an edge-assisted object-based resolution configuration algorithm to achieve efficient multi-task video analytics. The proposed algorithm harnesses the diversity of neural networks used for detecting different objects in one frame, which brings about two-fold possibility for bandwidth saving. On one hand, background information cannot be indiscriminately transmitted, as is unlikely to contribute to improving the analytics accuracy. On the other hand, fine-grained resolution selection allows object-level optimal resolution that minimizes the transmitted data volume under accuracy and latency constraints. Simulation results demonstrate that the proposed method can effectively reduce up to 50% of the transmitted data volume, compared to existing benchmarks.

Traffic flow estimation (TFE) plays an important role in intelligent transportation systems (ITS). Considering the prohibitive overhead of collecting and processing massive data in vehicular networks, it is more practical to use the sparse vehicular big data. In this paper, we focus on accurately estimating the urban traffic flow of vehicular networks only using a small portion of vehicular data. A new spatiotemporal machine learning model, named Graph Sampling and Aggregate Transformer (GSAT), is developed to improve the estimation accuracy by leveraging the inner correlation of traffic data. Specifically, the GSAT uses the graph sample and aggregate (GraphSAGE) model, a variety of graph neural network (GNN), to aggregate the spatial correlation and applies the Transformer model to capture the temporal correlation. We evaluate GSAT at multiple sparsity on the real world dataset of vehicular network, and it is demonstrated that GSAT can achieve accurate estimation with sparse big data.

In this article, we investigate the freshness of the vehicular status updates in space–air–ground-integrated networks (SAGINs), where the status updates are generated by sampling a fixed-rate dynamic Markov process and delivered to the monitor over an unreliable channel instantaneously. The Age of Information (AoI) is adopted to capture the timeliness of the status updates. Two hybrid automatic repeat request (HARQ) schemes, namely, classical HARQ scheme and incremental redundancy HARQ (IR-HARQ) scheme, are taken into consideration to combat the errors occurred in the transmission. In this setting, once an update is not decoded successfully, one should carefully decide how to schedule the updates for optimizing the AoI. Especially, differential encoding scheme is introduced in the considered system to exploit the temporal correlations of the source. By differential encoding, each update can be actual or differential, based on the differential encoding level. To minimize the long-term average age, we formulate a Markov decision process (MDP), and prove that the optimal transmission policies for classical HARQ scheme and IR-HARQ scheme behave differently in threshold structures. Furthermore, we jointly optimize the codeword length, differential encoding level, and retransmission times to minimize the AoI. The performance comparison shows the advantages of the IR-HARQ scheme over the classical HARQ scheme from the age perspective.

In this paper, we propose a covert wireless uplink transmission strategy in space-air-ground integrated vehicular networks, where the source vehicle transmits its own message over the channel that being used by the host communication system, to avoid being detected by the warden. It is obvious that the data transmission efficiency of the covert communication system is limited due to the co-channel interference. To improve the data transmission efficiency, we consider that the covert communication system adopts improper Gaussian signaling (IGS). We formulate a joint transmit power and IGS factor optimization problem to minimize the outage probability of the covert communication system. The minimum error detection probability of the warden is first analyzed with noise uncertainty, which is used to measure the system covertness. Under the constraints of the quality of service (QoS) of host communication system and the covertness requirement, the optimal transmit power is first derived with proper Gaussian signaling (PGS) scheme. Then, with the approximate outage probability derived under IGS scheme, the optimization problem is solved by jointly designing the transmit power and IGS factor. Finally, we provide extensive numerical results to validate the proposed covert transmission strategy, and demonstrate that the IGS scheme is beneficial in improving the data transmission efficiency in terms of outage probability compared to PGS scheme.

As a promising solution for massive machine-type communication, grant-free non-orthogonal multiple access (GF-NOMA) has received considerable attention in recent years. However, the multidimensional constellation design (MCD) and multiuser detection (MUD) in GF-NOMA are usually optimized in adivide and conquerway, leading to local optima and performance degradation. To address this issue, we investigate the joint optimization of MCD and MUD for GF-NOMA. The formulated joint optimization is based on variational inference, which is intractable due to the signal superimposition that makes the optimization variables intricately coupled. Then, we resort to end-to-end deep learning (DL) to obtain the optimal solution. Specifically, we propose a DL-based multi-task variational autoencoder (Mul-VAE) that adopts a variational autoencoder network to optimize the distribution of the constellation points. We further derive the loss function of the proposed network and analyze it from an information-theoretic perspective. On this basis, multi-task learning is employed to deal with mutually conflicting yet related detection processes. Besides, taking heterogeneous transmission rates of users into account, a multi-task prioritizing strategy is designed to balance training performance. Simulation results reveal that the proposed method enables significant gains compared to state-of-the-art techniques.

Unmanned aerial vehicle (UAV)-assisted wireless powered sensor networks (WPSNs) have emerged as a promising paradigm for charging sensor nodes' batteries in remote areas. However, the sum-throughput of overall sensor nodes can dramatically decrease due to their long-distance transmission to the UAV. In this paper, we propose a joint distributed beamforming and backscatter cooperation (BC) scheme to enhance the sum-throughput of UAV-assisted WPSNs with various types of sensor nodes. In particular, we consider the BC mechanism which leverages other types sensor nodes with constructive multi-path signals to enhance the long-distance transmission of same-type sensor nodes. We maximize the sum-throughput by jointly optimizing the distributed backscattering, distributed beamforming and time allocation. The sum-throughput maximization problem is difficult to be solved directly due to the coupling among optimizing variables. We decompose the problem into a BC subproblem and a time allocation subproblem, and propose a two-step scheme to solve them. First, for the BC subproblem, we derive closed-form low-complexity distributed beamforming solutions and distributed backscattering solutions to maximize the signal-to-noise ratios of the same-type sensor nodes. Second, for the time allocation subproblem, we derive the closed-form solutions according to KKT conditions. Simulation results are provided to demonstrate that the proposed joint distributed beamforming and BC scheme can increase the sum-throughput as compared to conventional distributed beamforming schemes.

Space-ground integrated vehicular networks (SGIVNs) are envisioned as a promising architecture to support multifarious vehicular services with enhanced network flexibility and reliability. Access mode selection (AMS) is of capital importance in the SGIVN for the ingenious cooperation among different network segments to exploit their complementary advantages. In this paper, we investigate the AMS problem for vehicles in the SGIVN by taking distinct features of satellite networks (long propagation delay) and terrestrial networks (frequent handover) into account. In light of the high vehicle/satellite mobility and dynamic data packet arrivals, we formulate a stochastic integer programming problem of sequential AMS to maximize vehicles' long-term data rate. To cope with the time-varying network dynamics, we leverage a Markov decision process framework to model the evolution of vehicle states. For the special case with known stochastic model of data packet arrivals, we transform the problem into a linear programming problem that can be solved with low complexity. For the general case without the data packet arrival model, we propose a reinforcement learning-based algorithm to make adaptive AMS decisions to keep pace with network dynamics. Simulation results demonstrate that the proposed algorithm outperforms benchmark algorithms in terms of data rate under different data packet arrival patterns and vehicle velocities.

This paper aims to investigate the joint optimization of multidimensional constellation design (MCD) and multiuser detection (MUD) for grant-free non-orthogonal multiple access (GF-NOMA). We first formulate the joint optimization problem and derive its explicit expression using variational inference. Due to the intractability of the joint optimization problem, we then resort to deep learning (DL) and approximate the optimal solution in an end-to-end manner. Specifically, we develop a novel variational autoencoder based network, such that the distribution of the multidimensional constellations can be accessed and optimized. We also design a multi-task learning architecture on the decoder side to deal with the complex coupling among signal streams, by taking the MUD process as multiple distinctive yet related tasks. The derivation of the loss function for network training is presented, and simulation results are provided to validate the superior performance of the proposed method over conventional approaches.

Low-latency and accuracy-guaranteed video analytics is essential to many delay-sensitive camera-based applications. Analyzing video frames on edge nodes in proximity can effectively reduce the response delay compared with cloud-based solutions. However, the computation and bandwidth resources on an edge node are always limited. In this paper, we design a joint video query scheduling and resource allocation problem based on an edge coordinated architecture, in order to properly accommodate real-time video queries on end cameras, the edge nodes, or the cloud. This problem is challenging in that 1) the arrivals of video queries with different resource requirements are unknown in advance and 2) the design space (of both query scheduling and resource allocation) to provision video queries varies over time. Taking the two-fold uncertainty into consideration, we formulate the query provision problem as a mix integer non-linear program which is NP-hard and not solved directly. To deal with the NP-hardness and the absence of future information, the problem is re-formulated as a Markov decision process, which can leverage historical query information to make decisions about scheduling and resource allocation. The transformed problem calls for an online solution that can efficiently adapt to the dynamic design space. Hence, we propose an edge-coordinated reinforcement learning algorithm to continuously learn from the environment, and make decisions for query scheduling and resource allocation to achieve low latency and accurate video analytics. Extensive simulation results demonstrate the advantages of the proposed algorithm in latency and accuracy.

It is well known that concurrent multipath transfer (CMT) can improve the transmission rate. However, due to multiple heterogeneous paths from users to the access network, a large number of out-of-order packets significantly degrade the overall transmission reliability. Cybertwin provides a potential solution to alleviate the packet out-of-order problem by accurately detecting and perceiving the path state. In this article, we investigate the data scheduling problem and propose a learning-based cybertwin-driven CMT algorithm to obtain the optimal data scheduling policy. In particular, we first formulate the data scheduling problem as an integer linear programming by taking the QoS metrics into account. To cope with the packet out-of-order problem in CMT, we propose a reliable cybertwin-CMT with deep reinforcement learning (CMT-DRL) algorithm to determine the data scheduling decisions. The proposed algorithm takes multipath throughput, end-to-end delay, and packet loss rate into account. Besides, CMT-DRL adopts an asynchronous learning framework to efficiently execute data collection, packet scheduling, and neural network training in sequence by decoupling model training and execution. We conduct extensive experiments in a P4-based programmable network platform. Experimental results indicate that the CMT-DRL outperforms the existing benchmarks in terms of the number of out-of-order packets, round-trip time, and throughput.

In this paper, we investigate a radio access network (RAN) slicing problem for Internet of vehicles (IoV) services with different quality of service (QoS) requirements, in which multiple logically-isolated slices are constructed on a common roadside network infrastructure. A dynamic RAN slicing framework is presented to dynamically allocate radio spectrum and computing resource, and distribute computation workloads for the slices. To obtain an optimal RAN slicing policy for accommodating the spatial-temporal dynamics of vehicle traffic density, we first formulate a constrained RAN slicing problem with the objective to minimize long-term system cost. This problem cannot be directly solved by traditional reinforcement learning (RL) algorithms due to complicatedcoupled constraintsamong decisions. Therefore, we decouple the problem into a resource allocation subproblem and a workload distribution subproblem, and propose atwo-layer constrainedRL algorithm, namedResourceAllocation andWorkload diStribution (RAWS) to solve them. Specifically, anouter layerfirst makes the resource allocation decision via an RL algorithm, and then aninner layermakes the workload distribution decision via an optimization subroutine. Extensive trace-driven simulations show that the RAWS effectively reduces the system cost while satisfying QoS requirements with a high probability, as compared with benchmarks.

In this paper, we aim to make the best joint decision of device selection and computing and spectrum resource allocation for optimizing federated learning (FL) performance in distributed industrial Internet of Things (IIoT) networks. To implement efficient FL over geographically dispersed data, we introduce a three-layer collaborative FL architecture to support deep neural network (DNN) training. Specifically, using the data dispersed in IIoT devices, the industrial gateways locally train the DNN model and the local models can be aggregated by their associated edge servers every FL epoch or by a cloud server every a few FL epochs for obtaining the global model. To optimally select participating devices and allocate computing and spectrum resources for training and transmitting the model parameters, we formulate a stochastic optimization problem with the objective of minimizing FL evaluating loss while satisfying delay and long-term energy consumption requirements. Since the objective function of the FL evaluating loss is implicit and the energy consumption is temporally correlated, it is difficult to solve the problem via traditional optimization methods. Thus, we propose a “Reinforcement on Federated” (RoF) scheme, based on deep multi-agent reinforcement learning, to solve the problem. Specifically, the RoF scheme is executed decentralizedly at edge servers, which can cooperatively make the optimal device selection and resource allocation decisions. Moreover, a device refinement subroutine is embedded into the RoF scheme to accelerate convergence while effectively saving the on-device energy. Simulation results demonstrate that the RoF scheme can facilitate efficient FL and achieve better performance compared with state-of-the-art benchmarks.

With proliferation of computation-intensive Internet of Things (IoT) applications, the limited capacity of end devices can deteriorate service performance. To address this issue, computation tasks can be offloaded to the Mobile Edge Computing (MEC) for processing. However, it consumes considerable energy to transmit and process these tasks. In this paper, we study the energy efficient task offloading in MEC. Specifically, we formulate it as a stochastic optimization problem, with the objective of minimizing the energy consumption of task offloading while guaranteeing the average queue length. Solving this offloading optimization problem faces many technical challenges due to the uncertainty and dynamics of wireless channel state and task arrival process, and the large scale of solution space. To tackle these challenges, we apply stochastic optimization techniques to transform the original stochastic problem into a deterministic optimization problem, and propose an energy efficient dynamic offloading algorithm called EEDOA. EEDOA can be implemented in an online manner to make the task offloading decisions with polynomial time complexity. Theoretical analysis is provided to demonstrate that EEDOA can approximate the minimal transmission energy consumption while still bounding the queue length. Experiment results are presented which show the EEDOA’s effectiveness.

As an emerging computing paradigm, mobile edge computing (MEC) can improve users’ service experience by provisioning the cloud resources close to the mobile devices. With MEC, computation-intensive tasks can be processed on the MEC servers, which can greatly decrease the mobile devices’ energy consumption and prolong their battery lifetime. However, the highly dynamic task arrival and wireless channel states pose great challenges on the computation task allocation in MEC. This paper jointly investigates the task allocation and CPU-cycle frequency, to achieve the minimum energy consumption while guaranteeing that the queue length is upper bounded. We formulate it as a stochastic optimization problem, and with the aid of stochastic optimization methods, we decouple the original problem into two deterministic optimization subproblems. An online Task Offloading and Frequency Scaling for Energy Efficiency (TOFFEE) algorithm is proposed to obtain the optimal solutions of these subproblems concurrently. TOFFEE can obtain the close-to-optimal energy consumption while bounding the applications’ queue length. Performance evaluation is conducted which verifies TOFFEE’s effectiveness. Experiment results indicate that TOFFEE can decrease the energy consumption by about 15 percent compared with the RLE algorithm, and by about 38 percent compared with the RME algorithm.

Collaboration among industrial Internet of Things (IoT) devices and edge networks is essential to support computation-intensive deep neural network (DNN) inference services, which require low delay and high accuracy. Sampling rate adaption, which dynamically configures the sampling rates of industrial IoT devices according to network conditions, is the key in minimizing the service delay. In this article, we investigate the collaborative DNN inference problem in industrial IoT networks. To capture the channel variation and task arrival randomness, we formulate the problem as a constrained Markov decision process (CMDP). Specifically, sampling rate adaption, inference task offloading, and edge computing resource allocation are jointly considered to minimize the average service delay while guaranteeing the long-term accuracy requirements of different inference services. Since CMDP cannot be directly solved by general reinforcement learning (RL) algorithms due to the intractable long-term constraints, we first transform the CMDP into an MDP by leveraging the Lyapunov optimization technique. Then, a deep RL-based algorithm is proposed to solve the MDP. To expedite the training process, an optimization subroutine is embedded in the proposed algorithm to directly obtain the optimal edge computing resource allocation. Extensive simulation results are provided to demonstrate that the proposed RL-based algorithm can significantly reduce the average service delay while preserving long-term inference accuracy with a high probability.

In this article, we investigate a computing task scheduling problem in space-air-ground integrated network (SAGIN) for delay-oriented Internet of Things (IoT) services. In the considered scenario, an unmanned aerial vehicle (UAV) collects computing tasks from IoT devices and then makes online offloading decisions, in which the tasks can be processed at the UAV or offloaded to the nearby base station or the remote satellite. Our objective is to design a task scheduling policy that minimizes offloading and computing delay of all tasks given the UAV energy capacity constraint. To this end, we first formulate the online scheduling problem as an energy-constrained Markov decision process (MDP). Then, considering the task arrival dynamics, we develop a novel deep risk-sensitive reinforcement learning algorithm. Specifically, the algorithm evaluates the risk, which measures the energy consumption that exceeds the constraint, for each state and searches the optimal parameter weighing the minimization of delay and risk while learning the optimal policy. Extensive simulation results demonstrate that the proposed algorithm can reduce the task processing delay by up to 30% compared to probabilistic configuration methods while satisfying the UAV energy capacity constraint.

In this paper, we investigate the joint task assignment and resource allocation for deep neural network (DNN) inference in the device-edge-cloud based industrial Internet of things (IIoT) networks. To efficiently orchestrate the limited spectrum and computing resources in IIoT networks for massive DNN inference tasks, a resource management problem is formulated with the objective of maximizing the average inference accuracy while satisfying the quality-of-service of DNN inference tasks. Considering the strict delay requirements of inference tasks, we transform the formulated problem into a Markov decision process, and propose a deep deterministic policy gradient based learning algorithm to obtain the solution rapidly. Simulation results show that the proposed algorithm can achieve high average inference accuracy.

Accurate cellular traffic load prediction is a pre-requisite for efficient and automatic network planning and management. Considering diverse users' activities at different locations and times, it is technically challenging to characterize the network resource demands at different time scales via traditional prediction methods. In this paper, we propose to combine the long short-term memory (LSTM) and Gaussian process regression (GPR) to achieve accurate single-cell level cellular traffic prediction, using the open Milan cellular traffic dataset provided by Telecom Italia. Firstly, the dominant periodic components of the cellular data are extracted, and then the small components are fed to the LSTM network. To further improve the prediction accuracy, GPR is used to recover the residual components. Extensive experiments are conducted based on the dataset, and it is shown that the proposed LSTM-GPR scheme outperforms the benchmark schemes, especially for a relatively long time and burst traffic prediction.

To explore the potential of machine learning‐based cooperative spectrum sensing (CSS) in training time, classification speed and classification performance, this study mainly focuses on studying the problem of the feature vectors selecting for machine learning‐based CSS. First, a new machine learning‐based CSS framework is presented, in which, energy vector forming module, feature vector conversion module, training module, classification module and training sample database are included. Second, a new two‐dimensional distance vector is developed, and it is converted by an m ‐dimensional energy vector according to the distance measurement between vectors. Furthermore, six combination modes are obtained by combining three feature vectors (energy, probability and distance vectors) with two supervised machine learning methods, which are support vector machine (SVM) and weighted K‐nearest‐neighbour, respectively. From the proposed experimental simulations, the authors can find that the distance vector is obviously superior to the probability vector in computation time. Moreover, the probability vector and distance vector are superior to the energy vector in training time except for the case of poor signal and fewer users, and obviously superior to the energy vector in classification speed. At last, the probability vector and distance vector with SVM classifier show the best classification performance in six combination modes.

To develop smart city and intelligent manufacturing, video cameras are being increasingly deployed. In order to achieve fast and accurate response to live video queries (e.g., license plate recording and object tracking), the real-time high-volume video streams should be delivered and analyzed efficiently. In this article, we introduce an end-edge-cloud coordination framework for low-latency and accurate live video analytics. Considering the locality of video queries, edge platform is designated as the system coordinator. It accepts live video queries and configures the related end cameras to generate video frames that meet quality requirements. By taking into account the latency constraint, edge computing resources are subtly distributed to process the live video frames from different sources such that the analytic accuracy of the accepted video queries can be maximized. Since the amount of required edge computing resource and video quality to accurately address different video queries are unknown in advance, we propose an online video quality and computing resource configuration algorithm to gradually learn the optimal configuration strategy. Extensive simulation results show that as compared to other benchmarks, the proposed configuration algorithm can effectively improve the analytic accuracy, while providing low-latency response.

In this paper, we propose a low-complexity user selection algorithm for an uplink multiuser transmission in millimeter wave (mmWave) WLAN. We first formulate the user selection problem, taking hybrid beamforming (HBF), an NP-hard problem, into consideration. We then develop a three-step HBF algorithm that incorporates user selection. Specifically, users can be selected based on semi-orthogonality instead of collecting perfect channel state information (CSI) from all potential users. We optimize the digital beamforming to mitigate residual interference among the selected users. Furthermore, we provide analytical validation for the proposed user selection algorithm and study the impact of angle correlation, analog beam pattern, and beamwidth on the achievable rate of the selected users. Extensive simulations validate the performance of the proposed overall HBF algorithm when compared with existing solutions.

In this paper, we investigate the edge caching and content delivery problem for both high-speed train (HST) passengers and low-mobility cellular users. Under multi-dimensional resources constraints, we formulate an optimization problem to minimize the content retrieval delay of HST passengers and meanwhile guarantee the delay requirements of cellular users. As the formulated problem is a mixed-integer nonconvex optimization problem, which is intractable directly, we propose an efficient iterative algorithm that optimizes the three decision variables (i.e., content placement, subchannel allocation, and transmission power allocation) alternately. In specific, Lagrangian multiplier is introduced to convert the constrained optimization, which transforms the content caching problem into a Lagrangian relaxed knapsack problem. Afterwards, the subchannel assignment problem is solved by the Hungarian algorithm with polynomial time complexity, and the power allocation strategy is obtained by the bisection method. Extensive simulations are carried out and results demonstrate that our proposed caching strategy can reduce the content retrieval delay by up to 25% in comparison with the benchmark strategy.

Due to the versatile networking capability, space- air-ground integrated network (SAGIN) becomes a prominent future architecture to support the ever- increasing Internet of Things (IoT) applications. In this paper, we investigate the IoT task offloading under an SAGIN scenario where multiple IoT devices generate computing tasks to be processed. We adopt an unmanned aerial vehicle (UAV) to fly along a given trajectory to collect the tasks of IoT devices within the coverage area, and then makes the online offloading decision, i.e., processing locally, or offloading to the nearby base station or the far-away satellite. However, due to the constrained energy resources committed by UAV and the uncertainty of the system dynamics, designing an efficient computation task offloading algorithm is challenging. This dynamic scheduling problem is formulated as a constrained Markov decision process (CMDP), considering the stochastic channel conditions, UAV coverage, energy consumption, and task queue backlogs. By exploiting the stationary stochastic feature of the CMDP, the problem can be solved by the linear programming to find a stochastic policy. Simulation results demonstrate that the proposed computation offloading scheme can significantly reduce IoT task processing delay as compared to other benchmarks.

Multiuser multiple input multiple output (MU-MIMO) millimeter wave (mmWave) communication is considered as a key technology to provide multi-gigabit train-to-ground wireless connections in the high-speed railway (HSR) system. Considering the power consumption and hardware constraint, the hybrid beamforming (BF), which combines analog BF and digital BF, is widely adopted in the MU-MIMO mmWave systems. In this paper, we target on an efficient hybrid BF structure design in HSR scenario with taking the practical HSR mmWave channel model into consideration. Specifically, the hybrid BF design aims at maximizing the overall throughput and is formulated as an optimization problem which is proved to be nonconvex and NP-hard. Therefore, a suboptimal yet efficient two-stage solution is proposed, where a weighted minimum mean square error (WMMSE) based beamforming strategy is exploited to devise the hybrid beamformer at the base station (BS) at the first stage, and the orthogonal matching pursuit (OMP) approach is leveraged to decouple the digital BF and analog BF at BS at the second stage. Simulation results demonstrate that higher overall throughput can be achieved by the proposed hybrid BF scheme compared to other state-of-the-art benchmarks.

Ensuring network QoS for Internet of vehicles (IoVs) is crucial for safe and intelligent transportation system, while the vehicle density variation seems invincible for stationary base station (BS) networks. In this paper, we study IoV's downlink throughput guarantee, in which, in addition to the cellular BS resource, UAVs (equipped with WiFi interfaces) can be dynamically sent out to provide additional wireless connections. To cope with the dynamic IoV density, we propose an Online UAV Scheduling scheme, referred to as OUS, to online schedule and manage UAVs to guarantee seamless connections with reliable throughput performance. In OUS, we first use the complementary cumulative distribution function (CCDF) of IoV throughput to calculate the likelihood of a channel resource shortage. If a shortage condition is imminent and then minimal UAVs will be sent out to their optimal hovering positions. In particular, we revealed the marginal effect for the optimal hovering position acquisition, i.e., the further the UAV is away from the BS, the larger throughput gain can be achieved by the system. We conduct extensive simulations to evaluate the performance of our OUS scheme, and results demonstrate that it can well react to the throughput QoS demand by intelligently sending out minimal UAVs, and its hovering position acquisition method can fully utilize the efficacy of UAVs.

In this paper, we propose a cooperation framework in heterogeneous cloud radio access networks (H-CRANs) to mitigate inter-tier interference. Specifically, small cell remote radio head (S-RRH) acts as the cognitive relay for multiple macrocell users (MUEs) which are primary users, and obtains a fraction of time slot from multiple MUEs as a reward. Through the cooperation, the S-RRHs can obtain extra spectrum resource for serving secondary users-small cell users (SUEs), while the MUEs can improve their transmission rates. Moreover, the inter-tier interference between macrocell networks and small cell networks can be mitigated via cooperation. The cooperation problem is formulated as a binary integer programming problem which is NP-hard. To solve this problem, we transform it to an equivalent many-to-one matching problem. Then, we achieve the near optimal solution by proposing a two-sided cooperator selection algorithm, which takes the benefits of both S-RRHs and MUEs into consideration. Simulation results show that the performance of the macrocell networks as well as small cell networks can be improved by adopting the proposed scheme, and the cooperator selection result is stable and close to the optimal solution.

In this paper, unmanned aerial vehicles (UAVs) are used to efficiently collect information in an areas of interest. Based on the matrix completion, an optimal UAV data collection trajectory (OUDCT) scheme is proposed for improving energy efficiency and reducing redundant data by optimizing the trajectory of the UAV. With the proposed scheme, the backbone sampling points can be selected as follows. First, sampling points with higher degrees are selected as dominator sampling points. Second, sampling points with lower degrees are selected as virtual dominator sampling points to ensure that the information in all rows and columns is collected. Third, sampling points with lower degrees are selected as follower sampling points until the total number of selected sampling points satisfies the minimum requirement of the matrix completion. Thus, all the information in the monitoring area can be recovered by using the matrix completion. Finally, the optimal simulated annealing algorithm is used to plan the path of UAV based on the selected sampling points. The experimental results indicate that the performance of the OUDCT scheme is better than those in previous studies. Extensive simulation results are provided, which demonstrate that the OUDCT scheme can reduce data redundancy by 50%-52% and increase the lifetime by 17% compared with the random selection sampling points scheme.

Beam alignment (BA) is to ensure the transmitter and receiver beams are accurately aligned to establish a reliable communication link in millimeter-wave (mmwave) systems. Existing BA methods search the entire beam space to identify the optimal transmit-receive beam pair, which incurs significant BA latency on the order of seconds in the worst case. In this paper, we develop a learning algorithm to reduce BA latency, namely Hierarchical Beam Alignment (HBA) algorithm. We first formulate the BA problem as a stochastic multi-armed bandit problem with the objective to maximize the cumulative received signal strength within a certain period. The proposed algorithm takes advantage of the correlation structure among beams such that the information from nearby beams is extracted to identify the optimal beam, instead of searching the entire beam space. Furthermore, the prior knowledge on the channel fluctuation is incorporated in the proposed algorithm to further accelerate the BA process. Theoretical analysis indicates that the proposed algorithm is asymptotically optimal. Extensive simulation results demonstrate that the proposed algorithm can identify the optimal beam with a high probability and reduce the BA latency from hundreds of milliseconds to a few milliseconds in the multipath channel, as compared to the existing BA method in IEEE 802.11ad.

The ultra-dense edge networks with mmWave and beamforming are envisioned as a potential solution to satisfy the high rate and capacity requirements in 5G networks. In IEEE 802.11 ad, which is the first beamforming-enabled WLAN standard, all stations (STs) contend for beamforming (BF) training opportunities in associated beamforming training (A-BFT) slots. However, due to limited number of A-BFT slots, BF training suffers from a severe collision issue, especially in dense networks, which results in a low channel utilization in the A-BFT stage. To achieve the maximum channel utilization, it is of significance to allocate A-BFT slots efficiently. Therefore, in this paper, we propose an analytical model to analyze IEEE 802.11 ad medium access control (MAC) protocol in BF training stage. In particular, we analyze the successful transmission probability and channel utilization of IEEE 802.11 ad MAC protocol in the dense network. Based on theoretical analysis, we provide the optimal number of A-BFT slots. In addition, theoretical analysis indicates that the maximum channel utilization in the A-BFT stage is barely e−1which is the same as that of slotted ALOHA protocol. Simulation results are provided to validate the accuracy of the analytical model and theoretical analysis.

This study presents a new machine learning (support vector machine (SVM))‐based cooperative spectrum sensing (CSS) model, which utilises the methods of user grouping, to reduce cooperation overhead and effectively improve detection performance. Cognitive radio users were properly grouped before the cooperative sensing process using energy data samples and an SVM model. The resulting user group which participates in cooperative sensing procedures is safe, less redundant, or the optimised user group. Three grouping algorithms are presented in this study. The first grouping algorithm divides normal and abnormal users (malicious and severely fading users) into two groups. The second grouping algorithm distinguishes redundant and non‐redundant users. The third grouping algorithm establishes an optimisation model with the objective of minimising average correlation within subsets. All users are then divided into a specific number of optimised groups, only one of which is required for cooperative sensing in each time. The performances of the three algorithms were quantified in terms of the average training time, classification speed and classification accuracy. Experimental results showed the proposed algorithms achieved their intended function and outperformed a conventional machine learning‐based CSS model (proposed by Karaputugala et al. ) in terms of security, energy consumption, and sensing efficiency.

Hybrid beamforming (BF) is a widely considered strategy to enable downlink multiuser transmission for mmWave communication systems. However, current mmWave WiFi standard, the IEEE 802.11 ad, does not support hybrid BF because it could only serve one user at a time. Thus, it is important to implement hybrid BF based on IEEE 802.11.ad such that it could be applied in future mmWave WiFi. In this paper, we propose a hybrid BF scheme compatible with the IEEE 802.11 ad, and then analyze its BF overhead and throughput gain. Theoretical analysis and simulation results show that with the increasing number of users, BF overhead increases linearly, whereas the throughput gain increases and then decreases. Specifically, we analyze the tradeoff between the hybrid BF overhead and the throughput gain of multiuser transmission enabled by hybrid BF based on an IEEE 802.11 ad setting. Our finding suggests that there is an optimal number of users that a hybrid BF enabled mmWave communication systems should support.

Interference alignment (IA) is a scheme to approach the capacity at high signal-to-noise ratio (SNR) in multiuser multiple-input multiple-output (MIMO) interference networks. To implement the IA scheme in a frequency-division duplexing (FDD) system, transmitter channel state information (CSIT) is fed back from the receiver with finite bits. However, such CSIT is subject to quantization errors and delays of feedback channels. In this paper, we verify that interference leakage is bounded by chordal distance in the MIMO channel. Besides, a joint real Grassmannian quantization strategy is proposed to reduce chordal distance to improve CSIT quality. Meanwhile, under the noise-limited criterion, the lower bound of the codebook size of our proposed strategy is much smaller than that of the conventional complex Grassmannian quantization strategy. Simulations demonstrate that our proposed strategy provides substantial performance gains compared with the conventional strategy.

Interference alignment (IA) is a scheme to achieve degrees of freedom (DOF) of interference network at high signal-to-noise ratio (SNR). In order to implement IA scheme in frequency-division duplexing (FDD) system, receivers feedback channel state information to transmitters. The key problem is to acquire accurate transmitter channel state information (CSIT) in the presence of the quantization error. In this paper, a joint real Grassmannian quantization strategy is proposed to reduce codebook size in single-input single-output (SISO) frequency-selective channel with K user. More concretely, this strategy quantizes the real part and imaginary part of channel vector respectively to reduce the chordal distance. Meanwhile, a noise-limited criterion is assumed that interference leakage is smaller than thermal noise. Under this criterion, the codebook size using the proposed strategy is much smaller than the codebook size using conventional complex Grassmannian quantization strategy. With the same codebook size, simulations show a significant sum rate gain at high SNR compared with the conventional strategy.