In the Internet of Vehicles (IoV), vehicles have the capability to offload their computational tasks to the Mobile Edge Computing (MEC) servers in order to reduce service delay. However, the majority of existent task offloading and computational resource allocation schemes are static and lack consideration of the heterogeneous nature of tasks. Furthermore, in scenarios involving both collaborative and competitive resource utilization, there remains considerable room for performance enhancement for delay-sensitive tasks. To address these challenges, this paper proposes a novel Global Heterogeneous Multi-Agent Reinforcement Learning (GHMARL) that is an enhancement to the general MARL. In GHMARL, each vehicle and MEC server is represented by an agent, and intelligent collaboration and dynamic resource allocation are employed to balance resource usage and delay performance. In particular, GHMARL introduces a global Critic network and a local Critic network, working in a collaborative manner. The former is responsible for guiding the overall system performance to ensure the service delay performance, and the latter is responsible for MEC servers’ performance to ensure the resource usage efficiency. Simulation results demonstrate that, in comparison with alternative schemes, GHMARL significantly enhances the overall system performance, particularly with regard to resource usage efficiency. Furthermore, GHMARL offers distinct advantages in balancing task delay and resource consumption under various system dynamics, making it a robust solution to address issues of resource wastage and delay violations for IoV systems.

Large language models are increasingly deployed across mobile and edge environments, where privacy-sensitive and heterogeneous user data raise critical concerns of copyright infringement, data leakage, and regulatory non-compliance. Ma chine unlearning has thus emerged as an essential capability to remove the influence of specific data without full retraining. However, two key challenges remain open: 1) how to quantify unlearning to enable data valuation without retraining, especially since the massive scale of pretraining makes it infeasible to evaluate the contribution of individual data samples in advance, and 2) how to verify the correctness without retraining to ensure that third-party auditors can efficiently confirm the complete removal of targeted data influence. To address the aforementioned challenges, in this paper, we design a dual-stage machine unlearning framework to quantify the contribution of forgotten data and certify data removal without full retraining, serving as an auditing layer for first-order unlearning methods. Specifically, we design a run-time Shapley value-based unlearned data evaluation mechanism that utilizes a first-order approximation strategy to estimate the marginal contribution of forgotten samples. Moreover, we propose a proof of unlearning mechanism that generates compact, auditable artifacts of the unlearning process to efficiently verify that the targeted data influence has been completely removed. Compared with five state-of-the-art unlearning baselines, our approach achieves effectiveness in data valuation, stronger guarantees of removal correctness, and lower computational overhead.

Due to the down-tilt of BS antennas to serve ground users in existing networks, aerial user equipments (AUEs) are only supported through the side lobes, which leads to insufficient aerial coverage. Fortunately, intelligent reflecting surfaces (IRSs) possess the remarkable ability to offer extra signal power to enhance AUEs’ coverage. However, to fully realize the potential of the IRS, its deployment is contingent upon the radiation pattern of the BS which substantially modifies the network topology. This paper proposes a novel IRS-based network model to serve AUEs by constructing the virtual LoS air-to-ground links to provide targeted signal for AUEs, where IRSs are practically distributed in the BS main lobe to effectively utilize the BS radiation power. Specifically, the distribution of IRSs is modeled by a variant of the Matérn cluster process (MCP), based on which the correlated interference from BSs and IRSs introduced by their location correlation is theoretically characterized. Furthermore, based on a concise two-lobe model for BS antenna gain, the effective distribution area of IRSs is derived as a ring concentric with the cell, which exhibits tunability in accordance with the beamwidth and the tilt angle of the BS antenna. In addition, the framework is characterized for analyzing the correlated interference from BSs and IRSs through the accurate integration of the power correlation associated with both direct paths and IRS-reflected paths. Leveraging stochastic geometry, theoretical expressions of network metrics are derived on the IRS-assisted AUE networks. Numerical results demonstrate the effectiveness of the proposed scheme, as manifested by the significant elevation in the coverage probability of AUEs by 67% when the number of elements per IRS hitsN= 2000.

Score-based diffusion models represent a significant variant within the family of diffusion models and have found extensive application in the increasingly popular domain of generative tasks. Recent investigations have explored the denoising potential of diffusion models in semantic communications. However, in previous paradigms, noise distortion in the diffusion process does not match precisely with digital channel noise characteristics. In this work, we introduce the ScoreBased Channel Denoising Model (SCDM) for Digital Semantic Communications (DSC). SCDM views the distortion of constellation symbol sequences in digital transmission as a score-based forward diffusion process. We design a tailored forward noise corruption to better align digital channel noise properties in the training phase. During the inference stage, the well-trained SCDM can effectively denoise received semantic symbols under various SNR conditions, reducing the difficulty for the semantic decoder in extracting semantic information from the received noisy symbols and thereby enhancing the robustness of the reconstructed semantic information. Experimental results show that SCDM outperforms the baseline model in PSNR, SSIM, and MSE metrics, particularly at low SNR levels. Moreover, SCDM reduces storage requirements by a factor of 7.8. This efficiency in storage, combined with its robust denoising capability, makes SCDM a practical solution for DSC across diverse channel conditions.

Integrated sensing and communication (ISAC) is emerging as a crucial technology for 6G networks, with channel state information (CSI) based ISAC playing a vital role. These systems utilize various AI models to process and analyze the CSI extracted from wireless communication signals, thereby enabling monitoring of physical spaces and human activities. However, due to the costs and privacy issues, collecting sufficient training CSI data is challenging. In response, this paper proposes a data augmentation system based on the diffusion model. Specifically, we first use the limited samples collected from real-world ISAC scenarios to train a conditional diffusion model, which then generates new samples to enhance sample quantity. Subsequently, we train another diffusion model with noise-free data to reduce noise in these generated samples, thereby further enhancing the sample quality. The evaluation based on the real-world CSI data validates that our approach can effectively enhance the data from both quantity and quality perspectives, thereby supporting the model training in ISAC networks.

With the rapid development of Internet of Things (IoT) technology, an increasing number of resource-constrained devices operate in dynamic and heterogeneous network environments, posing challenges for efficient image transmission. Multi-user semantic communication (SC) enables reduced bandwidth consumption and enhanced noise resilience by understanding the intrinsic meaning of information and sharing common semantic features across devices, offering great potential for widespread applications in various IoT scenarios. However, current multi-users SC approaches for image transmission lack adaptability and fail to consider both content and style features, leading to degraded image reconstruction quality. Moreover, semantic redundancy among devices remains underutilized, limiting bandwidth efficiency in IoT networks. To address these limitations, in this paper, a novel multi-user content-style adaptive semantic communication system for image transmission in IoT scenarios is proposed. Specifically, a dual-branch semantic information extraction and adaptive recovery scheme is first established, which simultaneously captures and adaptively fuses semantic content and style features to improve reconstruction quality. Secondly, an adaptive common information extraction and enhanced coding module is introduced for resource-limited IoT devices, which dynamically adjusts the transmission rate based on varying channel conditions and the computational capabilities of different users, further optimizing communication performance. Finally, experimental results show that the proposed method improves peak signal-to-noise (PSNR) by at least 10% under poor SNR conditions for multi-users semantic communication, compared to baseline methods.

Recently proliferated deep learning-based semantic communications (DLSC) focus on how transmitted symbols efficiently convey a desired meaning to the destination. However, the sensitivity of neural models and the openness of wireless channels cause the DLSC system to be extremely fragile to various malicious attacks. This inspires us to ask a question: “Can we further exploit the advantages of transmission efficiency in wireless semantic communications while also alleviating its security disadvantages?”. Keeping this in mind, we propose SemEntropy, a novel method that answers the above question by exploring the semantics of data for both adaptive transmission and physical layer encryption. Specifically, we first introduce semantic entropy, which indicates the expectation of various semantic scores regarding the transmission goal of the DLSC. Equipped with such semantic entropy, we can dynamically assign informative semantics to Orthogonal Frequency Division Multiplexing (OFDM) subcarriers with better channel conditions in a fine-grained manner. We also use the entropy to guide semantic key generation to safeguard communications over open wireless channels. By doing so, both transmission efficiency and channel security can be simultaneously improved. Extensive experiments over various benchmarks show the effectiveness of the proposed SemEntropy. We discuss the reason why our proposed method benefits secure transmission of DLSC, and also give some interesting findings, e.g., SemEntropy can keep the semantic accuracy remain 95% with 60% less transmission.

Reconfigurable intelligent surface (RIS)-assisted multiple-input multiple-output (MIMO) has recently emerged as a promising candidate to improve the energy and spectral efficiency of Internet of Things (IoT) systems. This paper aims to develop an efficient channel estimation scheme for RIS-assisted MIMO IoT systems within structured Bayesian learning framework. However, the high-dimensional channel matrix with considering its underlying structured sparsity makes efficient channel estimation scheme design a challenging task. To deal with it, we firstly formulate the cascaded RIS-assisted MIMO channel estimation as a generic sparse signal recovery problem with considering the constructed two-level block-structured sparsity of channels. Secondly, we design a flexible prior model to characterize such structured sparsity of channels, in which hierarchical hyperparameters are introduced, and the iterative Bayesian learning-based method is developed to autonomously estimate channels and the hyperparameters associated with the prior model. Thirdly, to relieve the high-computational complexity involving matrix inversion when calculating the posterior of channels, we develop efficient methods from two perspectives. On the one hand, an inverse-free method is developed by relaxed evidence lower bound (ELBO) maximization with an adjustable factor of reducing the gap between the standard ELBO and relaxed ELBO. On the other hand, a method of reducing the dimension of sparse representation matrix aided by external block-structured sparsity is developed. Finally, the computational complexity and convergence properties of the proposed methods are analyzed in detail. Simulation results are provided to verify the superiority of the devised channel estimation methods.

We investigate the coexistence of task-oriented and data-oriented communications in a IoT system that shares a group of channels, and study the scheduling problem to jointly optimize the weighted age of incorrect information (AoII) and throughput, which are the performance metrics of the two types of communications, respectively. This problem is formulated as a Markov decision problem, which is difficult to solve due to the large discrete action space and the time-varying action constraints induced by the stochastic availability of channels. By exploiting the intrinsic properties of this problem and reformulating the reward function based on channel statistics, we first simplify the solution space, state space, and optimality criteria, and convert it to an equivalent Markov game, for which the large discrete action space issue is greatly relieved. Then, we propose a Whittle’s index guided multi-agent proximal policy optimization (WI-MAPPO) algorithm to solve the considered game, where the embedded Whittle’s index module further shrinks the action space, and the proposed offline training algorithm extends the training kernel of conventional MAPPO to address the issue of time-varying constraints. Finally, numerical results validate that the proposed algorithm significantly outperforms state-of-the-art age of information (AoI) based algorithms under scenarios with insufficient channel resources.

As the proliferation of sophisticated task models in 5G empowered digital twin, it yields significant demands on fast and accurate model training over resource-limited wireless networks. It is vital to investigate how to accelerate the training process based on the salient features of practical systems, including heterogeneous data distributions and system resources both across devices and over time. To study the non-trivial coupling between participating device selection and their appropriate training parameters, we first characterize the dependency of convergence performance bound on system parameters, i.e., statistical structure of local data, mini-batch size and gradient quantization level. Based on the theoretical analysis, a training efficiency optimization problem is formulated subject to heterogeneous communication and computation capabilities among devices. To realize online control of training parameters, we propose an adaptive batch-size assisted device scheduling strategy, which prioritizes the selection of devices that offer good data utility and dynamically adjust their mini-batch sizes and gradient quantization levels adapting to network conditions. Simulation results demonstrate our proposed strategy can effectively speed up the training process as compared with benchmark algorithms.

The randomness and complexity of the wireless channel is challenging to meet the various quality of service (QoS) for different wireless communication application scenarios. Reconfigurable intelligent surface (RIS) technology has been proposed to achieve dynamic control of signal propagation over the wireless medium, and thus enables intelligent reconstruction of the channel environment. Moreover, age of information (AoI) has been proposed to quantify the timeliness of status update information accurately, which is new QoS metric. However, the AoI-driven statistical QoS guarantee problem in the RIS-enabled wireless network is not trivial and needs to be solved. In this paper, we employ the AoI violation probability to measure the reliability requirement for maintaining the freshness of status updates and derive its upper bound. Then, we formulate the AoI-driven effective capacity maximization problem. Finally, we transform the formulated problem into a signal-to-noise ratio (SNR) maximization problem, and further propose a twin delayed deep deterministic policy gradient (TD-DDPG) based joint optimization algorithm for obtaining the effective decisions on transmission power of device and the phase shift of RIS. Simulation results show that the TD-DDPG-based scheme has better performance than other traditional schemes.

This artilce aims to develop a differential private federated learning (FL) scheme with the least artificial noises added while minimizing the energy consumption of participating mobile devices. By observing that some communication efficient FL approaches and even the nature of wireless communications contribute to the differential privacy (DP) preservation of training data on mobile devices, in this paper, we propose to jointly leverage gradient compression techniques (i.e., gradient quantization and sparsification) and additive white Gaussian noises (AWGN) in wireless channels to develop a piggyback DP approach for FL over mobile devices. Even with the piggyback DP approach, information distortion caused by gradient compression and noise perturbation may slow down FL convergence, which in turn consumes more energy of mobile devices for local computing and model update communications. Thus, we theoretically analyze FL convergence and formulate an energy efficient FL optimization under piggyback DP, transmission power, and FL convergence constraints. Furthermore, we propose an efficient iterative algorithm where closed-form solutions for artificial DP noise and power control are derived. Extensive simulation and experimental results demonstrate the effectiveness of the proposed scheme in terms of energy efficiency and privacy preservation.

The scope of the 6G wireless communication system is envisioned to expand beyond delivering data to humans and towards connecting machines that constantly upload computation-intensive status updates to obtain real-time situational awareness. Under dynamic environments, the amount of useful information contained in status updates degrades over time, which could be measured based on the concept of age of information. In this paper, we develop an analytical framework to investigate the temporal value of status updates, in terms of the peak age of information. Given the temporal dynamics of observed physical process, the procedure of transmission and computing is modeled as tandem queues for both parallel processing and series processing modes at the edge server. The obtained closed-form expressions explicitly characterize the coupling among information generation, transmission, and usage, which can be exploited as performance metrics for task-oriented resource optimization. The accuracy of our analysis is verified with simulation results. Based on the theoretical analysis, we formulate an optimization problem to simultaneously minimize the age of status updates and energy consumption for multiple devices. Numerical results reveal that the computation and transmission time could be traded off to obtain timely status updates at low energy cost.

Abstract Unmanned aerial vehicles (UAVs) are employed as mobile relay nodes to enable timely remote monitoring by collecting information from monitoring devices and transferring the collected information to base station. The freshness of delivered information is critical to system performance, which can be quantified by the concept of age of information (AoI). Nevertheless, the fresher information comes at the cost of higher energy consumption at UAVs. Considering the limited onboard energy, it is essential to strike a balance between the age of delivered information and the required energy budget. here, both straight trajectory and circular trajectory of UAV are considered, and study a problem with the goal of supporting timely data collection while minimizing the energy consumption at UAV. The problem is formulated as a multi‐criteria optimization problem by jointly considering the aging of collected information, the trajectory planning of UAV and energy consumption at UAV. To solve the formulated problem, a solution procedure to find a sequence of Pareto‐optimal points is proposed. Simulation results demonstrate the Pareto‐optimal curve, which yields the energy‐efficient UAV trajectory for timely data collection.

Moving beyond just interconnected devices, the increasing interplay between communication and computation has fed the vision of real-time networked control systems. To obtain timely situational awareness, IoT devices continuously sample computation-intensive status updates, generate perception tasks and offload them to edge servers for processing. In this sense, the timeliness of information is considered as one major contextual attribute of status updates. In this paper, we derive the closed-form expressions of timeliness of information for computation offloading at both edge tier and fog tier, where two-stage tandem queues are exploited to abstract the transmission and computation process. Moreover, we exploit the statistical structure of Gauss-Markov process, which is widely adopted to model temporal dynamics of system states, and derive the closed-form expression for process-related timeliness of information. The obtained analytical formulas explicitly characterize the dependency among task generation, transmission and execution, which can serve as objective functions for system optimization. Based on the theoretical results, we formulate a computation offloading optimization problem at edge tier, where the timeliness of status updates is minimized among multiple devices by joint optimization of task generation, bandwidth allocation, and computation resource allocation. An iterative solution procedure is proposed to solve the formulated problem. Numerical results reveal the intertwined relationship among transmission and computation stages, and verify the necessity of factoring in the task generation process for computation offloading strategy design.

In a multi-user system, system resources should be allocated to different users. In traditional communication systems, system resources generally include time, frequency, space, and power, so multiple access technologies such as time division multiple access (TDMA), frequency division multiple access (FDMA), space division multiple access (SDMA), code division multiple access (CDMA), and non-orthogonal multiple access (NOMA) are widely used. In semantic communication, which is considered a new paradigm of the next-generation communication system, we extract high-dimensional features from signal sources in a model-based artificial intelligence approach from a semantic perspective and construct a model information space for signal sources and channel features. From the high-dimensional semantic space, we excavate the shared and personalized information of semantic information and propose a novel multiple access technology, named model division multiple access (MDMA), which is based on the resource of the semantic domain. From the perspective of information theory, we prove that MDMA can attain more performance gains than traditional multiple access technologies. Simulation results show that MDMA saves more bandwidth resources than traditional multiple access technologies, and that MDMA has at least a 5-dB advantage over NOMA in the additive white Gaussian noise (AWGN) channel under the low signal-to-noise (SNR) condition.

We investigate the coexistence of task-oriented and data-oriented communications in a IoT system that shares a group of channels, and study the scheduling problem to jointly optimize the weighted age of incorrect information (AoII) and throughput, which are the performance metrics of the two types of communications, respectively. This problem is formulated as a Markov decision problem, which is difficult to solve due to the large discrete action space and the time-varying action constraints induced by the stochastic availability of channels. By exploiting the intrinsic properties of this problem, we first simplify it and convert it to an equivalent Markov game, for which the large and discrete action space issue is greatly relieved. Then, we propose a Whittle's index guided multi-agent proximal policy optimization (WI-MAPPO) algorithm to solve the considered game, where the embedded Whittle's index module further shrinks the action space, and the proposed offline training algorithm extends the training kernel of the conventional MAPPO to address the issue of time-varying constraints.

The ubiquitous computing resource at UAVs and IoT devices can be exploited in conjunction to form a UAV-IoT edge computing system for low-cost and responsive environmental monitoring. Under stochastic computational task arrival at IoT devices, one major challenge is how to realize path control for multiple UAVs and energy efficient computation offloading in real time. Moreover, the freshness of obtained updates is of critical importance to the system performance under such time-critical scenarios. In this paper, we employ the concept of age of information (AoI) to quantify the timeliness of updates at IoT devices, and formulate an energy minimization problem by jointly considering UAV path planning, energy consumption of computation offloading and age evolution of updates. To solve the formulated problem, we propose a deep reinforcement learning based solution to achieve fast decision making. Simulation results show that the performance of proposed solution is competitive in terms of obtaining fresh updates at low energy cost.

In this paper, we propose a novel three-dimensional (3D) multi-confocal ellipsoid simulation model with uniform planar antenna array (UPA) for massive multiple-input multiple-output (MIMO) communication systems. Firstly, by employing the spherical wavefront, we characterize near-field effects including the angle of arrival (AoA) shifts and Doppler frequency variations in both space and time domains, and we derive the closed-form expressions of impulse responses of the theoretical model. Secondly, we develop a corresponding simulation model with finite and discrete scatterers within a cluster for the theoretical model. Additionally, we develop the cluster evolution algorithm with a 3D extension of our previously proposed scheme for modeling non-stationary properties of clusters. Their impacts on the proposed channel model are investigated via key statistical properties, e.g., the spatial-temporal cross-correlation function. Moreover, we also discuss the impacts of the range of offset angles and the number of scatterers within a cluster on statistical properties of the proposed simulation model. Finally, our numerical and simulation results show that our proposed simulation channel model is able to capture characteristics of massive MIMO channels while well agreeing with the results obtained from the theoretical modeling.

Over-the-air (OTA) radiated testing for multi-input multi-output (MIMO) capable mobile terminals has been actively discussed in the standardization in recent years, where multiprobe anechoic chamber (MPAC) method has been selected. Setting up a multiprobe configuration is costly, so finding ways to limit the number of probes will make the implementation of the test system simpler and cheaper. In this paper, two probe subset selection algorithms for three dimensional (3D) MPAC and fading emulator are proposed, namely, decremental selection algorithm (DSA) and error threshold selection algorithm based on alternating search (SAAS), where the goal is to minimize the number of probe antennas while ensuring the accuracy of the target channel emulation. Simulation results show that a small number of probe sets are selected under the given error threshold by the two algorithms, which greatly saves the cost of setup configuration. The performance of SAAS generally outperform that of DSA, especially when there are fewer probes selected.

In this paper, a QoS differentiation adaptive retransmission limits ARQ (QDARL-ARQ) is proposed to improve the efficiency of retransmission in conventional SR-ARQ for the IEEE 802.16e BWA systems. With a simple algorithm implemented based on the conventional SR-ARQ, QDARL-ARQ scheme is able to dynamically adjust the retransmission limits for services with different characteristics by considering their QoS requirements as well as the current system states simultaneously. This scheme aims to achieve lower packet error rate with restrained end-to-end delay in the time-variable and error prone wireless environment in comparison with conventional SR-ARQ. Several performance metrics of QDARL-ARQ are compared with conventional SR-ARQ in both single service scenarios and multiple services scenarios. The performance improvement due to QDARL-ARQ is evaluated through the IEEE 802.16e system level simulation, and the results clearly show that it can improve the performance of mean end-to-end delay, packet error rate and throughput, especially the retransmission efficiency. It can also be found that the conventional SR-ARQ is in fact a special instance of the QDARL-ARQ designed here.