Judicious resource allocation can effectively enhance federated learning (FL) training performance in wireless networks by addressing both system and statistical heterogeneity. However, existing strategies typically rely on block fading assumptions, which overlook rapid channel fluctuations within each round of FL gradient uploading, leading to a degradation in FL training performance. Therefore, this paper proposes a small-scale-fading-aware resource allocation strategy using a multi-agent reinforcement learning (MARL) framework. Specifically, we establish a one-step convergence bound of the FL algorithm and formulate the resource allocation problem as a decentralized partially observable Markov decision process (Dec-POMDP), which is subsequently solved using the QMIX algorithm. In our framework, each client serves as an agent that dynamically determines spectrum and power allocations within each coherence time slot, based on local observations and a reward derived from the convergence analysis. The MARL setting reduces the dimensionality of the action space and facilitates decentralized decision-making, enhancing the scalability and practicality of the solution. Experimental results demonstrate that our QMIX-based resource allocation strategy significantly outperforms baseline methods across various degrees of statistical heterogeneity. Additionally, ablation studies validate the critical importance of incorporating small-scale fading dynamics, highlighting its role in optimizing FL performance.

Semantic communication has been introduced into collaborative perception systems for autonomous driving, offering a promising approach to enhancing data transmission efficiency and robustness. Despite its potential, existing semantic communication approaches predominantly rely on analog transmission models, rendering these systems fundamentally incompatible with the digital architecture of modern vehicle-to-everything (V2X) networks and posing a significant barrier to real-world deployment. To bridge this critical gap, we propose CoDS, a novel collaborative perception framework based on digital semantic communication, designed to realize semantic-level transmission efficiency within practical digital communication systems. Specifically, we develop a semantic compression codec that extracts and compresses task-oriented semantic features while preserving downstream perception accuracy. Building on this, we propose a novel semantic analog-to-digital converter that converts these continuous semantic features into a discrete bitstream, ensuring integration with existing digital communication pipelines. Furthermore, we develop an uncertainty-aware network (UAN) that assesses the reliability of each received feature and discards those corrupted by decoding failures, thereby mitigating the cliff effect of conventional channel coding schemes under low signal-to-noise ratio (SNR) conditions. Extensive experiments demonstrate that CoDS significantly outperforms existing semantic communication and traditional digital communication schemes, achieving state-of-the-art perception performance while ensuring compatibility with practical digital V2X systems.

With the advancement of 5G networks, the deploy-ment of Internet of Things (IoT) technology has seen significant growth. Blockchain technology, recognized for its strong security features, is increasingly utilized within the IoT domain. However, the current IoT landscape is characterized by challenges such as substantial resource consumption, limited throughput capacity, and insufficient security protocols, which hinder its optimal per-formance. Towards addressing such problems, we propose a con-sensus algorithm called Proof-of-GoS (PoG) based on the grade of service (GoS), in which a node must have a service score over a set score threshold to be allowed to join the consensus process. The correct behavior of a node results in a reward, while any malicious actions result in penalties. Finally, we simulate a network to evalu-ate the performance and security of PoG and compare it with sev-eral existing consensus algorithms. The experimental findings in-dicate that the proposed PoG consensus algorithm retains the fun-damental security properties of blockchain and outperforms the state-of-the-art consensus mechanisms.

Age of information (AoI), a metric for data freshness in status update systems, has received growing attention in various applications. This paper focuses on dynamic power control to minimize the average AoI of all users in a sum-power constrained downlink network, where each user has multi-level selectable powers in every slot. By relaxing instantaneous sum-power constraint to a time-averaged sum-power constraint, we decompose the Lagrangian minimization problem into multiple independent power allocation subproblems with each corresponding to a particular user. We show that the optimal policy of each subproblem under a given Lagrange multiplier holds a multi-threshold property, based on which the full indexability property can be possessed by every subproblem. By comparing the Whittle indices and the Lagrange multiplier, the full indexability allows us to obtain the Lagrange multiplier which can effectively utilize the power budget. Given this, a low-complexity power allocation approach is proposed to solve the problem. Moreover, we prove the proposed approach is asymptotic optimality when the number of selectable powers are three. Simulation results verify the analysis and show that our proposed approach outperforms benchmark policies.

Stand-alone perception systems in autonomous driving suffer from limited sensing ranges and occlusions at extended distances, potentially resulting in catastrophic outcomes. To address this issue, collaborative perception is envisioned to improve perceptual accuracy by using vehicle-to-everything (V2X) communication to enable collaboration among connected and autonomous vehicles and roadside units. However, due to limited communication resources, it is impractical for all units to transmit sensing data such as point clouds or high-definition video. As a result, it is essential to optimize the scheduling of communication links to ensure efficient spectrum utilization for the exchange of perceptual data. In this work, we propose a deep reinforcement learning-based V2X user scheduling algorithm for collaborative perception. Given the challenges in acquiring perceptual labels, we reformulate the conventional label-dependent objective into a label-free goal, based on characteristics of 3D object detection. Incorporating both channel state information (CSI) and semantic information, we develop a double deep Q-Network (DDQN)-based user scheduling framework for collaborative perception, named SchedCP. Simulation results verify the effectiveness and robustness of SchedCP compared with traditional V2X scheduling methods. Finally, we present a case study to illustrate how our proposed algorithm adaptively modifies the scheduling decisions by taking both instantaneous CSI and perceptual semantics into account.

Purely chromatic background images are widely used in computer wallpapers and advertisements, leading to issues such as copyright infringement and the loss of interest of holders. Image hashing is a technique used for comparing the similarity between images, and is often used for image verification, search, and copy detection due to its insensitivity to subtle changes in the original image. In a purely chromatic background image, the central detail of the image is the primary part and the key for copyright authentication. As the perception hash (pHash) algorithm only retains the low-frequency portion of the discrete cosine transform (DCT) matrix, it is unsuitable for purely chromatic background images. To deal with this issue, we propose an improved perception hash (ipHash) algorithm to enhance the universality of the algorithm by extracting purely chromatic background image features. Meanwhile, the development of image hashing is restricted due to the requirement of a trusted third party. To solve this issue, a secure blockchain-based image copyright protection scheme is designed. It realizes the copyright authentication and traceability, and overcomes the issue of a lack of trusted third parties. Experimental results show that the proposed method outperforms the state-of-theart image copyright protection schemes.

In this brief, we propose a deep learning-based performance testing framework to minimize the number of required test modules while guaranteeing the accuracy requirement, where a test module corresponds to a combination of one circuit and one stimulus. First, we apply a deep neural network (DNN) to establish the mapping from the response of the circuit under test (CUT) in each module to all specifications to be tested. Then, the required test modules are selected by solving a 0–1 integer programming problem. Finally, the predictions from the selected test modules are combined by a DNN to form the specification estimations. The simulation results validate the proposed approach in terms of testing accuracy and cost.

This paper considers hybrid beamforming in multiple-input multiple-output integrated sensing and communications systems. In particular, the transmit hybrid beamformers are jointly designed with digital receive beamformers of users by maximizing the ratio of minimum mainlobe level to peak sidelobe level of the transmit beampattern, under constraints on the transmission power and signal-to-interference-plus-noise ratio requirements of users. In order to deal with the resulting nonconvex problem, a computationally efficient algorithm is developed under the framework of consensus alternating direction method of multipliers, by deriving the solution of each subproblem. The proposed design is verified by simulation results.

Cooperative perception has been shown an effective approach to address the perception limitation problem faced by the individual perception in the era of autonomous driving. Considering a two-source two-hop cooperative perception vehicular network, we investigate the average age of information (AoI) with different automatic repeat-request (ARQ) strategies in this paper. We formulate the packet transmission process as a Markov chain, which allows us to establish linear equations about the first and second moments of all states’ residual waiting time for the destination to receive a new update packet. Then, we derive the average AoI based on the analytical solution to the equations. Furthermore, the analysis is applied to a special case of the single-source two-hop cooperative perception system. Simulation results show that the optimal strategy is neither non-ARQ nor infinite-ARQ, but truncated ARQ, which means that there exists a finite retransmission limit to minimize the average AoI, implying that better cooperative perception can be achieved by optimizing the retransmission limit, especially in the single-source two-hop situation.

This article focuses on power allocation and sampling rate control in a spectrum-sharing vehicle-to-vehicle (V2V) status update network, where data packets are sampled in batches at the transmitter of the V2V links. In particular, we aim to minimize the overall power consumption while satisfying the age of information (AoI) requirement of all links. First, we analyze the average AoI of the resulting queueing system with periodical packet batch arrivals and geometrically distributed packet service time. Then, the primal problem is decomposed into two subproblems, i.e., sampling rate optimization and transmit power optimization. Finally, a computationally efficient algorithm with polynomial-time complexity is developed that optimally solves the two subproblems and, thus, solves the original problem with global optimality. Simulation results validate our average AoI analysis and the proposed algorithm.

In this paper, we investigate the problem of age-of-information (AoI)-aware dynamic user scheduling in vehicular networks based on soft reinforcement learning, where multiple vehicle-to-infrastructure (V2I) downlinks share the spectrum resource. To address the slow convergence and local optimality problem that is usually faced by traditional reinforcement learning, we formulate the AoI-aware user scheduling problem as a sequential decision making problem and then use the soft actor-critic (SAC) reinforcement learning algorithm to address it. The agent, i.e., the road side unit (RSU), chooses an appropriate V2I link to occupy the spectrum to send data at each slot to decrease the AoI outage probability of the status update system in vehicular networks. By maximizing the expected return and policy entropy, the agent can converge fast to an efficient solution while holding some robustness to cope with the differences between actual and training environments. Simulation results validate the proposed scheme in terms of convergence, effectiveness, and robustness.

Reinforcement learning has been widely used to train a sequential power control policy from simulation environment in Internet of Vehicles. However, disturbance is usually inevitably introduced when the agent getting into the practical environment from the simulation environment, which leads to a critical challenge when multiple links share a common spectrum. This paper is dedicated to addressing this issue in a two-pronged way. On one hand, we set the aim of policy learning as minimizing the network transmission outage probability from a risk-sensitive perspective. On the other hand, we propose a meta soft actor-critic based power control scheme, where the key hyperparameter is auto-adjusted to adapt to environment variations and L2 regulation is taken in the loss function of critic network to avoid overfitting to the simulation environment. Simulation results show that, the proposed algorithm achieves a higher successful transmission probability under the same conditions and is more robust under disturbed environment, than the baseline schemes.

Indoor positioning system (IPS) plays an important role in the applications of Internet of Things (IoT), including intelligent hospital, logistics, and warehousing. Ultrawideband (UWB)-based IPS has shown superior performance due to its strong multipath resistance and high temporal resolution. However, the non-line-of-sight (NLOS) situations noticeably degrade both the positioning accuracy and the communication reliability. To address this issue, we first propose a support vector machine (SVM)-based channel detection method to distinguish the line-of-sight (LOS) and NLOS conditions. Then, one base station (BS)-based distance and angle positioning algorithm with extended Kalman filter (DAPA-EKF) in NLOS environment is proposed. For the LOS environment, least squares (LSs) with EKF processing of acceleration (LS-AEKF) and velocity (LS-VEKF) are developed. To further improve the performance, the combination of time difference of arrival (TDOA) and KF in LOS environment is proposed. Simulation results show that the positioning accuracy of the proposed algorithm is improved in various environments. Finally, validated using more than 1000 testing positions, the positioning accuracy of LS-AEKF is 73.8%–74.1% higher than that of LS-VEKF among the two proposed algorithms in terms of three or four BSs metrics.

In this article, we investigate sequential power allocation over fast varying channels for mission-critical applications, aiming to minimize the expected sum power while guaranteeing the transmission success probability. In particular, a reinforcement learning framework is constructed with appropriate reward design so that the optimal policy maximizes the Lagrangian of the primal problem, where the maximizer of the Lagrangian is shown to have several good properties. For the model-based case, a fast converging algorithm is proposed to find the optimal Lagrange multiplier and thus the corresponding optimal policy. For the model-free case, we develop a three-stage strategy, composed in order of online sampling, offline learning, and online operation, where a backward$Q$-learning with full exploitation of sampled channel realizations is designed to accelerate the learning process. According to our simulation, the proposed reinforcement learning framework can solve the primal optimization problem from the dual perspective. Moreover, the model-free strategy achieves a performance close to that of the optimal model-based algorithm.

In this paper, a non-orthogonal multiple access (NOMA) based downlink vehicle-to-infrastructure network is considered. Particularly, we focus on the specific case of two users, one of which requires reliable road-safety-critical data transmission while the other pursues high-capacity services, with extension to multi-user scenarios. Leveraging only slow fading of channel state information, the transmit powers and target rates are jointly optimized to maximize the expected sum throughput of the capacity hungry user, with consideration of the payload delivery outage probability of the reliability sensitive user. The optimization is formulated as an unconstrained single-objective sequential decision problem via introducing a dual variable. A dynamic programming based algorithm is then designed to derive the optimal policy that maximizes the Lagrangian. Afterwards, a bisection search based method is proposed to find the optimal dual variable. The proposed scheme is shown by numerical results to be superior to the baseline methods in terms of the expected return, performance region, and objective value.

Positioning technology is essential for promoting intelligence in many residential, commercial, and industrial application scenarios. To improve the accuracy of indoor positioning, researchers have proposed many localization schemes based on the fusion of sensors. However, most existing methods focus on integrating more sensors instead of further extracting the original data. In this paper, we propose an efficient cooperative positioning algorithm for None-Line-of-Sight (NLOS) environments. Firstly, a multi-scenarios NLOS detection approach is introduced based on the channel impulse response of ultra-wideband. Secondly, a cycle least-squares positioning algorithm is proposed to maximize the utilization of the original ranging information. Thirdly, we propose a cooperative positioning algorithm based on location information sharing to minimize the impact of NLOS propagation. The simulation results demonstrate that our method outperforms all baseline methods with a large margin in terms of both stability and accuracy.

Vehicular communications face a tremendous challenge in guaranteeing low latency for safety-critical information exchange due to fast varying channels caused by high mobility. Focusing on the tail behavior of random latency experienced by packets, latency violation probability (LVP) deserves particular attention. Based on only large-scale channel information, this paper performs spectrum and power allocation to maximize the sum ergodic capacity of vehicle-to-infrastructure (V2I) links while guaranteeing the LVP for vehicle-to-vehicle (V2V) links. Using the effective capacity theory, we explicitly express the latency constraint with introduced latency exponents. Then, the resource allocation problem is decomposed into a pure power allocation subproblem and a pure spectrum allocation subproblem, both of which can be solved with global optimum in polynomial time. Simulation results show that the effective capacity model can accurately characterize the LVP. In addition, the effectiveness of the proposed algorithm is demonstrated from the perspectives of the capacity of the V2I links and the latency of the V2V links.

Proximity-based communications have been considered as a promising candidate for supporting vehicular communications. However, the high mobility in vehicular communications makes it hard to obtain accurate fast varying channel information, which poses significant challenges on meeting the requirements of high reliability and low latency. Based only on slowly varying large-scale fading channel information, this paper performs a reliability and latency aware resource allocation, which maximizes the throughput of vehicular-to-network (V2N) links while satisfying reliability and latency requirements of vehicular-to-vehicular (V2V) links. First, we obtain steady-state reliability and latency expressions based on queueing analysis for each possible spectrum reusing pair of a V2N link and a V2V link. Then, an optimal power allocation algorithm is developed for each possible spectrum reusing pair. Afterward, the spectrum reusing pattern is optimized by addressing a polynomial time solvable bipartite matching problem. The simulation results demonstrate the accuracy of the proposed queueing analysis and confirm the effectiveness of the proposed resource allocation comparing with available strategies.

Vehicular communications have stringent latency requirements on safety-critical information transmission. However, lack of instantaneous channel state information due to high mobility poses a great challenge to meet these requirements and the situation gets more complicated when packet retransmission is considered. Based on only the obtainable large- scale fading channel information, this paper performs spectrum and power allocation to maximize the ergodic capacity of vehicular-to- infrastructure (V2I) links while guaranteeing the latency requirements of vehicular-to-vehicular (V2V) links. First, for each possible spectrum reusing pair of a V2I link and a V2V link, we obtain the closed- form expression of the packets' average sojourn time (the queueing time plus the service time) for the V2V link. Then, an optimal power allocation is derived for each possible spectrum reusing pair. Afterwards, we optimize the spectrum reusing pattern by addressing a polynomial time solvable bipartite matching problem. Numerical results show that the proposed queueing analysis is accurate in terms of the average packet sojourn time. Moreover, the developed resource allocation always guarantees the V2V links' requirements on latency.

This paper investigates multi-antenna beamforming and time allocation to maximize the network energy-efficiency (EE) in a wireless powered communication network (WPCN). Since the EE optimization problem has an inherent fractional form, it is difficult to obtain the optimal value directly due to the lack of convexity in the objective function. To overcome this challenge, we first convert the original problem into a more tractable one by the fractional programming. Then, two schemes are proposed to find the optimal value. In the first scheme, the iterative value is updated according to the EE based on energy beamforming and time allocation derived in the current iteration. In the second one, the optimal value is obtained by consecutively shrinking the region in which it is located. Simulation results show that the proposed two schemes can improve the network EE significantly compared with the algorithm that only pursues high throughput. In addition, it is shown that the two schemes have simlilar performance in the network EE. However, the computation complexity of the first one is lower than that of the second one.

In this paper we propose a new analog beamforming structure by switching on or off each of multiple transmit antennas according to channel state information. The proposed analogue beamforming can significantly reduce the high cost, high power and bulky analogue phase-shifters which are employed in analog massive MIMO systems. On one hand, the high performance low cost commercial switch devices make our architecture easy to implement, saving both system cost and space. On the other hand, our on-off analog beamforming (OABF) can achieve good performance with low complexity algorithms. Specifically, we first propose two SNR-maximization algorithms, which determines the on-off state of each switch under per-antenna power constraint. After that, we theoretically prove our on-off analog beamforming scheme can achieve full system diversity gain and array gain with polynomial complexity. The simple structure of OABF makes the massive MIMO much easier to implement, at a cost of small constant rate loss.

We aim to maximize system throughput subject to constraints on both short-term and long-term fairness in terms of Jain's index in single cell downlink OFDMA systems, where the transmission power is fixed. While it is accepted that short-term fairness implies long-term fairness, we find that this is not always true. Noting that long-term performance metric is the average of short-term ones, we point out that it depends on the averaging method and the fairness definition. We prove that short-term throughput Jain's index implies long-term throughput Jain's index. Therefore, we can remove the long-term fairness constraint if it is looser than the short-term constraint. Otherwise, we heuristically replace the long-term fairness constraint by a cumulative fairness constraint. We relax the considered discrete subchannel and slot allocation problem into a continuous convex problem, which can be efficiently solved. Then, the discrete resource allocation is derived by rounding the optimal solution. The analysis indicates that the rounding error is small. Simulation results show that we obtain a good suboptimal solution with small deviations from the optimal relaxed system throughput and the Jain's index constraints. Moreover, comparing with the strategies that take into account only long-term fairness, we guarantee both long-term and short-term fairness.

In wireless resource allocation, improving system throughput and simultaneously enhancing user fairness are two fundamental but contradictory objectives. As for fairness, both short-term and long-term fairness are of significant importance. However, less effort has been dedicated to explore the optimal tradeoff between system throughput and the two mentioned fairness in terms of widely used Jain's index. In this context, we aim to maximize system throughput subject to constraints on both short-term and long-term fairness in single cell downlink OFDMA systems. The difficulty of this issue lies in that the considered subchannel and slot allocation problem is a nonlinear integer programming problem, and furthermore seems to be non-causal. To overcome these challenges, we first relax the integer variables. Second, we prove that short-term fairness ensures long-term fairness so that the long-term fairness constraint is redundant and can be removed. Third, the problem is decomposed into a sequence of short-term convex optimization problems that can be easily solved. Numerical results show that the proposed method achieves a good suboptimal solution with small deviations from the optimal relaxed system throughput and the Jain's index constraint.

Enhancing system throughput and improving user fairness are two basic but contradictory objectives for resource allocation in wireless cellular networks. To obtain an efficient tradeoff between these two goals, Network Utility Maximization (NUM) framework has been adopted with log-utility to obtain proportional fairness among all the users in the network. However, such tradeoff can not control the bias towards throughput or fairness. In this paper, we focus on α-fairness NUM in Soft Frequency Reuse (SFR) based cellular networks, where SFR is an attractive frequency reuse technique to mitigate Inter-Cell-Interference (ICI) and α can be utilized to adjust the tradeoff. The difficulty of the considered issue comes from that it is a Mixed Integer Programming (MIP) problem taking into account both intra-cell user scheduling and inter-cell user association. To overcome this challenge, the α-fairness NUM problem is decomposed into two subproblems, which are dealt with one by one. First, maximize intra-cell utility by user scheduling and second, maximize network utility by distributed user association. Numerical results show that the proposed algorithm approaches the optimal solution of the α-fairness NUM problem. Also, we get a better tradeoff between throughput and fairness, where fairness is measured by Jain's index. Particularly, we improve the maximum Jain's index from about 0.3 to about 1.

Traditional load balancing schemes only considered two cells cooperation that is less likely to succeed. A novel scheme, load balancing by cells- cooperation-chains (C$^3$LB), is proposed. C$^3$LB establishes multi-level cells-cooperation-chains (C$^3$) to transfer traffic and extents the conditions of traffic transfer. We formulate a minimum-level C$^3$ selection problem and propose a simple algorithm to solve it. In addition, we present a C$^3$LB protocol to execute the found C$^3$. Numerical results show that as the maximum allowed levels of C$^3$ increase, the system call blocking probability decreases. Finally, we give the proposed value of the maximum allowed levels.