Graph neural networks (GNNs) excel at modeling graph-structured data but often inherit and amplify biases, leading to substantial efforts in developing fair GNNs. However, most existing approaches assume full access to sensitive attribute information, which is often impractical in real-world scenarios due to privacy concerns or risks of discrimination. To address this limitation, this paper focuses on graph fairness with limited sensitive attribute information, ensuring applicability to real-world contexts where current methods fall short. Specifically, we introduce an innovative fairness optimization strategy, propose a novel framework named FGLISA, and provide a theoretical perspective linking limited sensitive attribute information access to fairness objectives, thus enabling fair graph learning in real-world applications with limited sensitive attribute information. Experiments on diverse real-world datasets and tasks validate the effectiveness of our approach in achieving both fairness and predictive performance.

Channel sounding is crucial for achieving Extremely High Throughput (EHT) and Ultra-high reliability (UHR) in next-generation Wi-Fi systems, i.e., Wi-Fi 7 and beyond. In Downlink Multi-User Multiple-Input Multiple-Output (DL MUMIMO) communications, data rate significantly deteriorates under time-varying channel with Doppler effect. Therefore, effective channel sounding mechanisms must balance the Channel State Information (CSI) overhead and CSI staleness, which is governed by the channel coherence time. Despite its critical importance, channel sounding optimization under time-varying channel conditions remains under-explored. This paper addresses this research gap by proposing a cross-layer optimization problem for the channel sounding period with the objective of maximizing data rate by considering the CSI overhead over the MAC layer and the channel capacity degradation over the PHY layer. This problem is then converted into an equivalent formulation leveraging the EHT sounding protocol, which can be solved efficiently using our proposed optimal search algorithm. Through simulations, we evaluate the baseline EHT sounding using outdated beamforming matrices and benchmark it against our proposed solution. The numerical results demonstrate that the channel sounding period optimization significantly reduces CSI overhead by up to 11% while boosting the average data rate by up to 8%.

Integrated sensing and communication systems face critical challenges, including limited bandwidth, power constraints, and varying communication conditions, which demand efficient data transmission and processing strategies. This paper introduces, ByteTrans, a novel joint optimization framework that integrates byte-level predictive modeling with adaptive model scheduling to maximize data transmission efficiency while adhering to communication and computational constraints. The proposed framework employs Transformer-based models to predict and compress data packets losslessly, leveraging the inherent redundancy in multi-modal network data. Such a unified data compression approach predicts occurring byte probabilities, encodes them as ranks using lossless entropy coding, and efficiently reduces data size and entropy across diverse modalities. Then, a dynamic adaptation strategy selects the optimal compression model based on packet characteristics and channel conditions, ensuring efficient operation across heterogeneous sensor environments. Experimental results validate that our scheme achieves compression rates exceeding 50%, while showcasing substantial reductions in communication time and bandwidth usage under both normal and adverse channel conditions. Furthermore, we effectively implement these models across various real-world edge sensors and servers, showcasing their practicality and efficiency in various network applications. By addressing the trade-offs between achieving lower compression ratios and limiting computational and energy consumption, this work establishes a scalable and robust solution for data management in multi-modal communication systems.

In this paper, deceptive signal-assisted private split learning is investigated. In our model, several edge devices jointly perform collaborative training, and some eavesdroppers aim to collect the model and data information from devices. To prevent the eavesdroppers from collecting model and data information, a subset of devices can transmit deceptive signals. Therefore, it is necessary to determine the subset of devices used for deceptive signal transmission, the subset of model training devices, and the models assigned to each model training device. This problem is formulated as an optimization problem whose goal is to minimize the information leaked to eavesdroppers while meeting the model training energy consumption and delay constraints. To solve this problem, we propose a soft actor-critic deep reinforcement learning framework with intrinsic curiosity module and cross-attention (ICM-CA) that enables a centralized agent to determine the model training devices, the deceptive signal transmission devices, the transmit power, and sub-models assigned to each model training device without knowing the position and monitoring probability of eavesdroppers. The proposed method uses an ICM module to encourage the server to explore novel actions and states and a CA module to determine the importance of each historical state-action pair thus improving training efficiency. Simulation results demonstrate that the proposed method improves the convergence rate by up to 3× and reduces the information leaked to eavesdroppers by up to 13% compared to the traditional SAC algorithm.

In this paper, a novel three dimensional (3D) positioning framework of fluid antenna system (FAS)-enabled unmanned aerial vehicles (UAVs) is developed. In the proposed framework, a set of controlled UAVs including an active UAV and four FAS-enabled passive UAVs cooperatively estimate the real-time 3D position of a target UAV. Here, the active UAV transmits a measurement signal to the passive UAVs via the reflection from the target UAV. Each passive UAV estimates the distance of the active-target-passive UAV link and selects an antenna port to share the distance information with the base station (BS), which calculates the real-time position of the target UAV. As the target UAV is moving due to its task operation, the controlled UAVs must optimize their trajectories and select optimal antenna port for transmitting the positioning information, aiming to estimate the real-time position of the target UAV. We formulate this problem as an optimization problem whose goal is to minimize the target UAV positioning error via optimizing the trajectories of all controlled UAVs and antenna port selection of passive UAVs. To address this problem, an attention-based recurrent multi-agent reinforcement learning (AR-MARL) scheme is proposed, which enables each controlled UAV to use the local Q function to determine its trajectory and antenna port while optimizing the target UAV positioning performance without knowing the trajectories and antenna port selections of other controlled UAVs. Different from current MARL methods that use feedforward neural networks to approximate Q functions, the proposed method uses a recurrent neural network (RNN) that incorporates historical state-action pairs of each controlled UAV, and an attention mechanism to analyze the importance of these historical state-action pairs, thus improving the global Q function approximation accuracy and the target UAV positioning accuracy. Simulation results show that the proposed scheme can reduce the average positioning error by up to 17.5% and 58.5% compared to the value decomposition based-MARL scheme with FAS and the proposed AR-MARL method without FAS.

Multi-agent architectures leveraging Large Language Models (LLMs) have significantly advanced the precision of Question Answering (QA) systems across diverse domains. However, existing frameworks remain vulnerable to adversarial manipulations, including poisoning, backdoor, and jailbreak at tacks, primarily due to their reliance on centralized orchestration. To mitigate these risks, we propose AgentChain, a framework that substitutes centralized control with a distributed semantic consensus process. By modeling the blockchain as an ideal functionality, AgentChain establishes a secure distributed layer to coordinate role allocation, answer proposal, evaluation and voting through a decentralized council. Specifically, we design Proof-of-Content-Quality (PoCQ) mechanism to ensure that the f inal answers reflect a robust semantic agreement among the majority of honest agents. Furthermore, we propose an incentive mechanism based on stake reassignment that penalizes malicious agents by reducing their rewards, ultimately phasing them out of the network. Comprehensive evaluations across eight datasets demonstrate that AgentChain achieves superior performance and resilience. AgentChain minimizes the impact of poisoning attacks on precision to less than 3% and reduces the success rate of backdoor and jailbreak attacks to less than 4%. These findings highlight the effectiveness and trustworthiness of AgentChain in mitigating security threats while maintaining high QA accuracy.

WiFi-based indoor positioning plays a crucial role in a variety of location-based services due to its widespread avail ability and cost-effectiveness. However, most existing indoor positioning systems predominantly utilize channel state information (CSI) to learn channel characteristics and apply fingerprinting for position estimation. Unfortunately, CSI can only be extracted from a limited set of commercial WiFi devices, hindering its widespread application in practice. In this work, we introduce BFMLoc, a novel indoor positioning framework that exploits the beamforming feedback matrix (BFM), which is readily available on commercial WiFi devices. Although BFM provides broader sensing coverage, it sacrifices detailed channel information due to the data compression applied to reduce feedback overhead. To address this limitation, we explore the feasibility of using BFM derivatives for indoor positioning and propose a U-net model to reconstruct the angle-delay profiles (ADP) from the compressed BFM data, thereby enhancing positioning accuracy. A Vision Transformer (ViT) model is then developed to extract spatial features from the predicted ADP maps to perform localization. Additionally, we design a model adaptation module based on transfer learning, integrated into the overall framework. This allows the positioning model to be easily deployed and adapted to various indoor environments with minimal retraining overhead. Extensive evaluations and validation on a digital twin testbed demonstrate that our framework achieves high positioning ac curacy and enhanced robustness compared to state-of-the-art methods.

Motivated by real-world applications, we study the problem of decentralized online learning with dynamic feedback delays in the presence of malicious data generators under different threat models. In this problem, multiple agents collaborate to classify the features of streaming data samples generated online and receive dynamically delayed feedback on the ground-truth labels. While some data generators are benign, others—due to internal motives or external factors such as cyberattacks—may maliciously manipulate data features to compromise the classification performance. In this work, we first investigate the targeted attacks by malicious data generators, i.e., feature manipulation with aims to gain preferred classification outcomes from the agents. In response, we propose two robust algorithms,RDOC-TOandRDOC-TC, countering ordinary and clairvoyant adversaries that can access certain outdated and the latest classification models of the agents, respectively. Subsequently, we address the untargeted attacks by malicious data generators, which aim to disrupt the classification outcomes without targeting any particular class, by proposing another algorithm,RDOC-U. Our theoretical analysis establishes that all three proposed algorithms achieve sublinear regret bounds. The evaluations conducted in the application of network traffic classification with two real-world datasets demonstrate the competitiveness of the proposed algorithms compared to advanced baselines.

In this paper, a secure and communication-efficient clustered federated learning (CFL) design is proposed. In our model, several base stations (BSs) with heterogeneous task-handling capabilities and multiple users with non-independent and identically distributed (non-IID) data jointly perform CFL training incorporating differential privacy (DP) techniques. Since each BS can process only a subset of the learning tasks and has limited wireless resource blocks (RBs) to allocate to users for federated learning (FL) model parameter transmission, it is necessary to jointly optimize RB allocation and user scheduling for CFL performance optimization. Meanwhile, our considered CFL method requires devices to use their limited data and FL model information to determine their task identities, which may introduce additional communication overhead. We formulate an optimization problem whose goal is to minimize the training loss of all learning tasks while considering device clustering, RB allocation, DP noise, and FL model transmission delay. To solve the problem, we propose a novel dynamic penalty function assisted value decomposed multi-agent reinforcement learning (DPVD-MARL) algorithm that enables distributed BSs to independently determine their connected users, RBs, and DP noise of the connected users but jointly minimize the training loss of all learning tasks across all BSs. Different from the existing MARL methods that assign a large penalty for infeasible actions, we propose a novel penalty assignment scheme that assigns penalty depending on the number of devices that cannot meet communication constraints (e.g., delay), which can guide the MARL scheme to quickly find valid actions, thus improving the convergence speed. Simulation results show that the DPVD-MARL can improve the convergence rate by up to 20% and the ultimate accumulated rewards by 15% compared to independent Q-learning.

3D reconstruction is a cornerstone for creating immersive digital experiences in metaverse. Owing to explicit scene representation and efficient rendering, Gaussian splatting (GS) has become a prominent research focus in 3D reconstruction. However, the input images for GS are often imperfect, as those collected via highly-interfered wireless environment (HIWE) tend to be distorted, thereby undermining the accuracy of 3D reconstruction and limiting scalability. This paper proposes a novel Gaussian semantic splatting (GSS) scheme, designed for agile, reliable, and communication-efficient 3D reconstruction in the metaverse. Specifically, the semantic communication encoder/decoder (SCED) within GSS performs sequential semantic encoding and channel encoding using the proposed reliable and efficient semantic communication (RESC) algorithm, enabling the receiver to recover images with near-perfect accuracy. These images are then processed by the memory-efficient Gaussian renderer (MEGR), which employs an agile Gaussian splatting rendering (AGSR) algorithm to complete the 3D reconstruction and render a series of new viewpoint images. Additionally, a semantic control unit (SCU) is designed to oversee the components, enhancing the overall efficiency of the 3D reconstruction process. Experimental results demonstrate that GSS achieves competitive 3D reconstruction quality in HIWE, delivering real-time rendering speeds of 145 FPS at an$800\times 800$resolution while reducing storage memory overhead by more than 12 times compared to the state-of-the-art (SOTA) scheme.

Semantic Communication (SC) achieves meaning transmission instead of bitstreams by deep semantic encoding decoding. Since the encoder-decoder contains sensitive and proprietary knowledge, its illicit leakage infringes commercial benefits and copyright, which warrants corresponding protection. However, current SC security paradigms narrowly emphasize transmission data protection while neglecting encoding knowl edge safeguarding. To bridge this gap, we present SemanAegis, the first SC knowledge protection framework. SemanAegisinte grates a built-in-system access control mechanism that remains effective even if the system is stolen, ensuring that unauthorized access attempts yield unacceptable low-fidelity outputs, while credential-embedded inputs from authorized entities are met with accurate responses. Specifically, we establish access control through backdoor implantation, whereby only inputs embedded with credentials activate the backdoor and access system, while source inputs are constrained to generate erroneous results. Moreover, we adopt a synthesizer to generate imperceptible credentials, thus guaranteeing their confidentiality. Additionally, a dedicated contrastive learning strategy is implemented to accelerate the convergence of backdoor implanting. Empirical evaluations across SC systems and benchmark datasets demonstrate SemanAegis precisely rejects unauthorized inputs, effectively mitigates knowledge extractions, and consistently preserves SC regular functionality.

In this paper, the optimization of unmanned aerial vehicle (UAV) localization under jamming attacks is studied. In the considered network, a base station (BS) collaborates with an active UAV to localize a target UAV. During this positioning process, a jamming UAV transmits discontinuous signals to passive UAVs to interfere the distance information measurement. To localize the target UAV under jamming attacks, the BS jointly uses two localization methods: 1) generative adversarial network (GAN) based positioning method and 2) time difference of arrival (TDOA) based positioning method. Since GAN-based method cannot defend against a strong jamming signal while TDOA-based method may consume more energy and sacrifice localization accuracy, the BS must select an appropriate positioning method (GAN-based or TDOA-based methods) and four distance measurement information of passive UAVs to localize the target UAV. This problem is formulated as an optimization problem. The aim of this problem is to minimize the positioning error between the estimated and the ground truth positions of the target UAV while considering jamming attacks and the trajectory of passive UAVs. To solve this problem, we propose a mixture Gaussian distribution model based collaborative reinforcement learning (RL) method which enables the active UAV to optimize its transmit power and trajectory, and enables the BS to select the most appropriate subsets of distance measurement information and the optimal positioning method according to the UAVs movement and the unknown jamming attack pattern. Simulation results show the proposed method can reduce the positioning error of the target UAV by up to 36.5% compared to the method that does not consider the GAN-based positioning method.

3D networks with unmanned aerial vehicles (UAVs) are emerging as a cornerstone of next-generation communication infrastructure, offering flexibility and enhanced coverage in challenging environments. However, prior works predominantly focus on UAV-specific optimizations and high-throughput strategies, often overlooking the critical aspect of network reliability when incorporating these movable entities in the infrastructure. Resilience is paramount in such networks, as it ensures stable performance and connectivity in the face of dynamic conditions, such as mobile edges, transient ground devices, and significant signal interference from urban environments. To address this gap, this article proposes a topology-driven scheme from a holistic view of the 3D networks, leveraging comprehensive scene-based information to enable real-time network adaptability through topological (re)configuration. We decompose this reliability problem into three intertwined stages: topological resilience quantification, UAV self-positioning, and learning-based connectivity optimization. This framework ensures network resilience from a functional perspective, emphasizing the ability to consistently deliver high-quality performance while mitigating connectivity interruptions, essential for reliability of next-generation 3D communication infrastructure. Experimental results validate the effectiveness of our approach, demonstrating significant improvements over traditional methods in terms of bandwidth allocation to ground devices and load balancing among UAVs. Notably, our system excels in highly dynamic scenarios, where it adapts to network instability and connectivity failures on-demand, ensuring consistent and reliable communication performance.

In this work, we propose a novel integrated sensing and communication (ISAC) framework for connected and autonomous vehicles (CAVs), which incorporates digital semantic communication (SemCom) to achieve both reliable communication and accurate sensing. Within this framework, the transmitting vehicle extracts semantic symbols from the source data and transmits them over orthogonal frequency division multiplexing (OFDM) sub-carriers, while simultaneously utilizing echo signals for radar-based environmental sensing. To achieve reliable SemCom, the transmitter must jointly optimize the quantization bitwidth for semantic symbols, the modulation order, the power allocation across semantic symbol dimensions, and the transmit beamforming strategy. These optimizations must also consider sensing performance, leading to a tradeoff between radar sensing and task-oriented SemCom. To address this joint optimization problem, we decompose it into three subproblems and develop corresponding solutions: 1) a hierarchical constrained proximal policy optimization (H-CPPO) algorithm to determine the quantization bitwidth, modulation order, and power allocation under frequency-flat channels, 2) a joint beamforming strategy to optimize the dual-function radar-SemCom transmit beamforming vector, and 3) a semantic importance-based signal-to-noise ratio (SNR) matching strategy that effectively adapts the optimal power allocation obtained under frequency-flat conditions to fading channels with random gains. Simulation results on a road image segmentation task show that, the proposed SemCom scheme achieves near-optimal segmentation accuracy while reducing radar beamforming error by up to 82% compared to the conventional digital system using the same quadrature phase shift keying (QPSK) modulation.

Cellular vehicle-to-everything (C-V2X) networks provide a promising solution to improve road safety and traffic efficiency. One key challenge in such systems lies in meeting quality-of-service (QoS) requirements of vehicular communication links given limited network resources, particularly under imperfect channel state information (CSI) conditions caused by the highly dynamic environment. In this paper, a novel two-phase framework is proposed to instill resilience into C-V2X networks under unknown imperfect CSI. The resilience of the C-V2X network is defined, quantified, and optimized for the first time through two principal dimensions:absorption phaseandadaptation phase. Specifically, the probability distribution function (PDF) of the imperfect CSI is estimated during the absorption phase through dedicated absorption power scheme and resource block (RB) assignment. The estimated PDF is further used to analyze the interplay and reveal the tradeoff between these two phases. Then, a novel metric namedhazard rate (HR)is exploited to balance the C-V2X network’s prioritization on absorption and adaptation. Finally, the estimated PDF is exploited in the adaptation phase to recover the network’s QoS through a real-time power allocation optimization. Simulation results demonstrate the superior capability of the proposed framework in sustaining the QoS of the C-V2X network under imperfect CSI. Specifically, in the adaptation phase, the proposed design reduces the vehicle-to-vehicle (V2V) delay that exceeds QoS requirement by 23% and 46%, and improves the average vehicle-to-infrastructure (V2I) throughput by 14% and 16% compared to the model-based and data-driven benchmarks, respectively, without compromising the network’s QoS in the absorption phase.

To address the challenges of Internet of Things (IoT) device diversity and media service heterogeneity in human and machine-type communications, a predominant approach in sixth-generation (6G) networks and beyond is to serve diversified IoT devices by differentiated services. In this paper, a satellite-terrestrial IoT framework with multi-access edge computing (MEC) is investigated for two types of heterogeneous services, data-intensive and computation-intensive service. In our proposed framework, MEC and millimeter wave (mmWave) communication are jointly considered to optimize data- and computation-intensive services, guaranteeing the rate, delay and energy requirements of diversified IoT devices. From the viewpoint of heterogeneous services, we formulate a joint resource allocation problem, in which quality of experience (QoE) of diversified IoT devices are recognized as system utility. Specifically, service offloading, power allocation and computation resource allocation are jointly considered. Since the optimized problem is nonconvex, necessary problem reformulations are conducted to transfer the original problem to convex problems. Furthermore, an alternating iterative method based on deep reinforcement learning (DRL) and CVX technique is adopted to obtain the sub-optimal solution with low computation complexity. Finally, extensive simulations are conducted with different system parameter configurations to verify the effectiveness of our proposed scheme.

Next-generation Wi-Fi 8 (IEEE 802.11bn) targets ultra-high reliability (UHR) by introducing coordinated beamforming (CoBF). In dense networks with multiple access points (APs), simultaneous downlink (DL) multi-user MIMO (MU-MIMO) transmissions from multiple APs can cause severe intra-basic service set (intra-BSS) and inter-BSS interference. CoBF aided by only partial channel state information (CSI) feedback through medium access control (MAC) layer frame exchange is envisioned to support concurrent DL transmission with mitigated physical-(PHY-)layer interference. To improve the network throughput, not only the interference mitigation algorithm design requires careful design but also the selection of optimal AP CoBF clusters is crucial for dense AP deployments. This paper presents a cross-layer solution combining PHY and MAC layer design to optimize AP cluster formation for Wi-Fi 8 CoBF. At the PHY layer, we introduce two beamforming nulling strategies: full nulling, which completely cancels all intra-BSS and inter-BSS interference when sufficient spatial degrees of freedom are available, and partial nulling, which is used under limited degrees of freedom to reduce interference as much as possible. Based on this, we formulate the cross-layer problem that aims to optimize the network throughput, to which we propose an exact linear programming (LP) optimization to determine the optimal AP cluster formation. A greedy clustering algorithm is proposed as a low-complexity alternate. Simulation results demonstrate that the proposed CoBF approach significantly mitigates interference and achieves substantial throughput gains in dense AP scenarios. Furthermore, the LP-optimized AP clustering yields the higher network throughput than the greedy heuristic and mixed integer linear programming (MILP) by up to 12% and 26%, highlighting the benefits of global optimization in terms of performance and time complexity.

Next generation communications demand better spectrum management, lower latency, and guaranteed quality-of-service (QoS). Recently, artificial intelligence (AI) has been widely introduced to advance these aspects in next generation wireless systems. However, such AI applications suffer from limited training data, low robustness, and poor generalization capabilities. To address these issues, we introduce a model-driven deep unfolding (DU) algorithm in this paper to address the gap between traditional model-driven communication algorithms and data-driven deep learning. Focusing on the QoS-aware rate-splitting multiple access (RSMA) resource allocation problem in multi-user communications, a conventional fractional programming (FP) algorithm is first applied as a benchmark. The solution is further refined using projection gradient descent (PGD). DU is employed to further accelerate convergence, thereby improving the efficiency of PGD. Moreover, the feasibility of results is guaranteed by designing a low-complexity projection based on scale factors, and adding violation control mechanisms into the loss function that minimizes error rates. Finally, we provide a detailed analysis of the computational complexity and analysis design of the proposed DU algorithm. Extensive simulations are conducted and the results demonstrate that the proposed DU algorithm can reach the optimal communication efficiency with only 1.1% violation rate for the five-layer DU. The DU algorithm also exhibits robustness in out-of-distribution tests and can be effectively trained with as few as 50 samples.

Extremely High Throughput (EHT) and Ultra-high reliability (UHR) are new objectives in Next-Gen Wi-Fi, i.e., Wi-Fi 7 and beyond; however, the data rate within a periodic channel sounding round is expected to significantly deteriorate under time-varying channels with Doppler effect in Downlink Multi-User Multiple-Input Multiple-Output. Therefore, Next-Gen channel sounding must carefully balance the MAC-layer CSI overhead reduction and the PHY-layer channel capacity degradation caused by the Doppler effect for data rate maximization. Despite its critical importance, the cross-layer (PHY + MAC) Wi-Fi channel sounding optimization in time-varying channels remains under-explored. This paper addresses this research gap by proposing a cross-layer optimization problem to find the optimal EHT sounding period that maximizes the average data rate by considering both MAC-layer CSI overhead and PHY-layer channel capacity degradation. This problem is then converted into an equivalent optimization problem that can be solved efficiently using our proposed model driven optimal search algorithm with proven convexity. Afterwards, we introduce a data driven Transformer-based partial CSI prediction framework to alleviate CSI staleness without introducing extra CSI overhead, which further enhances the average data rate. Through simulations, we evaluate the baseline EHT sounding protocol that always uses outdated partial CSI, and then benchmark the baseline against our proposed hybrid data and model driven approach. The numerical results demonstrate that integrating Transformer-based partial CSI prediction with the optimal channel sounding period significantly reduces CSI overhead by up to 25.2%, while increasing the average throughput by up to 30.9%.

In this paper, a novel covert semantic communication framework is investigated. Within this framework, a server extracts and transmits the semantic information, i.e., the meaning of image data, to a user over several time slots. An attacker seeks to detect and eavesdrop the semantic transmission to acquire details of the original image. To avoid data meaning being eavesdropped by an attacker, a friendly jammer is deployed to transmit jamming signals to interfere the attacker so as to hide the transmitted semantic information. Meanwhile, the server will strategically select time slots for semantic information transmission. Due to limited energy, the jammer will not communicate with the server and hence the server does not know the transmit power of the jammer. Therefore, the server must jointly optimize the semantic information transmitted at each time slot and the corresponding transmit power to maximize the privacy and the semantic information transmission quality of the user. To solve this problem, we propose a prioritised sampling assisted twin delayed deep deterministic policy gradient algorithm to jointly determine the transmitted semantic information and the transmit power per time slot without the communications between the server and the jammer. Compared to standard reinforcement learning methods, the proposed method uses an additional Q network to estimate Q values such that the agent can select the action with a lower Q value from the two Q networks thus avoiding local optimal action selection and estimation bias of Q values. Simulation results show that the proposed algorithm can improve the privacy and the semantic information transmission quality by up to 77.8% and 14.3% compared to the traditional reinforcement learning methods.

Network intrusion detection systems analyze network traffic to monitor and identify potential cyber threats. Recent research has primarily focused on enhancing detection performance using advanced deep-learning techniques, yet there is a notable gap in exploring the interpretability and transparency of these systems. Building upon advancements in large language models (LLMs) that enable reasoning-aware predictions, we propose integrating LLMs with conventional decision trees to jointly enhance interpretability, reasoning, and detection performance. Decision trees discover numerical patterns from input traffic features, which can be formulated as reasoning paths through tree traversal. These paths are then serialized into natural language descriptions and fed into LLMs to make final predictions, accompanied by detailed explanations. Such fusion strategy enables the strengths of both the numerical analysis capabilities of decision trees for pattern recognition and the embedded general logic in LLMs. Experimental results on a real-world network security dataset demonstrate multi-dimensional performance gains, even in scenarios with missing data features.

Integrated sensing and communication (ISAC) emerged as a key feature of next-generation 6G wireless systems, allowing them to achieve high data rates and sensing accuracy. While prior research has primarily focused on addressing communication safety in ISAC systems, the equally critical issue of sensing safety remains largely ignored. In this paper, a novel threat to the sensing safety of ISAC vehicle networks is studied, whereby a malicious reconfigurable intelligent surface (RIS) is deployed to compromise the sensing functionality of a roadside unit (RSU). Specifically, a malicious attacker dynamically adjusts the phase shifts of an RIS to spoof the sensing outcomes of a vehicular user (VU)’s echo delay, Doppler shift, and angle-of-departure (AoD). To achieve spoofing on Doppler shift estimation, a time-varying phase shift design on the RIS is proposed. Furthermore, the feasible spoofing frequency set with respect to the Doppler shift is analytical derived. Analytical results also demonstrate that the maximum likelihood estimator (MLE) of the AoD can be significantly misled under spoofed Doppler shift estimation. Simulation results validate our theoretical findings, showing that the RIS can induce a spoofed velocity estimation from 0.1 m/s to 14.9 m/s for a VU with velocity of 10 m/s, and can cause an AoD estimation error of up to 65° with only a 5° beam misalignment.

This paper investigates the energy efficiency (EE) of the fluid antenna relay (FAR)-assisted wireless communication systems in non-line-of-sight (NLoS) scenarios. Unlike conventional fixed-position antenna systems, the FAR dynamically adjusts the spatial positions of fluid antennas (FAs), enabling efficient signal transmission through blockages. By integrating the amplify-and-forward (AF) protocol, the proposed FAR architecture amplifies and forwards signals while controlling phase shifts via FA reconfiguration. An optimization problem is formulated to maximize the system EE under given constraints. The problem is decomposed into three sub-problems including large-scale fading optimization, small-scale fading optimization, and joint power control and beamforming design optimization. These subproblems are solved iteratively with successive convex approximation (SCA) and Dinkelbach methods. Numerical simulation results demonstrate that the proposed algorithm significantly outperforms the existing STAR-RIS and AF relay schemes, improving EE of the system by up to 29.92% and 45.04%, respectively. The work in this paper bridges the research gap in FAS research with NLoS challenges and provides a framework for future FAR-enabled wireless communication systems.

In this paper, a novel resilient unmanned aerial vehicle (UAV) framework that enables UAVs to efficiently adjust their trajectories and antenna ports to serve disconnected users due to unexpected accidents is designed. In the proposed framework, a set of UAVs equipped with fluid antennas provide service for ground users. At the beginning, each UAV optimizes its three dimensional (3D) location and selects an antenna port to maximize the sum data rate of all users. During the service period, several UAVs may not be able to continue to serve ground users due to unexpected accidents. The remaining UAVs must adjust their trajectories and antenna ports to provide communication services for the users originally served by UAVs with accidents. This problem is formulated as an optimization problem that aims to maximize the total data rates of all users during the entire service period including the period that all UAVs can provide service, the period that some UAVs cannot provide service and the remaining UAVs must adjust their trajectories and antenna ports, and the period that the remaining UAVs find fixed locations to serve users. To solve this problem, an attention and gate recurrent unit (GRU) based reinforcement learning (AGRL) method is designed. In this method, the GRUs are utilized to capture previous UAV actions including trajectories and antenna port selections and states. The transformer is used to analyze the importance of previous UAV actions and states, thus further improving the total data rates of all users. To further improve the training speed of the designed AGRL method, we mathematically derive the optimally initial UAV locations. Simulation results show that the proposed AGRL method can improve the expected data rate of all users by up to 9.89% and 10.19% compared to the value function decomposition RL (VDRL) method and the proposed AGRL method without optimizing antenna port selection.

In this paper, a novel contrastive language–image pre-training (CLIP) model based on semantic The communication framework is designed. Compared to a standard neural network (e.g., convolutional neural network) based semantic encoders and decoders that require joint training over a common dataset, Our CLIP model-based method does not require any training procedures, thus enabling a transmitter to extract data meanings of the original data without neural network model training, and the receiver to train a neural network for follow-up task implementation without the communications with the transmitter. Next, we investigate the deployment of the CLIP model-based semantic framework over a noisy wireless network. Since the semantic information generated by the CLIP model is susceptible to wireless noise and the spectrum used for semantic information transmission are limited; it is necessary to optimize CLIP jointly model architecture and spectrum resource block (RB) allocation to maximize semantic communication performance while considering wireless noise, the delay and energy used for semantic communication. To achieve this goal, we use a proximal policy optimization (PPO) based reinforcement learning (RL) algorithm to learn how wireless noise affects the semantic communication performance, thus finding optimal CLIP model and RB for each user. Simulation results show that our proposed method improves the convergence rate by up to 40%, and the accumulated reward by 4x compared to soft actor-critic.

Modern network environments—spanning 5G cores, industrial IoT, and spine-leaf data-centers—offer rich hierarchical structure and multi-layer telemetry, yet deep learning models applied to these settings remain black-box predictors that ignore domain logic and struggle with scarce data. We introduce LogiK-Net, a neurosymbolic framework that bridges data and knowledge by decoupling the learning process into (i) a forward-discovery module based on Kolmogorov-Arnold Networks (KANs) that yields interpretable edge activations for feature pruning and rule mining, and (ii) a backward-validation module that employs differentiable first-order network logic to enforce domain axioms and the rules mined on-the-fly. This modular design allows practitioners to swap in richer feature extractors or stricter logical rule sets in the machine learning model as needed, scaling smoothly from supervised traffic-classification to unsupervised, open-world network management. Extensive experiments on reliable feature pruning, IoT threat detection, and topology discovery demonstrate LogiK-Net's generality, interpretability, and reliability, outperforming standard neural network baselines employed in network analysis.

In this paper, we investigate a novel digital network twin (DNT) assisted deep learning (DL) model training framework that enables a base station (BS) to select the data collection source from both physical network and DNT for training DL models used to optimize network performance. In particular, we consider a DNT enabled cellular network that consists of a physical network where a BS uses several antennas to serve multiple mobile users, and a DNT that is a virtual representation of the physical network. The BS must adjust the antenna tilt angles to optimize the data rates of all users. Due to the user mobility, the BS may not be able to accurately track the network dynamics. Hence, a reinforcement learning (RL) approach is used to dynamically adjust the antenna tilt angles. To train the RL, we can use data collected from the physical network and the DNT. The data collected from the physical network is more accurate but incurs more communication overhead compared to the data collected from the DNT. Therefore, it is necessary to determine the ratio of data collected from the physical network and the DNT to improve the training of the RL model, so as to optimize the tilt angle of each antenna in response to user mobility. We formulate an optimization problem to jointly optimize the tilt angle adjustment policy and the data collection strategy, aiming to maximize the data rates of all users while constraining the time delay introduced by collecting data from the physical network. To solve this optimization problem, we propose a hierarchical RL framework consisting of a two-level proximal policy optimization (PPO). The first level PPO dynamically adjusts the antenna tilt angles, and the second level PPO determines the ratio of data collected from the physical network to improve the first level PPO training performance. Compared to traditional single RL algorithms such as deep Q network (DQN), the designed method optimizes the data collection ratio and the antenna tilt angles at diverse time intervals, allowing the second level PPO to adjust the data collection ratio with a large timescale using the training information provided by the first level PPO, and allowing the first level PPO focuses on adjusting the antenna tilt angles with a small timescale. Simulation results show that our proposed method reduces the physical network data collection delay by up to 71.85% compared to a hierarchical RL that uses a deep deterministic policy gradient algorithm as the second level RL.

In this paper, a novel covert semantic communication framework is investigated for image transmission. Within this framework, a server extracts and transmits the semantic information, i.e., the meaning of image data, to a user. An attacker seeks to detect and eavesdrop the semantic transmission to acquire the details of the original image. To secure the semantic communications from such eavesdropping attack, a friendly jammer is deployed to transmit jamming signals so as to interfere the attacker. To evaluate the quality of the received and the eavesdropped semantic information, we introduce a semantic similarity metric called graph-to-nearest-triple (GNT). The privacy level of the system is quantified as the difference between the GNT of the received semantic information at the user and the attacker. The server and the jammer collaboratively manage their transmit power to maximize the privacy level of the semantic communication. To solve this non-convex power management problem, we propose a step-wise dense reward function guided recurrent Q learning algorithm to jointly optimize the transmit power at the server and friendly jammer with no inter-device communication, such that the considered problem is solved in a spectrally, computationally and space compact way. Simulation results show that the proposed method can improve privacy and the semantic transmission quality by up to 17.2% improvement compared to the traditional RL based solutions.

This paper investigates the energy efficiency maximization problem in a resource-constrained visible light communication (VLC)-based probabilistic semantic communication (PSCom) system. In the considered model, light-emitting diode (LED) transmitters perform semantic compression, reducing data size at the cost of computation overhead. The compressed semantic information is transmitted to the users for semantic inference based on a shared knowledge base, which requires regular updates to maintain synchronization. Rate splitting multiple access (RSMA) is used to transmit both knowledge base and information data simultaneously. The goal is to maximize the energy efficiency of the system through optimizing transmit beamforming, direct current (DC) bias, rate allocation, and semantic compression ratio, considering both communication and computation costs. An alternating optimization algorithm, utilizing successive convex approximation and Dinkelbach method, is proposed to solve the problem. Simulation results validate the effectiveness of the proposed approach.

Fine-tuning large language models (LLM) in a distributed manner over edge devices with limited communication and computational resources presents substantial challenges in wireless networks. To tackle these issues, this paper proposes a novel Split Federated Learning framework tailored for LLM (SflLLM), which integrates split federated learning with parameter-efficient fine-tuning techniques. By employing model partitioning and low-rank adaptation (LoRA), SflLLM significantly reduces the computational load on edge devices. Moreover, the introduction of the federated server not only facilitates parallel training but also enhances privacy preservation. To accommodate the heterogeneous communication conditions and diverse computational capacities of edge devices—while accounting for the influence of LoRA rank selection on model convergence and training overhead—we formulate a joint optimization problem. This problem simultaneously optimizes subchannel allocation, power control, model split point selection, and LoRA rank configuration, with the objective of minimizing the overall training latency. An alternating optimization algorithm is developed to efficiently solve the proposed problem and accelerate the training process. Simulation results demonstrate that, compared to conventional methods, the proposed resource allocation scheme and adaptive LoRA rank selection strategy significantly reduce training latency.

WiFi-based indoor positioning plays a crucial role in a variety of location-based services due to its widespread availability and cost-effectiveness. However, most existing indoor positioning systems predominantly utilize channel state information (CSI) to learn channel characteristics and apply fingerprinting for position estimation. Unfortunately, CSI can only be extracted from a limited set of commercial WiFi devices, hindering its widespread application in practice. In this work, we introduce BFMLoc, a novel indoor positioning framework that exploits the beamforming feedback matrix (BFM), which is readily available on commercial WiFi devices. Although BFM provides broader sensing coverage, it sacrifices detailed channel information due to the compression applied to reduce feedback overhead. To address this limitation, we explore the feasibility of using BFM derivatives for indoor positioning and propose a U-net model to reconstruct the angle-delay profiles (ADP) from the compressed BFM data, thereby enhancing positioning accuracy. A Vision Transformer (ViT) model is then developed to extract spatial features from the predicted ADP maps to perform localization. Extensive evaluation results demonstrate that our framework achieves high positioning accuracy and improved robustness compared to state-of-the-art methods.

Cellular vehicle-to-everything (C-V2X) networks provide a promising solution to improve road safety and traffic efficiency. One key challenge in such systems lies in meeting different quality-of-service (QoS) requirements of coexisting vehicular communication links, particularly under imperfect channel state information (CSI) conditions caused by the highly dynamic environment. In this paper, a novel analytical framework for examining the resilience of C-V2X networks in face of imperfect CSI is proposed. In this framework, the adaptation phase of the C-V2X network is studied, in which an adaptation power scheme is employed and the probability distribution function (PDF) of the imperfect CSI is estimated. Then, the resilience of C-V2X networks is studied through two principal dimensions: remediation capability and adaptation performance, both of which are defined, quantified, and analyzed for the first time. Particularly, an upper bound on the estimation's mean square error (MSE) is explicitly derived to capture the C-V2X's remediation capability, and a novel metric named hazard rate (HR) is exploited to evaluate the C-V2X's adaptation performance. Afterwards, the impact of the adaptation power scheme on the C-V2X's resilience is examined, revealing a tradeoff between the C-V2X's remediation capability and adaptation performance. Simulation results validate the framework's superiority in capturing the interplay between adaptation and remediation, as well as the effectiveness of the two proposed metrics in guiding the design of the adaptation power scheme to enhance the system's resilience.

In this paper, a secure and communication-efficient clustered federated learning (CFL) design is investigated. In our model, several base stations (BSs) with heterogeneous task-handling capabilities and multiple users with non-independent and identically distributed (non-IID) data jointly perform CFL training using differential privacy (DP) techniques. Since each BS can process only a subset of learning tasks and has limited wireless resource blocks to allocate to users for federated learning (FL) model parameter transmission, it is necessary to jointly optimize resource block (RB) allocation and user scheduling for CFL performance optimization. Meanwhile, our considered CFL requires devices to use their limited data and FL model information to determine their task identities, which may introduce additional communication overhead. This problem is formulated as an optimization problem whose goal is to minimize the training loss of all learning tasks while considering device clustering, RB allocation, noise, and FL model transmission delay. To solve this, we propose a novel value decomposed multi-agent reinforcement learning (VD-MARL) algorithm that enables distributed BSs to independently determine their connected users, the RBs, and DP noise of the connected users but jointly minimize the training loss of all learning tasks across all BSs. Different from the existing MARL methods that assign a large penalty for invalid actions, we propose a novel penalty assignment scheme that assigns penalty depending on the number of devices that cannot meet communication constraints (e.g., delay), which can guide the MARL scheme to quickly find valid actions thus improving the convergence speed. Simulation results show that the VD-MARL can improve the convergence rate by up to 35% and the ultimate accumulated rewards by 27% compared to independent Q-learning.

In this paper, the framework of fluid antenna system (FAS)-assisted three dimensional (3D) passive unmanned aerial vehicle (UAV) positioning is developed. In the proposed framework, a set of controlled UAVs including an active UAV and four FAS-assisted passive UAVs, as well as a ground base station (BS) cooperatively estimate the real-time 3D position of a target UAV. Here, the active UAV transmits a measurement signal to the passive UAVs. This signal is reflected via the target UAV and received by the passive UAVs. Each passive UAV estimates the distance of the active-target-passive UAV link and selects an antenna port to share the distance information with the BS. The BS calculates the real-time position of the target UAV. As the target UAV is moving due to its task operation, the controlled UAVs must optimize their trajectories and select optimal antenna port for transmitting the positioning information, aiming to estimate the real-time position of the target UAV. We formulate an optimization problem that optimizes the trajectories of all controlled UAVs and antenna port selection of passive UAVs with the aim of minimizing the target UAV positioning error. To address this problem, an attention-based recurrent multiagent reinforcement learning (AR-MARL) scheme is proposed. In the proposed method, a recurrent neural network (RNN) acts as a local Q function of each controlled UAV to capture its historical state-action pairs, and a transformer is used to analyze the importance of these historical state-action pairs, thus improving the global$\mathbf{Q}$function approximation accuracy, thereby further improving the positioning accuracy. Simulation results show that the proposed AR-MARL scheme can reduce the average positioning error by up to 17.5 % and 58.5 % compared to the VD-MARL scheme and the proposed method without FAS.

Rate-splitting multiple access (RSMA) has been proven as an effective communication scheme for 5G and beyond. However, current approaches to RSMA resource management require complicated iterative algorithms, which cannot meet the stringent latency requirement by users with limited resources. Recently, data-driven methods are explored to alleviate this issue. However, they suffer from poor generalizability and scarce training data to achieve satisfactory performance. In this paper, we propose a fractional programming (FP) based deep unfolding (DU) approach to address resource allocation problem for a weighted sum rate optimization in RSMA. By carefully designing the penalty function, we couple the variable update with projected gradient descent algorithm (PGD). Following the structure of PGD, we embed a few learnable parameters in each layer of the DU network. Through extensive simulation, we have shown that the proposed model-based neural networks can yield similar results compared to the traditional optimization algorithm for RSMA resource management but with much lower computational complexity, less training data, and higher resilience to out-ofdistribution (OOD) data.

The integration of digital twinning technologies is driving next-generation networks toward new capabilities, allowing operators to thoroughly understand network conditions, efficiently analyze valuable radio data, and innovate applications through user-friendly, immersive interfaces. Building on this foundation, network digital twins (NDTs) accurately depict the operational processes and attributes of network infrastructures, facilitating predictive management through real-time analysis and measurement. However, constructing precise NDTs poses challenges, such as integrating diverse data sources, mapping necessary attributes from physical networks, and maintaining scalability for various downstream tasks. Unlike previous works that focused on the creation and mapping of NDTs from scratch, we explore intra- and inter-operations among NDTs within a Unified Twin Transformation (UTT) framework, which uncovers a new computing paradigm for efficient transfer, merging, and splitting of NDTs to create task-oriented twins. By leveraging joint multi-modal and distributed mapping mechanisms, UTT optimizes resource utilization and reduces the cost of creating NDTs, while ensuring twin model consistency. A theoretical analysis of the distributed mapping problem is conducted to establish convergence bounds for this multi-modal gated aggregation process. Evaluations on real-world twin-assisted applications, such as trajectory reconstruction, human localization, and sensory data generation, demonstrate the feasibility and effectiveness of interoperability among NDTs for corresponding task development.

Various distributed learning approaches emerge for enabling ubiquitous intelligence in Internet of Things (IoT) without sacrificing data privacy. To improve communication efficiency in frequent knowledge exchange over resource-constrained IoT, different techniques for client selection have been proposed. However, the intractable scalability issues remain to be addressed in massive IoT, since highly-coupled co-channel interference adds exponential complexity to combinatorial client selection. In this work, we develop a client selection framework highly-scalable to large-scale networks with thousands of devices, which exploits the inherent graph structure derived from knowledge exchange and co-channel interference. Specifically, we first model a client selection problem for jointly optimizing learning performance and system cost under volatile network conditions. The formulated problem is encoded into a node classification problem by a directed graph. Subsequently, a general yet simple solver is designed based on graph neural networks, which selects clients by classifying node status with recursive neighborhood aggregation of node representations. Finally, extensive experimental results demonstrate that the proposed approach can perform on par with state-of-the-art methods, while scaling to networks whose size is orders of magnitude larger than they can handle.

In this article, we investigate an accurate synchronization between a physical network and its digital network twin (DNT), which serves as a virtual representation of the physical network. The considered network includes a set of base stations (BSs) that must allocate its limited spectrum resources to serve a set of users while also transmitting its partially observed physical network information to a cloud server to generate the DNT. Since the DNT can predict the physical network status based on its historical status, the BSs may not need to send their physical network information at each time slot, allowing them to conserve spectrum resources to serve the users. However, if the DNT does not receive the physical network information of the BSs over a large time period, the DNT’s accuracy in representing the physical network may degrade. To this end, each BS must decide when to send the physical network information to the cloud server to update the DNT, while also determining the spectrum resource allocation policy for both DNT synchronization and serving the users. We formulate this resource allocation task as an optimization problem, aiming to maximize the total data rate of all users while minimizing the asynchronization between the physical network and the DNT. The formulated problem is challenging to solve by traditional optimization methods, as each BS can only observe a partial physical network, making it difficult to find an optimal spectrum allocation strategy for the entire network. To address this problem, we propose a method based on the gated recurrent units (GRUs) and the value decomposition network (VDN). The GRU component allows the DNT to predict future status using the historical data, effectively updating itself when the BSs do not transmit the physical network information. The VDN algorithm enables each BS to learn the relationship between its local observation and the team reward of all BSs, allowing it to collaborate with others in determining whether to transmit physical network information and optimizing spectrum allocation. Simulation results show that our GRU-based and VDN-based algorithm improves the weighted sum of data rates and the similarity between the status of the DNT and the physical network by up to 28.96%, compared to a baseline method combining GRU with the independent Q learning (IQL).

Due to the exponential increase in wireless devices and a diversification of network services, unprecedented challenges, such as managing heterogeneous data traffic and massive access demands, have arisen in next-generation wireless networks. To address these challenges, there is a pressing need for the evolution of multiple access schemes with advanced transceivers. Millimeter-wave (mmWave) communication emerges as a promising solution by offering substantial bandwidth and accommodating massive connectivities. Nevertheless, the inherent signaling directionality and susceptibility to blockages pose significant challenges for deploying multiple transceivers with narrow antenna beams. Consequently, beam management becomes imperative for practical network implementations to identify and track the optimal transceiver beam pairs, ensuring maximum received power and maintaining high-quality access service. In this context, we propose a Contextual Combinatorial Beam Management (CCBM) framework tailored for mmWave wireless networks. By leveraging advanced online probing techniques and integrating predicted contextual information, such as dynamic link qualities in spatial-temporal domain, CCBM aims to jointly optimize transceiver pairing and beam selection while balancing the network load. This approach not only facilitates multiple access effectively but also enhances bandwidth utilization and reduces computational overheads for real-time applications. Theoretical analysis establishes the asymptotically optimality of the proposed approach, complemented by extensive evaluation results showcasing the superiority of our framework over other state-of-the-art schemes in multiple dimensions.

In this paper, a multi-modal data based semi-supervised learning (SSL) framework that jointly use channel state information (CSI) data and RGB images for vehicle positioning is designed. In particular, an outdoor positioning system where the vehicle locations are determined by a base station (BS) is considered. The BS equipped with several cameras can collect a large amount of unlabeled CSI data and a small number of labeled CSI data of vehicles, and the images taken by cameras. Although the collected images contain partial information of vehicles (i.e. azimuth angles of vehicles), the relationship between the unlabeled CSI data and its azimuth angle, and the distances between the BS and the vehicles captured by images are both unknown. Therefore, the images cannot be directly used as the labels of unlabeled CSI data to train a positioning model. To exploit unlabeled CSI data and images, a SSL framework that consists of a pretraining stage and a downstream training stage is proposed. In the pretraining stage, the azimuth angles obtained from the images are considered as the labels of unlabeled CSI data to pretrain the positioning model. In the downstream training stage, a small sized labeled dataset in which the accurate vehicle positions are considered as labels is used to retrain the model. Simulation results show that the proposed method can reduce the positioning error by up to 30% compared to a baseline where the model is not pretrained.

In this paper, a semantic communication framework where the transmitter and the receiver possess different knowledge (i.e., different methods to extract semantic information and regenerate source data) is investigated. In the proposed framework, the transmitter extracts semantic information according to its knowledge, and the receiver processes the received semantic information based on its own knowledge. To ensure the receiver can understand the semantic information as anticipated, the transmitter will ask a series of questions to estimate the receiver’s knowledge and adjust the method of semantic information extraction according to the estimation. Due to the limited wireless resources and communication time, the size of the extracted semantic information and the number of questions that the transmitter can ask are limited. This problem is formulated as an optimization problem whose goal is to maximize worse case answer similarities over semantic generation and question selection decisions. More specifically, the transmitter aims to ask the questions to pinpoint the largest knowledge divergence and adjusts its semantic generation method to minimize this divergence. An adversarial reinforcement learning (ARL) inspired algorithm, combined with a matching network, is designed to achieve such opposite goals by searching the optimal semantic information generation scheme and question selection scheme in an adversarial manner. Simulation results demonstrate that the proposed framework can improve the semantic similarity of answers by up to 5.5% gain and can achieve up to 10.7% gain in terms of the average similarity of texts compared to the algorithm without knowledge estimation.

To improve communication efficiency and handle data heterogeneity challenges in federated learning (FL), fine-tuning the pre-trained large models rather than training neural networks from scratch has received increasing attention in recent years, especially under cross-domain settings. However, such a cross-domain federated fine-tuning scenario opens up a broader attack surface for new threats, especially backdoors, posing significant security risks. Existing backdoor attacks mainly focus on label shift scenarios and use explicit triggers, which lack transferability and effectiveness in cross-domain settings, thereby exhibiting significant weaknesses. In this paper, we propose Silent Penetrator, an innovative penetration scheme tailored for cross-domain federated fine-tuning, which exploits a feature shift-induced backdoor to elicit specific symptoms in the trusted private data of targeted victims. In Silent Penetrator, the attacker can obtain a high-quality poisoned dataset by leveraging the available domain information as the text prompts for Stable Diffusion, and inject a domain-sensitive backdoor that can be unconsciously triggered by unmodified private data of the victims. To achieve stronger and more persistent penetration, we thoroughly explore the adversary’s configurable space and enhance our backdoor injection utilizing contrastive-enhanced boundary deviation and cross-domain predictive confrontation. Extensive experiments on three cross-domain datasets and four state-of-the-art federated fine-tuning frameworks validate the effectiveness of Silent Penetrator in successfully compromising target clients. Furthermore, our backdoor enhancement strategy improves the penetration accuracy by over 10% in most scenarios and significantly enhances the durability of the penetration compared to four state-of-the-art backdoor enhancement techniques.

Federated Learning (FL) is a distributed machine learning framework that efficiently reduces communication and preserves privacy. Existing FL algorithms typically rely on the assumption of direct communication between the server and clients for model data exchange. However, this assumption does not apply in many real-world scenarios where appropriate communication infrastructure is lacking, such as in remote smart sensing. To overcome this challenge, we propose a new framework, FedEx (Federated Learning via Model Express Delivery). FedEx employs mobile transporters, such as Unmanned Aerial Vehicles (UAVs), to establish indirect communication channels between the server and clients. We have developed two algorithms under this framework: FedEx-Sync and FedEx-Async, which differ based on whether the transporters operate on a synchronized or asynchronized schedule. Although indirect communication introduces variable delays in global model dissemination and local model collection, we demonstrate the convergence of both FedEx versions. Additionally, we explore the energy consumption of transporters, integrating it with the convergence bounds and proposing a bi-level optimization algorithm for efficient client assignment and route planning. Our experiments, conducted on two public datasets in a simulated environment, further demonstrate the efficacy of FedEx.

In this paper, a multi-modal vehicle positioning framework that jointly localizes vehicles with channel state information (CSI) and images is designed. In particular, we consider an outdoor scenario where each vehicle can communicate with only one BS, and hence, it can upload its estimated CSI to only its associated BS. Each BS is equipped with a set of cameras, such that it can collect a small number of labeled CSI, a large number of unlabeled CSI, and the images taken by cameras. To exploit the unlabeled CSI data and position labels obtained from images, we design an meta-learning based hard expectation-maximization (EM) algorithm. Specifically, since we do not know the corresponding relationship between unlabeled CSI and the multiple vehicle locations in images, we formulate the calculation of the training objective as a minimum matching problem. To reduce the impact of label noises caused by incorrect matching between unlabeled CSI and vehicle locations obtained from images and achieve better convergence, we introduce a weighted loss function on the unlabeled datasets, and study the use of a meta-learning algorithm for computing the weighted loss. Subsequently, the model parameters are updated according to the weighted loss function of unlabeled CSI samples and their matched position labels obtained from images. Simulation results show that the proposed method can reduce the positioning error by up to 61% compared to a baseline that does not use images and uses only CSI fingerprint for vehicle positioning.

This article investigates the adaptive resource allocation scheme for digital twin (DT) synchronization optimization over dynamic wireless networks. In our considered model, a base station (BS) continuously collects factory physical object state data from wireless devices to build a real-time virtual DT system for factory event analysis. Due to continuous data transmission, maintaining DT synchronization must use extensive wireless resources. To address this issue, a subset of devices is selected to transmit their sensing data, and resource block (RB) allocation is optimized. This problem is formulated as a constrained Markov process (CMDP) problem that minimizes the long-term mismatch between the physical and virtual systems. To solve this CMDP, we first transform the problem into a dual problem that refines RB constraint impacts on device scheduling strategies. We then propose a continual reinforcement learning (CRL) algorithm to solve the dual problem. The CRL algorithm learns a stable policy across historical experiences for quick adaptation to dynamics in physical states and network capacity. Simulation results show that the CRL can adapt quickly to network capacity changes and reduce normalized root mean square error (NRMSE) between physical and virtual states by up to 55.2%, using the same RB number as traditional methods.

This paper delves into the design of an energy efficient collaborative federated learning (CFL) methodology using which mobile devices exchange their FL model with a subset of their neighbors without reliance on a parameter server based on the distributed graph neural network (GNN) method. Each device is unable to send its FL model to every neighboring device due to device mobility and wireless resource limitations. To reduce the energy consumption of FL model transmission, each device must choose a subset of devices with which to share its FL model. This problem is formulated as an optimization problem to meet the constraints of delay and training loss while minimizing the energy consumption for model transmission. However, the formulated problem is difficult to solve since the device mobility patterns, and the relationship between the device connection scheme and CFL performance are unknown. To address this challenge, we analytically characterize the relationship between dynamic device connections and the performance of CFL methodology. Based on the analysis, a GNN based algorithm is proposed to enable each device to select a subset of its neighbors and the transmit power in a decentralized method. Compared to standard optimization methods that must determine device connections in a centralized manner, the GNN based method enables each device to use its neighboring devices' location and connection information to individually determine a subset of devices to transmit the local model. Given the device connections, the optimal transmit power of each device can be determined by convex optimization. Simulation results show that the proposed method can reduce the energy consumption for model transmission and training loss by up to 46% and 2%, respectively

The integration of covert communication in vehicle-to-everything (V2X) network has recently shown great potential to improve efficiency and reliability of data transmission under adversarial eavesdropping scenarios. In this paper, we propose a covert and reliable communication (CRC) framework for V2X networks, where the legitimate transmitter (Alice) attempts to communicate with a mobile receiver (Bob) in the presence of the location uncertainties of the eavesdropper (Willie). Specifically, the Bob adjusts the artificial noise power and position dynamically to communicate with Alice aided by full duplex antenna. In this context, we derive two key performance indicators of covert communication, namely the detection error probability and the effect covert throughput (ECT). Subsequently, we consider the worst case of CRC in the presence of single uncertain Willie, and derive the approximate maximum ECT expression by two-stage robust optimization. Building on this foundation, for more complex CRC scenario with multi uncertain Willies exist, we propose a deep reinforcement learning-empowered adaptation (DRLA) algorithm to maximize accumulated ECT. Extensive experiments compared to benchmarks (including stochastic selection, TD3 and DDPG) demonstrate the superiority of CRC. Specially, the designated DRLA algorithm not only can achieve a higher accumulated ECT but also can converge quickly compared with the benchmark schemes.

Space-air-ground integrated networks (SAGINs) are emerging as a pivotal element in the evolution of future wireless networks. Despite their potential, the joint design of communication and computation within SAGINs remains a formidable challenge. In this paper, the problem of energy efficiency in SAGIN-enabled probabilistic semantic communication (PSCom) system is investigated. In the considered model, a satellite needs to transmit data to multiple ground terminals (GTs) via an unmanned aerial vehicle (UAV) acting as a relay. During transmission, the satellite and the UAV can use PSCom technique to compress the transmitting data, while the GTs can automatically recover the missing information. The PSCom is underpinned by shared probabilistic graphs that serve as a common knowledge base among the transceivers, allowing for resource-saving communication at the expense of increased computation resource. Through analysis, the computation overhead function in PSCom is a piecewise function with respect to the semantic compression ratio. Therefore, it is important to make a balance between communication and computation to achieve optimal energy efficiency. The joint communication and computation problem is formulated as an optimization problem aiming to minimize the total communication and computation energy consumption of the network under latency, power, computation capacity, bandwidth, semantic compression ratio, and UAV location constraints. To solve this non-convex non-smooth problem, we propose an iterative algorithm where the closed-form solutions for computation capacity allocation and UAV altitude are obtained at each iteration. Numerical results show the effectiveness of the proposed algorithm.

In this paper, a passive low earth orbit (LEO) satellite localization framework is investigated. In our considered model, one active satellite and multiple passive satellites are selected to localize a target LEO satellite, where the active satellite transmits signals to the target satellite and passive satellites receive signals reflected by the target satellite. Based on the received signals, passive satellites calculate the transmission distances and send this distance information to the active satellite that will estimate the position of target satellite. Since LEO satellites are powered by the sun, the available energy that can be used for target satellite localization is limited and dynamic. Hence, the satellite selection scheme must be optimized for improving the localization accuracy under the energy consumption constraints. This problem is cast into an optimization setting with a goal of minimizing target satellite positioning error by jointly optimizing active/passive satellite selection and transmit power allocation. To solve this problem, a mixture Gaussian distribution-based reinforcement learning (MGD-RL) method is proposed. The proposed MGD-RL method enables each LEO satellite to determine whether to be an active or a passive satellite and optimize its transmit power under the energy constraints. Furthermore, the proposed MGD-RL method can approximate the probability distribution of value functions by using mixture Gaussian distributions, thus reducing the training complexity of the designed RL. Simulation results demonstrate that, compared to a value decomposition network method and independent RL method, the MGD-RL method can improve the positioning accuracy of the target LEO satellite by up to 26.8% and 48.9%.

Few-shot Visual Question Answering (VQA) realizes few-shot cross-modal learning, which is an emerging and challenging task in computer vision. Currently, most of the few-shot VQA methods are confined to simply extending few-shot classification methods to cross-modal tasks while ignoring the spatial distribution properties of multimodal features and cross-modal information interaction. To address this problem, we propose a novel Cross-modal feature Distribution Calibration Inference Network (CDCIN) in this paper, where a new concept named visual information entropy is proposed to realize multimodal features distribution calibration by cross-modal information interaction for more effective few-shot VQA. Visual information entropy is a statistical variable that represents the spatial distribution of visual features guided by the question, which is aligned before and after the reasoning process to mitigate redundant information and improve multi-modal features by our proposed visual information entropy calibration module. To further enhance the inference ability of cross-modal features, we additionally propose a novel pre-training method, where the reasoning sub-network of CDCIN is pretrained on the base class in a VQA classification paradigm and fine-tuned on the few-shot VQA datasets. Extensive experiments demonstrate that our proposed CDCIN achieves excellent performance on few-shot VQA and outperforms state-of-the-art methods on three widely used benchmark datasets.

Large scale artificial intelligence (AI) models possess excellent capabilities in semantic representation and understanding, making them particularly well-suited for semantic encoding and decoding. However, the substantial scale of these AI models imposes unacceptable computational resources and communication delays. To address this issue, we propose a semantic communication scheme based on robust knowledge distillation (RKD-SC) for large scale model enabled semantic communications. In the considered system, a transmitter extracts the features of the source image for robust transmission and accurate image classification at the receiver. To effectively utilize the superior capability of large scale model while make the cost affordable, we first transfer knowledge from a large scale model to a smaller scale model to serve as the semantic encoder. Then, to enhance the robustness of the system against channel noise, we propose a channel-aware autoencoder (CAA) based on the Transformer architecture. Experimental results show that the encoder of proposed RKD-SC system can achieve over 93.3% of the performance of a large scale model while compressing 96.67% number of parameters. Code: https://github.com/echojayne/RKD-SC.

In this paper, the problem of collaborative vehicle sensing is investigated. In the considered model, a set of cooperative vehicles provide sensing information to sensing request vehicles with limited sensing and communication resources. A base station (BS) determines the subset of sensing request vehicles that each cooperative vehicle will serve and the sub-regions that each cooperative vehicle will detect. We formulate an optimization problem aiming to maximize the number of successfully detected sub-regions of sensing request vehicles while satisfying the cooperative sensing energy requirement by jointly determining the cooperative vehicle association and the sensing sub-region selection. To solve this problem, we propose a graph attention based reinforcement learning (RL) algorithm that can generate the graph information vectors based on the correlation between each cooperative vehicle and each sensing request vehicle. Using the learned graph information, the joint cooperative vehicle association and sensing sub-region selection strategy will be determined. Simulation results show that the proposed scheme can improve the number of successfully detected sub-regions of sensing request vehicles by up to 12.5% compared to the conventional RL algorithm without using graph attention networks (GANs).

In this paper, a novel clustered FL framework that enables distributed edge devices with non-IID data to independently form several clusters in a distributed manner and implement FL training within each cluster is proposed. In particular, our designed clustered FL algorithm must overcome two challenges associated with FL training. First, the server has limited FL training information (i.e., the parameter server can only obtain the FL model information of each device) and limited computational power for finding the differences among a large amount of devices. Second, each device does not have the data information of other devices for device clustering and can only use global FL model parameters received from the server and its data information to determine its cluster identity, which will increase the difficulty of device clustering. To overcome these two challenges, we propose a joint gradient and loss based distributed clustering method in which each device determines its cluster identity considering the gradient similarity and training loss. The proposed clustering method not only considers how a local FL model of one device contributes to each cluster but also the direction of gradient descent thus improving clustering speed. By delegating clustering decisions to edge devices, each device can fully leverage its private data information to determine its own cluster identity, thereby reducing clustering overhead and improving overall clustering performance. Simulation results demonstrate that our proposed clustered FL algorithm can reduce clustering iterations by up to 99% compared to the existing baseline.

In this paper, we investigate an accurate synchronization between a physical network and its digital network twin (DNT) that is a virtual representation of the physical network. The considered network includes a physical network where a base station (BS) serves a set of users, and a DNT that evolves with the status of both DNT and the physical network. The BS must use its limited spectrum resources to serve the users, as well as transmit the physical network information to the cloud server for DNT synchronization. Since the DNT can predict the physical network status, the BS may not need to transmit physical network information to the server at each time slot thus saving spectrum resources to serve users. However, if the BS does not transmit physical information to the DNT over a long period of time, the DNT may not be able to represent the physical network accurately. To this end, the BS must determine whether to send physical network information to the server to update DNT and the spectrum resources used for physical network information transmission and serving users. We formulate this resources allocation problem as an optimization problem aiming to maximize the sum of data rates of all users, while minimizing the gap between the states of the physical network and the DNT. The formulated problem is challenging to solve by conventional optimization methods, since the BS may not be able to know the future status of the DNT. To solve this problem, we design a gate recurrent unit (GRU) and soft action-critic (SAC) based algorithm. The GRU enables the DNT to predict its future states by using historical state data, and updating the DNT when the BS does not transmit physical network information. The SAC based algorithm enables the BS to learn the relationship between the physical network information transmission and the future status estimation accuracy of the DNT thus determining whether to transmit physical network information to the cloud server, ensuring an accuracte synchronization between the physical network and the DNT. Simulation results demonstrate that our designed algorithm can promote the weighted sum of data rates and the similarity between the status of the DNT and the physical network by up to 10.31% compared to a baseline method integrating the GRU and the deep Q network.

In this paper, the energy efficiency maximization problem in space-air-ground integrated network (SAGIN)-enabled probabilistic semantic communication (PSC) is investigated. In the considered model, a satellite needs to transmit data to multiple ground terminals (GTs) via an unmanned aerial vehicle (UAV) acting as a relay. During transmission, the satellite and the UAV can use PSC technique to compress the transmitted data, while the GTs can automatically recover the original data. In the considered PSC system, shared probability graphs serve as a common knowledge base among the transceivers, allowing for resource-saving communication at the expense of increased computation resource. Therefore, it is important to study the trade-off between communication and computation to achieve optimal energy efficiency. The joint communication and computation problem is formulated as an optimization problem aiming to minimize the total communication and computation energy consumption of the network under latency, semantic compression ratio, and UAV location constraints. To solve this non-convex problem, we propose an alternating algorithm. Numerical results show the effectiveness of the proposed algorithm.

In this paper, the optimization of unmanned aerial vehicle (UAV) localization under jamming attacks is studied. In the considered network, a base station (BS) collaborates with an active UAV to localize a target UAV. During this positioning process, a jamming UAV transmits discontinuous signals to passive UAVs to interfere the distance information measurement. To localize the target UAV under jamming attacks, the BS jointly use two localization methods: 1) generative adversarial network (GAN)-based positioning method and 2) time difference of arrival (TDOA)-based positioning method. Since GAN-based positioning method cannot defense in a strong jamming signal while TDOA-based positioning method may consume more energy and sacrifice localization accuracy, the BS must select an appropriate positioning method (GAN-based or TDOA-based methods) and four distance measurement information of passive UAVs to estimate the position of the target UAV. This problem is formulated as an optimization problem whose goal is to minimize the positioning error between the estimated and the ground truth positions of the target UAV while considering jamming attacks and the trajectory of passive UAVs. To solve this problem, we propose a mixture Gaussian distribution model-based collaborative reinforcement learning (RL) method which enables the active UAV to determine its transmit power and trajectory, and enables the BS to select the most appropriate subsets of distance measurement information and the optimal positioning method according to the movement of passive UAVs and the unknown jamming attack pattern of the jamming UAV. Simulation results show the proposed method can reduce the positioning error of the target UAV by up to 36.5% compared to the method that does not consider the GAN-based positioning method.

In this paper, the problem of low-latency communication and computation resource allocation for digital twin (DT) over wireless networks is investigated. In the considered model, multiple physical devices in the physical network (PN) needs to frequently offload the computation task related data to the digital network twin (DNT), which is generated and controlled by the central server. Due to limited energy budget of the physical devices, both computation accuracy and wireless transmission power must be considered during the DT procedure. This joint communication and computation problem is formulated as an optimization problem whose goal is to minimize the overall transmission delay of the system under total PN energy and DNT model accuracy constraints. To solve this problem, an alternating algorithm with iteratively solving device scheduling, power control, and data offloading subproblems. For the device scheduling subproblem, the optimal solution is obtained in closed form through the dual method. Numerical results verify that the proposed algorithm can reduce the transmission delay of the system by up to 51.2% compared to the conventional schemes.

Current privacy-aware joint source-channel coding (JSCC) works aim at avoiding private information transmission by adversarially training the JSCC encoder and decoder under specific signal-to-noise ratios (SNRs) of eavesdroppers. However, these approaches incur additional computational and storage requirements as multiple neural networks must be trained for various eavesdroppers’ SNRs to determine the transmitted information. To overcome this challenge, we propose a novel privacy-aware JSCC for image transmission based on disentangled information bottleneck (DIB-PAJSCC). In particular, we derive a novel disentangled information bottleneck objective to disentangle private and public information. Given the separate information, the transmitter can transmit only public information to the receiver while minimizing reconstruction distortion. Since DIB-PAJSCC transmits only public information regardless of the eavesdroppers’ SNRs, it can eliminate additional training adapted to eavesdroppers’ SNRs. Experimental results show that DIB-PAJSCC can reduce the eavesdropping accuracy on private information by up to 20% compared to existing methods.

In this paper, a multi-modal vehicle positioning framework that jointly localizes vehicles with channel state information (CSI) and images is designed. In particular, we consider an outdoor scenario where each vehicle can communicate with only one base station (BS), and hence, it can upload its estimated CSI to only its associated BS. Each BS is equipped with a set of cameras, such that it can collect a small number of labeled CSI, a large number of unlabeled CSI, and the images taken by cameras. To exploit the unlabeled CSI data and position labels obtained from images, we design a hard expectation-maximization (EM) based deep learning (DL) algorithm. Specifically, since we do not know the corresponding relationship between unlabeled CSI and the multiple vehicle locations in images, we formulate the calculation of the log-likelihood function as a maximum matching problem. Subsequently, the model parameters are updated according to the maximum matching between unlabeled CSI and position labels obtained from images. Simulation results show that the proposed method can reduce the positioning error by up to 60% compared to a baseline that does not use images and uses only CSI fingerprint for vehicle positioning.

Millimeter-wave (mmWave) communication, a cor-nerstone in the evolution of next-generation wireless networks, offers substantial bandwidth and plays a crucial role in advancing wireless connectivity capabilities. Nevertheless, the inherent directionality and susceptibility to blockages pose significant challenges for a cost-effective beam management in densely deployed networks. This paper presents a Contextual Combina-torial Beam Management (CCBM) framework, leveraging both location-aware link qualities and beam correlation to tackle the joint access point (AP) and beam selection problem in mmWave networks, with a specific focus on mitigating coordination overhead and balancing the load across APs. Built upon a formulated multi-armed bandit problem, CCBM significantly reduces the uncertainty during online probing process by employing early stopping and attention-based selection mechanisms. Theoretical analysis establishes the asymptotically optimality of the proposed approach, complemented by extensive evaluation results showcasing the superiority of our framework over other state-of-the-art schemes in multiple dimensions.

This paper investigates the correlation between building material properties and indoor network coverage, encompassing both indoor Wi-Fi and outdoor 5G technologies to provide customized network services tailored to users' needs in diverse areas. We first analyze the impact of building material characteristics, with a special focus on wall materials, on the distribution of wireless signal propagation. Then, a ray-tracing-based method is introduced to synthetically generate high-quality training data that covers fine-grained network scenarios with a wide range of wall materials, extending beyond traditional materials. This dataset serves as the foundation for our proposed Global Embedding Isomorphism Network (GemNet), a machine learning framework that facilitates the prediction of optimal material parameters for customized in-building coverage. This innovation enables architects and builders to design novel, network-friendly materials, ensuring ubiquitous and on-demand network services. Extensive evaluations consistently demonstrate a re-markable prediction accuracy of 90.52% on material parameters, underscoring the framework's ability to optimize indoor wireless network planning through the lens of material engineering.

Collaborative federated learning (CFL) enables device cooperation in training shared machine learning models without reliance on a parameter server. However, the absence of a parameter server also impacts vulnerabilities associated with adversarial attacks, including privacy inference and Byzantine attacks. In this context, this paper introduces a novel CFL framework that enables each device to individually determine the subset of devices to transmit FL parameters to over the wireless network, based on its neighboring devices' location, current loss, and connection information, to achieve privacy protection and robust aggregation. This is formulated as an optimization problem whose goal is to minimize CFL training loss while satisfying the privacy preservation, robust aggregation, and transmission delay requirements. To solve this problem, a proximal policy optimization (PPO)-based reinforcement learning (RL) algorithm integrated with a graph neural network (GNN) is proposed. Compared to traditional algorithms that use global information with high computational complexity, the proposed GNN-RL method can be deployed on devices based on neighboring information with lower computational overhead. Simulation results show that the proposed algorithm can protect data privacy and increase identification accuracy by 15% compared to an algorithm in which devices are partially clustered for model aggregation.

In this paper, a semantic communication framework for a scenario where the transmitter and the receiver have different knowledge is proposed. In the proposed framework, the transmitter extracts semantic information from the data according to its knowledge and sends it to the receiver. The receiver requires to process the received semantic information based on its knowledge. Here, the knowledge implies a method which the transmitter or the receiver can use to process the semantic information. Since the transmitter or the receiver have different knowledge, they may have different understandings for the same information. To ensure the receiver can understand the semantic information, the transmitter requires to estimate the receiver's knowledge by asking a series of questions about the transmitted data. By evaluating the difference between the answers of the receiver and the answers of the transmitter, the transmitter can adjust the method of semantic information extraction. Since the size of the extracted semantic information and the number of the questions that the transmitter can ask are limited, the transmitter must adjust the method of semantic information extraction and select appropriate questions to transmit. This problem is formulated as an optimization problem whose goal is to maximize the similarity of answers of the transmitter and the receiver by determining semantic information while minimizing the semantic similarity of answers by determining the questions to be transmitted. To solve this problem, an adversarial reinforcement learning (ARL) algorithm is proposed. The proposed algorithm, which consists of a semantic information RL and a question RL, can find the optimal semantic information generation scheme and question selection scheme by a competitive game between two agents. Simulation results demonstrate that the proposed framework can improve the semantic similarity of answers by up to 3.7% gain and can achieve up to 15.2 % gain in terms of the average similarity of texts compared to the algorithm without the estimation of the knowledge of the receiver.

In this paper, we introduce a novel uplink semantic relay (SemRelay)-aided wireless communication system, catering to multiple users by leveraging a shared probability graph between the SemRelay and the base station (BS). In this system, users transmit text information to the SemRelay through conventional bit transmission, and the SemRelay compresses this information using a knowledge based characterized by probability graph before transmitting it to the BS through semantic communication. Then, the BS recovers the information based on the shared probability graph. While the semantic information compression incurs computational resource consumption, it significantly reduces communication resource usage. This paper addresses the challenge of minimizing overall system latency through jointly optimizing communication and computation re-source allocation, considering limited wireless resources and the system's energy budget. To address this problem, we introduce an efficient iterative algorithm, which employs block coordinate descent for communication resource allocation and exhaustive searching for determining the optimal data compression scheme. In particular, both power allocation subproblem and bandwidth allocation subproblem are proved to be convex. The complexity analysis of the proposed algorithm are also provided. Numerical results validate the effectiveness of the proposed algorithm and the superior performance of semantic communication compared to the conventional bit transmission.

By leveraging multi-view inputs to synthesize novel-view images, Neural Radiance Fields (NeRF) have emerged as a prominent technique in the realm of 3D object reconstruction. However, existing methods primarily focus on global scene reconstruction using large datasets, which necessitate substantial computational resources and impose high-quality requirements on input images. Nevertheless, in practical applications, users prioritize the 3D reconstruction results of on-demand specific object (OSO) based on their individual demands . Furthermore, the collected images transmitted through high-interference wireless environment (HIWE) leads to negatively impact the accuracy of NeRF reconstruction, thereby limiting its scalability. In this paper, we propose a novel on-demand Semantic Neural Radiance Fields (OSNeRF) scheme, which offers fast and robust 3D object reconstruction for diverse tasks. Within OSNeRF, semantic encoder is employed to extract core semantic features of OSOs from the collected scene images, semantic decoder is utilized to facilitate robust image recovery under HIWE conditions, lightweight renderer is employed for fast and efficient object reconstruction. Moreover, a semantic control unit (SCU) is introduced to guide above components, thereby enhancing the efficiency of reconstruction. Demonstrative experiments demonstrate that the proposed OSNeRF enables fast and robust object reconstruction in HIWE, surpassing the performance of state-of-the-art (SOTA) methods in terms of reconstruction quality.

In this paper, the problem of resource allocation for non-orthogonal multiple access (NOMA) enabled secure federated learning (FL) is investigated. In the considered model, a set of users participate in the FL training through transmitting their trained FL model parameters to the base stations (BSs) via NOMA techniques. To prevent data leakage, each user uses the differential privacy (DP) technique through adding Gaussian noise to its FL model parameters. The problem of minimizing overall privacy leakage of all FL participaring users is formulated as an optimization problem through jointly optimizing the connections between users and BSs, transmit power of the users, and the DP noise power. To solve the formulated non-convex optimization problem, a genetic algorithm is proposed to search for feasible solutions in which user connection matrix is taken as gene and the objective function value is taken as the fitness of solution. Simulation results show that the proposed genetic algorithm reduces privacy leakage by up to 73% compared to the conventional alternating optimization algorithm.

By leveraging multi-view inputs to synthesize novel-view images, Neural Radiance Fields (NeRF) have emerged as a prominent technique in the realm of 3D object reconstruction. However, the input images of NeRF transmitted through high-interference wireless environment (HIWE) leads to negatively impact the accuracy of 3D reconstruction, thereby limiting its scalability. Fortunately, semantic communication has been proved a effective method to solve the above problem. In this paper, we propose a novel NeRF based 3D semantic communication (NeRF-3DSC) system, which offers robust 3D reconstruction in HIWE. Within NeRF-3DSC, semantic encoder and decoder are employed to extract and recover core semantic features of task-specific specific object (TSO) from the collected images, channel encoder and decoder ensure robust transmission of compressed semantic information in HIWE, lightweight renderer based on NeRF is employed for fast and efficient 3D reconstruction. Moreover, a semantic control unit (SCU) is introduced to guide above components, thereby enhancing the efficiency of reconstruction. Demonstrative experiments demonstrate that the proposed NeRF-3DSC enables robust object reconstruction in HIWE, surpassing the performance of state-of-the-art (SOTA) methods in terms of reconstruction quality.

In this paper, the problem of joint transmission and computation resource allocation for probabilistic semantic communication (PSC) network with rate splitting multiple access (RSMA) is investigated. In the considered model, the base station (BS) needs to transmit a large amount of data, which is represented by substantial knowledge graphs, to multiple users. Due to limited communication resource, the BS needs to utilize semantic communication techniques to compress the large-sized data. In this paper, the semantic communication is enabled by shared probability graphs between the BS and users. The process of semantic compression requires computation power at the BS, which has an impact on limited power budget. Therefore, it is necessary to balance the power between transmission and computation. Based on the probability graph, the semantic rate related to semantic compression ratio is first theoretically formulated. Then, the problem is formulated as an optimization problem with the aim of maximizing the sum semantic rate of all users under total power, semantic compression ratio, and rate allocation constraints. To tackle this problem, an iterative algorithm is accordingly proposed to obtain a suboptimal solution. Numerical results validate the effectiveness of the proposed scheme.

In this paper, the problem of vehicle service mode selection (sensing, communication, or both) and vehicle connections within terahertz (THz) enabled joint sensing and communications over vehicular networks is studied. The considered network consists of several service provider vehicles (SPVs) that can provide: 1) only sensing service, 2) only communication service, and 3) both services, sensing service request vehicles, and communication service request vehicles. Based on the vehicle network topology and their service accessibility, SPVs strategically select service request vehicles to provide sensing, communication, or both services. This problem is formulated as an optimization problem, aiming to maximize the number of successfully served vehicles by jointly determining the service mode of each SPV and its associated vehicles. To solve this problem, we propose a dynamic graph neural network (GNN) model that selects appropriate graph information aggregation functions according to the vehicle network topology, thus extracting more vehicle network information compared to traditional static GNNs that use fixed aggregation functions for different vehicle network topologies. Using the extracted vehicle network information, the service mode of each SPV and its served service request vehicles will be determined. Simulation results show that the proposed dynamic GNN based scheme can improve the number of successfully served vehicles by up to 17% compared to a GNN based algorithm with a fixed neural network model.

Semantic communication has emerged as a revolutionary paradigm within wireless edge networks, showcasing remarkable communication efficiency. In contrast to traditional bit-level communication systems, semantic communication systems exhibit superior effectiveness and precision, particularly in scenarios characterized by low signal-to-noise ratios (SNR). Nonetheless, the privacy of semantic communication poses a critical challenge that demands attention. Once the attacker intercepts the semantic information through continuous eaves-dropping, the private data would be leaked under adversarial environment. Moreover, in low SNR scenario, joint optimization of anti -eavesdropping and privacy reconstruction has not yet been studied, coupled with the intricate nature of designing a cross-layer semantic protection strategy. To address this concern, this paper presents a covert and reliable semantic communication (CRSC) framework via full-duplex receiver to counter continuous eavesdropper by concealing the entire transmission process. Furthermore, a newly-defined metric, namely covert semantic throughput (CST), is introduced to quantify the system's performance. Furthermore, we formulate the maximization of average CST during the semantic transmission period as a multi-constraint optimization problem. Subsequently, we propose a reinforcement learning (RL)-empowered adaptation algorithm to address the formulated problem. Through simulation results, the effectiveness and feasibility of proposed CRSC framework are demonstrated, with an observed maximum average CST improvement of up to 42% compared to conventional communication systems in the low SNR scenario.

Abstract In this work, we consider a federated learning model in a wireless system with multiple base stations and inter‐cell interference. We apply a differentially private scheme to transmit information from users to their corresponding base station during the learning phase. We show the convergence behavior of the learning process by deriving an upper bound on its optimality gap. Furthermore, we define an optimization problem to reduce this upper bound and the total privacy leakage. To find the locally optimal solutions of this problem, we first propose an algorithm that schedules the resource blocks and users. We then extend this scheme to reduce the total privacy leakage by optimizing the differential privacy artificial noise. We apply the solutions of these two procedures as parameters of a federated learning system where each user is equipped with a classifier and communication cells have mostly fewer resource blocks than numbers of users. The simulation results show that our proposed scheduler improves the average accuracy of the predictions compared with a random scheduler. In particular, the results show an improvement of over 6%. Furthermore, its extended version with noise optimizer significantly reduces the amount of privacy leakage.

This article introduces an approach to harness digital twin (DT) technology in the realm of integrated sensing and communications (ISACs) in sixth-generation (6G) Internet of Everything (IoE) applications. We consider moving targets in a vehicular network and use DT to track and predict the motion of the vehicles. After predicting the location of the vehicle at the next time slot, the DT designs the assignment and beamforming for each vehicle. The real-time sensing information is then utilized to update and refine the DT, enabling further processing and decision making. In the DT, an extended Kalman filter (EKF) is used for the precise motion prediction. This model incorporates a dynamic Kalman gain, which is updated at each time slot based on the received echo signals. The state representation encompasses both the vehicle motion information and the error matrix, with the posterior Cramér-Rao bound (PCRB) employed to assess sensing accuracy. We consider a network with two roadside units (RSUs), and the vehicles need to be allocated to one of them. To optimize the overall transmission rate while maintaining acceptable sensing accuracy, an optimization problem is formulated. Since, it is generally hard to solve the original problem, the Lagrange multipliers and fractional programming are employed to simplify this optimization problem. To solve the simplified problem, this article introduces both the greedy and heuristic algorithms by optimizing both the vehicle assignments and predictive beamforming. The optimized results are then transferred back to the real space for ISAC applications. Recognizing the computational complexity of the greedy and heuristic algorithms, a bidirectional long short-term memory (LSTM)-based recurrent neural network (RNN) is proposed for efficient beamforming design within the DT. Simulation results demonstrate the effectiveness of the DT-based ISAC network. Notably, the LSTM-based RNN method achieves similar transmission rates as the heuristic algorithm but with significantly reduced computational complexity.

Visible light communication (VLC) is considered a promising technology for enabling Internet of Everything (IoE) applications in the sixth generation (6G), owing to its specific advantages over radio frequency (RF) communications. A comprehensive understanding of VLC channel characteristics and models is imperative for optimizing VLC technology, designing systems, and evaluating performance. This article presents an overview of ongoing research in channel characterization and modeling for VLC-IoE applications in the context of 6G. Recent advancements are systematically summarized, encompassing channel modeling methods, application scenarios, emerging combining technologies, such as reconfigurable intelligent surfaces (RISs) and integrated sensing and communication (ISAC), and distinctive channel characteristics. Additionally, future research directions in these domains are outlined to provide insights into forthcoming investigations for VLC-IoE applications in 6G.

In this article, the use of channel state information (CSI) for indoor positioning is studied. In the considered model, a server equipped with several antennas sends pilot signals to users, while each user uses the received pilot signals to estimate channel states for user positioning. To this end, we formulate the positioning problem as an optimization problem aiming to minimize the gap between the estimated positions and the ground truth positions of users. To solve this problem, we design a complex-valued neural network (CVNN) model based federated learning (FL) algorithm. Compared to standard real-valued centralized machine learning (ML) methods, our proposed algorithm has two main advantages. First, our proposed algorithm can directly process complex-valued CSI data without data transformation. Second, our proposed algorithm is a distributed ML method that does not require users to send their CSI data to the server. Since the output of our proposed algorithm is complex-valued which consists of the real and imaginary parts, we study the use of the CVNN to implement two learning tasks. First, the proposed algorithm directly outputs the estimated positions of a user. Here, the real and imaginary parts of an output neuron represent the 2D coordinates of the user. Second, the proposed method can output two CSI features (i.e., line-of-sight/non-line-of-sight transmission link classification and time of arrival (TOA) prediction) which can be used in traditional positioning algorithms. Simulation results demonstrate that our designed CVNN based FL can reduce the mean positioning error between the estimated position and the actual position by up to 36%, compared to a RVNN based FL which requires to transform CSI data into real-valued data.

In the era of 5G and beyond, the increasing complexity of wireless networks necessitates innovative frameworks for efficient management and deployment. Digital twins (DTs), embodying real-time monitoring, predictive configurations, and enhanced decision-making capabilities, stand out as a promising solution in this context. Within a time-series data-driven framework that effectively maps wireless networks into digital counterparts, encapsulated by integrated vertical and horizontal twinning phases, this study investigates the security challenges in distributed network DT (NDT) systems, which potentially undermine the reliability of subsequent network applications, such as wireless traffic forecasting. Specifically, we consider a minimal-knowledge scenario for all attackers, in that they do not have access to network data and other specialized knowledge, yet can interact with previous iterations of server-level models. In this context, we spotlight a novel fake traffic injection attack designed to compromise a distributed NDT system for wireless traffic prediction. In response, we then propose a defense mechanism, termed global-local inconsistency detection (GLID), to counteract various model poisoning threats. GLID strategically removes abnormal model parameters that deviate beyond a particular percentile range, thereby fortifying the security of network twinning process. Through extensive experiments on real-world wireless traffic data sets, our experimental evaluations show that both our attack and defense strategies significantly outperform existing baselines, highlighting the importance of security measures in the design and implementation of DTs for 5G and beyond network systems.

Positioning and sensing have long been an important area of research. Recently, this field has attracted more attention due to the rapid deployment of emerging applications and next-generation communication networks. On the one hand, emerging applications like extended reality (XR) and autonomous vehicle systems need to precisely “see” the physical world, thus greatly increasing the demands on positioning and sensing technologies. Moreover, these applications also require data rate communication links, and thus technologies like cellular networks and WiFi are excellent for supporting these applications. On the other hand, with the evolution of wireless networks, positioning, and sensing have also been considered important functions of future wireless networks that can further enhance communication performance. Although existing wireless communication has achieved significant success in the past several decades, achieving satisfying positioning and sensing performance for these emerging applications remains a challenge due to the complexity of the wireless environment and the stringent performance requirements.

Positioning has recently received considerable attention as a key enabler in emerging applications such as extended reality, unmanned aerial vehicles, and smart environments. These applications require both data communication and high-precision positioning, and thus they are particularly well-suited to be offered in wireless networks (WNs). The purpose of this paper is to provide a comprehensive overview of existing works and new trends in the field of positioning techniques from both academic and standard perspectives. The paper provides a comprehensive overview of indoor positioning in WNs, covering the background, applications, measurements, state-of-the-art technologies, and future challenges. The paper outlines the applications of positioning from the perspectives of public facilities, enterprises, and individual users. We investigate the key performance indicators and measurements of positioning systems, followed by the review of the key enabler techniques such as artificial intelligence/large models and adaptive systems. Next, we discuss a number of typical wireless positioning technologies. We extend our overview beyond the academic progress, to include the standardization efforts, and finally, we provide insight into the challenges that remain. The comprehensive overview of existing efforts and new trends in the field of indoor positioning from both academic and standardization perspectives would be a useful reference to researchers in the field.

This is Part II of the double-part Special Issue (SI) on Positioning and Sensing Over Wireless Networks. The two-part SI aims to bring cutting-edge and novel contributions on positioning and sensing over wireless networks for future and emerging applications. The accepted 51 papers are arranged into eight groups: 1) fundamental performance analysis and optimization; 2) positioning and sensing with cellular networks; 3) positioning and sensing with WiFi networks; 4) positioning and sensing with emerging communication technologies; 5) positioning and sensing applications; 6) cooperative positioning and sensing; 7) reconfigurable intelligent surfaces (RIS)-assisted positioning and sensing; and 8) privacy and security. The contributions made by the papers in Part II are summarized as follows, which correspond to the last four paper groups.

Optimizing edge caching is crucial for the advancement of next-generation (nextG) wireless networks, ensuring high-speed and low-latency services for mobile users. Existing data-driven optimization approaches often lack awareness of the distribution of random data variables and focus solely on optimizing cache hit rates, neglecting potential reliability concerns, such as base station overload and unbalanced cache issues. This oversight can result in system crashes and degraded user experience. To bridge this gap, we introduce a novel digital twin-assisted optimization framework, called D-REC, which integrates reinforcement learning (RL) with diverse intervention modules to ensure reliable caching in nextG wireless networks. We first develop a joint vertical and horizontal twinning approach to efficiently create network digital twins, which are then employed by D-REC as RL optimizers and safeguards, providing ample datasets for training and predictive evaluation of our cache replacement policy. By incorporating reliability modules into a constrained Markov decision process, D-REC can adaptively adjust actions, rewards, and states to comply with advantageous constraints, minimizing the risk of network failures. Theoretical analysis demonstrates comparable convergence rates between D-REC and vanilla data-driven methods without compromising caching performance. Extensive experiments validate that D-REC outperforms conventional approaches in cache hit rate and load balancing while effectively enforcing predetermined reliability intervention modules.

Multiple access (MA) is a crucial part of any wireless system and refers to techniques that make use of the resource dimensions (e.g., time, frequency, power, antenna, code, and message) to serve multiple users/devices/machines/ services, ideally in the most efficient way. Given the increasing need of multifunctional wireless networks for integrated communications, sensing, localization, and computing, coupled with the surge of machine learning (ML)/artificial intelligence (AI) in wireless networks, MA techniques are expected to experience a paradigm shift in 6G and beyond. In this article, we provide a tutorial, survey, and outlook on past, emerging, and future MA techniques and pay particular attention to how wireless network intelligence and multifunctionality will lead to a rethinking of those techniques. This article starts with an overview of orthogonal, physical-layer multicasting, space domain, power domain (PD), rate-splitting, code-domain MAs, MAs in other domains, and random access (RA), and highlights the importance of conducting research in universal MA (UMA) to shrink instead of grow the knowledge tree of MA schemes by providing a unified understanding of MA schemes across all resource dimensions. It then jumps into rethinking MA schemes in the era of wireless network intelligence, covering AI for MA such as AI-empowered resource allocation, optimization, channel estimation, and receiver designs, for different MA schemes, and MA for AI such as federated learning (FL)/edge intelligence and over-the-air computation (AirComp). We then discuss MA for network multifunctionality and the interplay between MA and integrated sensing, localization, and communications, covering MA for joint sensing and communications, multimodal sensing-aided communications, multimodal sensing and digital twin-assisted communications, and communication-aided sensing/localization systems. We finish with studying MA for emerging intelligent applications such as semantic communications (SeComs), virtual reality (VR), and smart radio and reconfigurable intelligent surfaces (RISs), before presenting a roadmap toward 6G standardization. Throughout the text, we also point out numerous directions that are promising for future research.

In this paper, the problem of joint user scheduling and computing resource allocation in asynchronous mobile edge computing (MEC) networks is studied. In such networks, edge devices will offload their computational tasks to an MEC server, using the energy they harvest from this server. To get their tasks processed on time using the harvested energy, edge devices will strategically schedule their task offloading, and compete for the computational resource at the MEC server. Then, the MEC server will execute these tasks asynchronously based on the arrival of the tasks. This joint user scheduling, time and computation resource allocation problem is posed as an optimization framework whose goal is to find the optimal scheduling and allocation strategy that minimizes the energy consumption of these mobile computing tasks. To solve this mixed-integer non-linear programming problem, the general benders decomposition method is adopted which decomposes the original problem into a primal problem and a master problem. Specifically, the primal problem is related to computation resource and time slot allocation, of which the optimal closed-form solution is obtained. The master problem regarding discrete user scheduling variables is constructed by adding optimality cuts or feasibility cuts according to whether the primal problem is feasible, which is a standard mixed-integer linear programming problem and can be efficiently solved. By iteratively solving the primal problem and master problem, the optimal scheduling and resource allocation scheme is obtained. Simulation results demonstrate that the proposed asynchronous computing framework reduces 87.17% energy consumption compared with conventional synchronous computing counterpart.

Joint source and channel coding (JSCC) has attracted increasing attention in semantic communications. However, JSCC is vulnerable to privacy issues due to the high relevance between the source image and channel input. In this paper, we propose a disentangled information bottleneck guided privacy-protective JSCC (DPJSCC) for image transmission, which aims at protecting private information and achieving superior image transmission performance. In particular, we propose a disentangled information bottleneck objective to compress the private information in public subcodewords and improve the reconstruction quality simultaneously. To optimize JSCC neural networks using the proposed objective, we derive a differentiable estimation based on variational approximation and the density-ratio trick. Additionally, we design a password-based privacy-protective algorithm that encrypts the private subcodewords, achieving joint optimization with JSCC neural networks. The proposed algorithm involves an encryptor for encrypting private information and a decryptor for recovering it at the legitimate receiver. A loss function is derived based on the maximum entropy principle for jointly training the encryptor, decryptor, and JSCC decoder to maximize eavesdropping uncertainty and improve reconstruction quality. Experimental results show that DPJSCC reduces eavesdropping accuracy on private information by up to 18% and decreases inference time by 10%.

Visible light positioning (VLP) is an accurate and low-cost positioning technique. However, existing VLP algorithms require multiple luminaires or multiple sensors to achieve the desired positioning accuracy, which may not be satisfied in practice. To circumvent this challenge, a novel visual odometry (VO) assisted VLP algorithm (VO-VLP) is proposed, which can achieve accurate positioning using only a single luminaire at the transmitter and a single camera at the receiver. In the considered model, the luminaires are equipped on the ceiling and consistently broadcast coordinate information of the luminaires by visible light communication (VLC). A user equipped with a camera captures photos of the ceiling so as to locate its position via VO-VLP. In particular, VO-VLP first uses the single luminaire’s circle feature and VLC information to obtain the pose and location of the user. However, there are dual solutions due to the limited received information in the single-luminaire scenario and the symmetry of the circular luminaire. Then, we propose a duality elimination method to eliminate the wrong one by introducing VO to exploit the visual features on the ceiling in two consecutive images, which are captured when the user moves. To verify the feasibility of our designed VO-VLP, a prototype is implemented. A cooperative multi-information image processing method is proposed for the prototype to ensure that the VLC information and the visual information of the luminaire and the ceiling can be simultaneously received for real-time positioning. Simulations and experiments are conducted to prove that VO-VLP can achieve accurate positioning with only a single luminaire and a camera without any extra sensors, such as an inertial measurement unit. In particular, simulation results show that the proposed indoor positioning algorithm can achieve a 97% positioning accuracy of around 10 cm, and experimental results show that the average positioning accuracy is less than 10 cm.

The susceptibility of millimeter-wave (mmWave) links to blockages poses challenges for maintaining consistent high-rate performance. By predicting link quality in advance at specific locations or times of interest, proactive resource allocation techniques, such as link-quality-aware scheduling, can be employed to optimize the utilization of network resources. In this paper, we introduce a map-driven link quality prediction framework that divides the problem into long-term and short-term link quality predictions to cater to the needs of mobile computing. The first stage aims to predict a long-term radio map considering static network characteristics. We propose to separate LoS and NLoS scenarios, and build an analytical model and a regression-based approach to construct a complete link quality map in the spatial domain. Next, short-term link quality prediction is explored to anticipate future variations in link quality through a spatial-temporal attention-based prediction framework. The essence of this approach lies in capturing the spatial correlation and temporal dependency of mmWave wireless characteristics, followed by an attention mechanism to complement the dynamic link quality prediction task. On top of that, we also design a regional training mechanism with a weighted loss function to address the classical data imbalance problem of map-driven prediction. Extensive experimental and simulation results show that our integrated framework effectively captures comprehensive spatial-temporal knowledge and achieves significantly higher accuracy than other baseline prediction methods, making it a promising solution for a wide range proactive configuration tasks in mobile mmWave networks.

In this paper, a clustered parallel training algorithm is designed for personalized federated learning (Per-FL), called CPPer-FL. CPPer-FL improves the communication and training efficiency of Per-FL from two perspectives, namely, less burden for the central server and lower interaction idling delay. CPPer-FL adopts a client-edge-center learning architecture, which offloads the central server's model aggregation and communication burden to distributed edge servers. Also, CPPer-FL redesigns the cascading model synchronization and updating procedure in conventional Per-FL and changes it to a parallel manner, thus improving the interaction efficiency in the training process. Further, for the proposed hierarchical architecture, two approaches are proposed to cater to Per-FL: similarity-based clustering for client-edge association and personalized model aggregation for parallel model updating, such that clients' personal features can be preserved in the training process. The convergence of CPPer-FL has been formally analyzed and proved. Evaluation results validate the communication efficiency, model convergence, and model accuracy improvement.

In this paper, the problem of using one active unmanned aerial vehicle (UAV) and four passive UAVs to localize a 3D target UAV in real time is investigated. In the considered model, each passive UAV receives reflection signals from the target UAV, which are initially transmitted by the active UAV. The received reflection signals allow each passive UAV to estimate the signal transmission distance which will be transmitted to a base station (BS) for the estimation of the position of the target UAV. Due to the movement of the target UAV, each active/passive UAV must optimize its trajectory to continuously localize the target UAV. Meanwhile, since the accuracy of the distance estimation depends on the signal-to-noise ratio of the transmission signals, the active UAV must optimize its transmit power. This problem is formulated as an optimization problem whose goal is to jointly optimize the transmit power of the active UAV and trajectories of both active and passive UAVs so as to maximize the target UAV positioning accuracy. To solve this problem, a Z function decomposition based reinforcement learning (ZD-RL) method is proposed. Compared to value function decomposition based RL (VD-RL), the proposed method can find the probability distribution of the sum of future rewards to accurately estimate the expected value of the sum of future rewards thus finding better transmit power of the active UAV and trajectories for both active and passive UAVs and improving target UAV positioning accuracy. Simulation results show that the proposed ZD-RL method can reduce the positioning errors by up to 39.4% and 64.6%, compared to VD-RL and independent deep RL methods, respectively.

In this paper, the problem of vehicle service mode selection (sensing, communication, or both) and vehicle connections within terahertz (THz) enabled joint sensing and communications over vehicular networks is studied. The considered network consists of several service provider vehicles (SPVs) that can provide: 1) only sensing service, 2) only communication service, and 3) both services, sensing service request vehicles, and communication service request vehicles. Based on the vehicle network topology and their service accessibility, SPVs strategically select service request vehicles to provide sensing, communication, or both services. This problem is formulated as an optimization problem, aiming to maximize the number of successfully served vehicles by jointly determining the service mode of each SPV and its associated vehicles. To solve this problem, we propose a dynamic graph neural network (GNN) model that selects appropriate graph information aggregation functions according to the vehicle network topology, thus extracting more vehicle network information compared to traditional static GNNs that use fixed aggregation functions for different vehicle network topologies. Using the extracted vehicle network information, the service mode of each SPV and its served service request vehicles will be determined. Simulation results show that the proposed dynamic GNN based method can improve the number of successfully served vehicles by up to 17% and 28% compared to a GNN based algorithm with a fixed neural network model and a conventional optimization algorithm without using GNNs.

In this paper, a new communication-efficient federated learning (FL) framework is proposed, inspired by vector quantized compressed sensing. The basic strategy of the proposed framework is to compress the local model update at each device by applying dimensionality reduction followed by vector quantization. Subsequently, the global model update is reconstructed at a parameter server by applying a sparse signal recovery algorithm to the aggregation of the compressed local model updates. By harnessing the benefits of both dimensionality reduction and vector quantization, the proposed framework effectively reduces the communication overhead of local update transmissions. Both the design of the vector quantizer and the key parameters for the compression are optimized so as to minimize the reconstruction error of the global model update under the constraint of wireless link capacity. By considering the reconstruction error, the convergence rate of the proposed framework is also analyzed for a non-convex loss function. Simulation results on the MNIST and FEMNIST datasets demonstrate that the proposed framework can improve classification accuracy by more than 2.4% compared to state-of-the-art FL frameworks when the communication overhead of the local model update transmission is 0.1 bit per local model entry.

This paper considers improving wireless communication and computation efficiency in federated learning (FL) via model quantization. In the proposed bitwidth FL scheme, edge devices train and transmit quantized versions of their local FL model parameters to a coordinating server, which, in turn, aggregates them into a quantized global model and synchronizes the devices. The goal is to jointly determine the bitwidths employed for local FL model quantization and the set of devices participating in FL training at each iteration. We pose this as an optimization problem that aims to minimize the training loss of quantized FL under a per-iteration device sampling budget and delay requirement. However, the formulated problem is difficult to solve without (i) a concrete understanding of how quantization impacts global ML performance and (ii) the ability of the server to construct estimates of this process efficiently. To address the first challenge, we analytically characterize how limited wireless resources and induced quantization errors affect the performance of the proposed FL method. Our results quantify how the improvement of FL training loss between two consecutive iterations depends on the device selection and quantization scheme as well as on several parameters inherent to the model being learned. Then, to address the second challenge, we show that the FL training process can be described as a Markov decision process (MDP) and propose a model-based reinforcement learning (RL) method to optimize action selection over iterations. Compared to model-free RL, this model-based RL approach leverages the derived mathematical characterization of the FL training process to discover an effective device selection and quantization scheme without imposing additional device communication overhead. Simulation results show that the proposed FL algorithm can reduce the convergence time by 29% and 63% compared to a model free RL method and the standard FL method, respectively.

In this paper, the performance optimization of federated learning (FL), when deployed over a realistic wireless multiple-input multiple-output (MIMO) communication system with digital modulation and over-the-air computation (AirComp) is studied. In particular, a MIMO system is considered in which edge devices transmit their local FL models (trained using their locally collected data) to a parameter server (PS) using beamforming to maximize the number of devices scheduled for transmission. The PS, acting as a central controller, generates a global FL model using the received local FL models and broadcasts it back to all devices. Due to the limited bandwidth in a wireless network, AirComp is adopted to enable efficient wireless data aggregation. However, fading of wireless channels can produce aggregate distortions in an AirComp-based FL scheme. To tackle this challenge, we propose a modified federated averaging (FedAvg) algorithm that combines digital modulation with AirComp to mitigate wireless fading while ensuring the communication efficiency. This is achieved by a joint transmit and receive beamforming design, which is formulated as an optimization problem to dynamically adjust the beamforming matrices based on current FL model parameters so as to minimize the transmitting error and ensure the FL performance. To achieve this goal, we first analytically characterize how the beamforming matrices affect the performance of the FedAvg in different iterations. Based on this relationship, an artificial neural network (ANN) is used to estimate the local FL models of all devices and adjust the beamforming matrices at the PS for future model transmission. The algorithmic advantages and improved performance of the proposed methodologies are demonstrated through extensive numerical experiments.

In this paper, a semantic communication framework for image data transmission is developed. In the investigated framework, a set of servers cooperatively transmit image data to a set of users utilizing semantic communication techniques, which enable servers to transmit only the semantic information that accurately captures the meaning of images. To evaluate the performance of studied semantic communication system, a multimodal metric called image-to-graph semantic similarity (ISS) is proposed to measure the correlation between the extracted semantic information and the original image. To meet the ISS requirement of each user, each server must jointly determine the semantic information to be transmitted and the resource blocks (RBs) used for semantic information transmission. Due to the co-channel interference among users associated with different servers, each server must cooperate with other servers to find a globally optimal semantic oriented RB allocation. We formulate this problem as an optimization problem whose goal is to minimize the sum of the average transmission latency of each server while reaching the ISS requirement. To solve this problem, we propose a value decomposition based entropy-maximized multi-agent reinforcement learning (RL) algorithm. The proposed algorithm enables each server to coordinate with other servers in training stage and execute RB allocation in a distributed manner to approach to a globally optimal performance with less training iterations. Compared to traditional multi-agent RL algorithms, the proposed RL framework improves the exploration of valuable action of servers and the probability of finding a globally optimal RB allocation policy based on local observation of wireless and semantic communication environments. Simulation results show that the proposed algorithm can reduce the transmission delay by up to 16.1% and improve the convergence speed by up to 100% compared to the traditional multi-agent RL algorithms.

In this paper, the problem of maximizing the sum of data rates of all users in an intelligent reflecting surface (IRS)-assisted millimeter wave multicast multiple-input multiple-output communication system is studied. In the considered model, one IRS is deployed to assist the communication from a multi-antenna base station (BS) to the multi-antenna users that are clustered into several groups. Our goal is to maximize the sum rate of all users by jointly optimizing the transmit beamforming matrices of the BS, the receive beamforming matrices of the users, and the phase shifts of the IRS. To solve this non-convex problem, we first use a block diagonalization method to represent the beamforming matrices of the BS and the users by the phase shifts of the IRS. Then, substituting the expressions of the beamforming matrices of the BS and the users, the original sum-rate maximization problem can be transformed into a problem that only needs to optimize the phase shifts of the IRS. To solve the transformed problem, a manifold method is used. Simulation results show that the proposed scheme can achieve up to 28.6% gain in terms of the sum rate of all users compared to the algorithm that optimizes the hybrid beamforming matrices of the BS and the users using our proposed scheme and randomly determines the phase shifts of the IRS.

Millimeter-wave (mmWave) communication is a promising technology that has become a key component of next-generation wireless networks due to its large available band-width. However, the susceptibility of mmWave link to dynamic blockages makes it challenging to maintain consistently high rate performance. Hence, it is imperative to have the knowledge of link quality in advance at the location of interest to proactively optimize the use of network resources. In this work, we propose a Spatial-Temporal Attention-based Prediction (STAP) framework to predict the link quality at arbitrary locations in the presence of dynamic blockages. Specifically, our STAP model is built to capture the spatial correlation and temporal dependency of mmWave wireless characteristics in an integrated module, followed by an attention mechanism to complement the link quality prediction task. On top of that, we also design a regional training approach with a weighted loss function to address the data imbalance problem of map-based prediction. Extensive evaluation results show that our framework effectively captures comprehensive spatial-temporal knowledge and achieves significantly higher accuracy than other baseline prediction methods.

In this paper, we consider the design of an energy efficient collaborative federated learning (CFL) methodology where devices exchange their local FL parameters with a subset of their neighbors without reliance on a parameter server. In the considered model, mobile devices implement the designed CFL to train their local FL models using their own datasets over a realistic wireless network. Due to the limited wireless resources and user movements, each device may not be able to transmit its FL parameters with all neighboring devices. Therefore, each device must select a subset of devices to share its FL parameters and optimize the transmit power. This problem is formulated as an optimization problem, whose goal is to minimize CFL training energy consumption while satisfying the delay and CFL training loss requirements. To solve this problem, a two-stage solution is proposed. At the first stage, a graph neural network (GNN) based algorithm is proposed, which enables each device to individually determine the subset of devices to transmit FL parameters using its neighboring devices' location and connection information. Compared to standard iterative algorithms that need to iteratively optimize device connections and transmit power, the proposed GNN based method can directly obtain the optimal device connections without iterative optimization. Given the optimal device connections, at the second stage, each device can directly obtain the optimal transmit power. Simulation results show that the proposed algorithm can decrease energy consumption by up to 46% compared to the algorithm where each device will directly connect to its first and second nearest neighbors.

In this paper, we consider the optimization of federated learning (FL) over a realistic wireless multiple-input multiple-output (MIMO) communication system with digital modulation and over-the-air computation (AirComp). In such a system, MIMO devices transmit their locally trained FL models to a parameter server (PS) using beamforming to maximize the number of devices scheduled for transmission. AirComp enables efficient wireless model aggregation by the PS in bandwidth-limited settings. However, wireless channel fading can produce distortions in AirComp-based FL. To tackle this challenge, we develop a novel aggregation scheme that combines digital modulation with AirComp to mitigate wireless fading while ensuring communication efficiency. We formulate this as a joint transmit-receive beamforming design optimization problem which dynamically adjusts the beamforming matrices to minimize the FL training loss with transmission errors. To solve this problem based on limited information at the PS, we employ an artificial neural network (ANN) to estimate the local FL models of all devices. Then, we derive a closed-form optimal design of the transmit and receive beamforming matrices based on predicted FL models. Numerical evaluations validate the advantages of the proposed methodology in terms of model training performance compared with baselines.

In this paper, the use of channel state information (CSI) for indoor positioning is investigated. In the considered model, a base station (BS) equipped with several antennas sends pilot signals to a user that transmits the received pilot signals back to the BS. The BS will use the received CSI data to estimate the position of the user. To this end, we formulate this positioning problem as an optimization problem aiming to minimize the mean square error between the estimated position and the actual position of the user. To solve this problem, we design a complex-valued neural network (CVNN) based positioning algorithm. Compared to real-valued neural networks (RVNNs) that need to convert complex-valued CSI data into real-valued data, the proposed method uses original CSI data to train the CVNN model for user positioning. Since the output of our proposed algorithm is complex-valued and it consists of the real and imaginary parts, we can use it to implement two learning tasks. Based on this property, two use cases of the proposed algorithm are proposed: 1) the algorithm directly outputs the estimated position of the user. Here, the real and imaginary parts of an output neuron represent the 2D coordinates of the user, 2) the algorithm outputs two CSI features (i.e., line-of-sight/non-line-of-sight transmission link classification and time of arrival (TOA) prediction) which can be used in traditional positioning algorithms. Simulation results demonstrate that our designed CVNN based algorithm can reduce the mean positioning error between the estimated position and the actual position by up to 11.1%, compared to a RVNN based method which has to transform CSI data into real-valued data.

In this paper, the problem of using several controlled unmanned aerial vehicles (UAVs) to localize a target UAV in real time is investigated. In the considered model, the controlled UAV consists of one active UAV and four passive UAVs. Each passive UAV receives signals transmitted from the active UAV and reflected by the target UAV, and then estimates the distance from the active UAV to the target UAV and then from the target UAV to the passive UAV. Each passive UAV then transmits this distance information to a base station (BS), which estimates the location of the target UAV. Since the target UAV will change its location according to its performed task, each controlled UAV must optimize its trajectory to continuously localize the target UAV. This trajectory design problem is formulated as an optimization problem whose goal is to jointly optimize the trajectories of active and passive UAVs so as to maximize the target UAV positioning accuracy. To solve this problem, a Z function decomposition based reinforcement learning (ZD-RL) method is proposed. Compared to value function decomposition based RL (VD-RL), the proposed method can find the probability distribution of the sum of future rewards to accurately estimate the expected value of the sum of future rewards, thus finding better trajectories for controlled UAVs and improving target UAV positioning accuracy. Simulation results show that the proposed ZD-RL method can reduce the positioning errors by up to 58.3% and 84.8%, compared to VD-RL and independent DRL methods, respectively.

In this paper, the problem of joint sensing and communications is studied over terahertz (THz) vehicular networks. In the studied model, a set of service provider vehicles provide either communication service or sensing service to communication target vehicles or sensing target vehicles, respectively. Therefore, it is necessary to determine the service mode (i.e., providing sensing or communication service) for each service provider vehicle and the subset of target vehicles that each service provider vehicle will serve. The problem is formulated as an optimization problem aiming to maximize the sum of the data rates of all communication target vehicles while satisfying the sensing service requirements of all sensing target vehicles by determining the service mode and the user association for each service provider vehicle. To solve this problem, a graph neural network (GNN) based algorithm with a heterogeneous graph representation is proposed. The proposed algorithm enables the central controller to extract each vehicle's graph information related to its location, connection, and communication interference. Using the extracted graph information, the joint service mode selection and user association strategy will be determined. Simulation results show that the proposed GNN-based scheme can achieve 94% of the sum rate produced by the optimal solution, and yield up to 3.95% and 36.16% improvements in sum rate, respectively, compared to a homogeneous GNN-based algorithm and the conventional optimization algorithm without using GNNs.

In this paper, a novel paradigm of mobile edgequantum computing (MEQC) is proposed, which brings quantum computing capacities to mobile edge networks that are closer to mobile users (i.e., edge devices). First, we propose an MEQC system model where mobile users can offload computational tasks to scalable quantum computers via edge servers with cryogenic components and fault-tolerant schemes. Second, we show that it is NP-hard to obtain a centralized solution to the partial offloading problem in MEQC in terms of the optimal latency and energy cost of classical and quantum computing. Third, we propose a multi-agent hybrid discrete-continuous deep reinforcement learning using proximal policy optimization to learn the long-term sustainable offloading strategy without prior knowledge. Finally, experimental results demonstrate that the proposed algorithm can reduce at least 30% of the cost compared with the existing baseline solutions under different system settings.

Visible light positioning (VLP) is a promising positioning technique, which, however, typically requires multiple luminaires to achieve accurate positioning. This paper proposes a novel visual odometry (VO) assisted visible light positioning algorithm (VO-VLP) in achieving positioning with only a single luminaire. In the considered model, a user equipped with a camera jointly uses geometric features in the captured images and coordinates information obtained via visible light communication (VLC) for positioning. The proposed VLP algorithm does not rely on any extra inertial measurement unit and relaxes the tilted angle limitation at the user. In particular, VO-VLP first uses the circle feature of a luminaire to obtain dual normal vectors of the luminaire. Then, the basic principle of VO is used to eliminate the wrong normal vector by exploiting the geometric features in two consecutive images captured when the user moves. Finally, the pose and location of the user are obtained by using an artificially marked point on the luminaire's contour. VO-VLP can achieve accurate positioning with only a single luminaire and a camera. Simulation results show that the proposed indoor positioning algorithm can achieve a 97th-percentile positioning accuracy of around 10 cm.

To enable ultra-high throughputs while addressing the potential blockage problem, maintaining an adaptive access point (AP) planning is critical to mmWave networking. By investigating the hidden interaction between the environment map and the placement of mmWave APs, we develop an adaptive AP planning (E-app) approach that can accurately sense the environment dynamics, reconstruct the obstacle map, and then predict the placements of mmWave APs adaptively. Specifically, our solution leverages mmWave radio itself to sniff the unacceptable performance degradation through sensing only a small fraction of observation points that are identified by a sparsity-aware analytical model, thereby accurately triggering a prediction module for AP positioning when necessary. Extensive evaluations show a very high prediction accuracy for our solution, which can provide around 25% improvement on user throughput performance in mmWave WLANs. This intelligent AP-planning framework well handles the environment dynamics that affect the average-case network performance, which is of utmost interest for network deployers because of its usage convenience and adaptivity.

In this paper, the problem of joint communication and sensing is studied in the context of terahertz (THz) vehicular networks. In the studied model, a set of service provider vehicles (SPVs) provide either communication service or sensing service to target vehicles, where it is essential to determine 1) the service mode (i.e., providing either communication or sensing service) for each SPV and 2) the subset of target vehicles that each SPV will serve. The problem is formulated as an optimization problem aiming to maximize the sum of the data rates of the communication target vehicles, while satisfying the sensing service requirements of the sensing target vehicles, by determining the service mode and the target vehicle association for each SPV. To solve this problem, a graph neural network (GNN) based algorithm with a heterogeneous graph representation is proposed. The proposed algorithm enables the central controller to extract each vehicle’s graph information related to its location, connection, and communication interference. Using this extracted graph information, a joint service mode selection and target vehicle association strategy is then determined to adapt to the dynamic vehicle topology with various vehicle types (e.g., target vehicles and service provider vehicles). Simulation results show that the proposed GNN-based scheme can achieve 93.66% of the sum rate achieved by the optimal solution, and yield up to 3.16% and 31.86% improvements in sum rate, respectively, over a homogeneous GNN-based algorithm and a conventional optimization algorithm without using GNNs.

Joint source and channel coding (JSCC) for image transmission has attracted increasing attention due to its robustness and high efficiency. However, the existing deep JSCC research mainly focuses on minimizing the distortion between the transmitted and received information under a fixed number of available channels. Therefore, the transmitted rate may be far more than its required minimum value. In this paper, an adaptive information bottleneck (IB) guided joint source and channel coding (AIB-JSCC) method is proposed for image transmission. The goal of AIB-JSCC is to reduce the transmission rate while improving the image reconstruction quality. In particular, a new IB objective for image transmission is proposed so as to minimize the distortion and the transmission rate. A mathematically tractable lower bound on the proposed objective is derived, and then, adopted as the loss function of AIB-JSCC. To trade off compression and reconstruction quality, an adaptive algorithm is proposed to adjust the hyperparameter of the proposed loss function dynamically according to the distortion during the training. Experimental results show that AIB-JSCC can significantly reduce the required amount of transmitted data and improve the reconstruction quality and downstream task accuracy.

In this paper, the problem of wireless resource allocation and semantic information extraction for energy efficient semantic communications over wireless networks with rate splitting is investigated. In the considered model, a base station (BS) first extracts semantic information from its large-scale data, and then transmits the small-sized semantic information to each user which recovers the original data based on its local common knowledge. At the BS side, the probability graph is used to extract multi-level semantic information. In the downlink transmission, a rate splitting scheme is adopted, while the private small-sized semantic information is transmitted through private message and the common knowledge is transmitted through common message. Due to limited wireless resource, both computation energy and transmission energy are considered. This joint computation and communication problem is formulated as an optimization problem aiming to minimize the total communication and computation energy consumption of the network under computation, latency, and transmit power constraints. To solve this problem, an alternating algorithm is proposed where the closed-form solutions for semantic information extraction ratio and computation frequency are obtained at each step. Numerical results verify the effectiveness of the proposed algorithm.

Visible light positioning (VLP) is an accurate indoor positioning technology that uses luminaires as transmitters. In particular, circular luminaires are a common source type for VLP, which are typically treated only as point sources for positioning, while ignoring their geometry characteristics. In this paper, the arc feature of the circular luminaire and the coordinate information obtained via visible light communication (VLC) are jointly used for positioning, and a novel perspective arcs approach is proposed for VLC-enabled indoor positioning. The proposed approach does not rely on any inertial measurement unit and has no tilted angle limitation at the user. First, a VLC assisted perspective circle and arc algorithm (V-PCA) is proposed for a scenario in which a complete luminaire and an incomplete one can be captured by the user. Based on plane and solid geometry theory, the relationship between the luminaire and the user is exploited to estimate the orientation and the coordinate of the luminaire in the camera coordinate system. Then, the pose and location of the user in the world coordinate system are obtained by single-view geometry theory. Considering the cases in which parts of VLC links are blocked, an anti-occlusion VLC assisted perspective arcs algorithm (OA-V-PA) is proposed. In OA-V-PA, an approximation method is developed to estimate the projection of the luminaire’s center on the image and, then, to calculate the pose and location of the user. Simulation results show that the proposed indoor positioning algorithm can achieve a 90th percentile positioning accuracy of around 10 cm. Moreover, an experimental prototype is implemented to verify the feasibility. In the established prototype, a fused image processing method is proposed to simultaneously obtain the VLC information and the geometric information. Experimental results in the established prototype show that the average positioning accuracy is less than 5 cm for different tilted angles of the user.

This paper considers improving wireless communication and computation efficiency in federated learning (FL) via model quantization. In the proposed bitwidth FL scheme, edge devices train and transmit quantized versions of their local FL model parameters to a coordinating server, which, in turn, aggregates them into a quantized global model and synchronizes the devices. With the goal of jointly determining the set of participating devices in each training iteration and the bitwidths employed at the devices, we pose an optimization problem for minimizing the training loss of quantized FL under a device sampling budget and delay requirement. Our analytical results show that the improvement of FL training loss between two consecutive iterations depends on not only the device selection and quantization scheme, but also on several parameters inherent to the model being learned. As a result, we propose, a model-based reinforcement learning (RL) method to optimize action selection over iterations. Compared to model-free RL, the proposed approach leverages the derived mathematical characterization of the FL training process to discover an effective device selection and quantization scheme without imposing additional device communication overhead. Numerical evaluations show that the proposed FL framework can achieve the same classification performance while reducing the number of training iterations needed for convergence by 20% compared to model-free RL-based FL.

In this paper, the problem of maximizing the sum rate of all users in an intelligent reflecting surface (IRS)-assisted millimeter wave multicast multiple-input multiple-output communication system is studied. In the considered model, one IRS is deployed to assist the communication from a multi-antenna base station (BS) to the multi-antenna users that are clustered into several groups. Our goal is to maximize the sum rate of all users by jointly optimizing the transmit beamforming matrices of the BS, the receive beamforming matrices of the users, and the phase shifts of the IRS. To solve this non-convex problem, we first use a block diagonalization method to represent the beamforming matrices of the BS and the users by the phase shifts of the IRS. Then, substituting the expressions of the beamforming matrices of the BS and the users, the original sum-rate maximization problem can be transformed into a problem that only needs to optimize the phase shifts of the IRS. To solve the transformed problem, a manifold method is used. Simulation results show that the proposed scheme can achieve up to 13.3 % gain in terms of the sum rate of all users compared to the algorithm that optimizes the hybrid beamforming matrices of the BS and the users using our proposed scheme and randomly determines the phase shifts of the IRS.

In this paper, a semantic communication framework for image transmission is investigated. In the framework, a server transmits image data to a set of users utilizing semantic communication techniques, which enable the server to transmit only the semantic information that accurately captures the meaning of an image. To evaluate the performance of the studied semantic communication system, we propose a multimodal metric called image-to-graph semantic similarity (ISS). The significance of this new metric is that it can measure the correlation of the meaning between semantic information and the original image. To meet the ISS requirement of each user, the server must jointly determine the semantic information to be transmitted and the resource blocks (RBs) used for semantic information transmission. We formulate this problem as an optimization problem whose goal is to minimize the average transmission latency while reaching the ISS requirement. To solve this problem, we propose a model-based actor critic deep reinforcement learning (DRL) algorithm. Compared to traditional actor critic DRL, in the proposed algorithm, we design a novel value function to improve the action exploration thus improving the probability of finding an optimal solution. Simulation results show that the proposed method can reduce the transmission delay by 16.4% and improves the convergence speed by up to 50% compared to the traditional actor critic DRL.

In this paper, the optimization of semantic communications over energy harvesting networks is studied. In the considered model, a set of users use semantic communication techniques and the harvested energy to transmit text data to a base station (BS). Here, semantic communication techniques enable each user to transmit the meaning of the original data (called semantic information) thereby reducing its transmission delay and energy consumption. The BS will recover the data using the received semantic information. To further improve communication efficiency, each user can transmit only partial semantic information to the BS. Therefore, each user needs to jointly determine the partial semantic information to be transmitted and the resource block (RB) that is used for semantic information transmission. This problem is formulated as an optimization problem whose goal is to maximize the sum of all users’ similarities that capture the differences between the original data that each user needs to transmit and the data recovered by the BS. To solve this problem, a value decomposition based deep Q network is proposed, which enables the users to jointly find the semantic information transmission and the RB allocation schemes that maximize the sum of all users’ similarities. Simulation results demonstrate that the proposed method can improve sum of all users’ similarities by up to threefold compared to the independent reinforcement learning.

In this paper, we investigate the exploration-exploitation dilemma of reinforcement learning algorithms. We adapt the information directed sampling, an exploration framework that measures the information gain of a policy, to the continuous reinforcement learning. To stabilize the off-policy learning process and further improve the sample efficiency, we propose to use a randomized learning target and to dynamically adjust the update-to-data ratio for different parts of the neural network model. Experiments show that our approach significantly improves over existing methods and successfully completes tasks with highly sparse reward signals.

Recent studies show that depression can be partially reflected from human facial attributes. Since facial attributes have various data structures and carry different information, existing approaches fail to specifically consider the optimal way to extract depression-related features from each of them, as well as investigate the best fusion strategy. In this paper, we propose to extend Neural Architecture Search (NAS) technique to design an optimal model for multiple facial attributes-based depression recognition, which can be efficiently and robustly implemented in a small dataset. Our approach first conducts a warmer up step to the feature extractor of each facial attribute, aiming to largely reduce the search space and provide customized architecture, where each feature extractor can be either a Convolution Neural Networks (CNN) or Graph Neural Networks (GNN). Then, we conduct an end-to-end architecture search for all feature extractors and the fusion network, allowing the complementary depression cues to be optimally combined with less redundancy. The experimental results on AVEC 2016 dataset show that the model explored by our approach achieves breakthrough performance with 27% and 30% RMSE and MAE improvements over the existing state-of-the-art. In light of these findings, this paper provides solid evidence and a strong baseline for applying NAS to time-series data-based mental health analysis.

In this paper, the problem of wireless resource allocation and semantic information extraction for energy efficient semantic communications over wireless networks is investigated. In the considered model, each user first extracts the semantic information from its large-scale data, and then transmits the small-sized semantic information to the base station (BS) which recovers the original data. Due to the limited energy budget of wireless users, both local computational energy and transmission energy must be considered. This joint computation and communication problem is formulated as an optimization problem whose goal is to minimize the total energy consumption of the network under a latency constraint. To solve this problem, an iterative algorithm is proposed where the optimal solution for joint bandwidth allocation, power control, and computation frequency optimization problem can be obtained. Numerical results show the effectiveness of the proposed algorithm.

In this article, the deployment of federated learning (FL) is investigated in an energy harvesting wireless network in which the base stations (BSs) employs massive multiple-input–multiple-output (MIMO) to serve a set of users powered by independent energy harvesting sources. Since a certain number of users may not be able to participate in FL due to interference and energy constraints, a joint energy management and user scheduling problem in FL over wireless systems is formulated. This problem is formulated as an optimization problem whose goal is to minimize the FL training loss via optimizing user scheduling. To find how the transmit power, the number of scheduled users and user association, affect the training loss, the FL convergence rate is first analyzed. Given this analytical result, the original optimization problem can be decomposed, simplified, and solved. Simulation results show that the proposed user scheduling and user association algorithm can reduce training loss compared to a standard FL algorithm.

This article proposes a hybrid dimming (HD) scheme based on joint light-emitting diode (LED) selection and precoding design (TASP-HD) for multiple-user (MU) multiple-cell (MC) visible light communications (VLCs) systems. In TASP-HD, both the LED selection and the precoding of each cell can be dynamically adjusted to reduce the intra- and inter-cell interferences while satisfying illumination constraints. First, an MU-MC-VLC system model is established, and then a sum-rate maximization problem under the dimming level and illumination uniformity constraints is formulated. In this studied problem, the indices of activated LEDs and precoding matrices are optimized, which result in a complex nonconvex mixed-integer problem. To solve this problem, the original problem is separated into two subproblems. The first subproblem, which maximizes the sum rate of users via optimizing the LED selection with a given precoding matrix, is a mixed-integer problem solved by the penalty method. With the optimized LED selection matrix, the second subproblem which focuses on the maximization of the sum-rate via optimizing the precoding matrix is solved by the Lagrangian dual method. Finally, these two subproblems are iteratively solved to obtain a convergent solution. Simulation results verify that in a typical indoor scenario under a dimming level of 70%, the mean bandwidth efficiency (MBE) of TASP-HD is 4.8 bit/s/Hz and 7.13 bit/s/Hz greater than analog dimming (AD) and digital dimming (DD), respectively.

This is Part II of a double-part special issue on distributed learning over wireless edge networks. This two-part special issue features papers dealing with two main research challenges: optimization of wireless network performance for efficient implementation of distributed learning in wireless networks, and distributed learning for solving communication problems and optimizing network performance. The accepted papers in this special issue have been grouped into three topics: 1) network optimization for federated learning (FL), 2) network optimization for other distributed learning methods, and 3) distributed reinforcement learning (RL) for wireless network optimization. In Part I (vol. 39, no. 12, Dec. 2021), the focus is on the first cluster (network optimization for FL). The focus of Part II is on the second and third clusters (network optimization for other distributed learning methods and RL for wireless network optimization). The readers are referred to Part I for an overview paper [A1] by the team of guest editors where a comprehensive study of how distributed learning can be efficiently deployed over wireless edge networks is provided. The contributions made by the papers in Part II are summarized as follows.

We exploit a behavior-shaping proactive mechanism, namely, recommendation, in cache-assisted non-orthogonal multiple access (NOMA) networks, aiming at minimizing the average system’s latency. Thereof, the considered latency consists of two parts, i.e., the backhaul link transmission delay and the content delivery latency. Towards this end, we first examine the expression of system latency, demonstrating how it is critically determined by content cache placement, personalized recommendation, and delivery associated NOMA user pairing and power control strategies. Thereafter, we formulate the minimization problem mathematically taking into account the cache capacity budget, the recommendation-oriented requirements, and the total transmit power constraint, which is a non-convex, multi-timescale, and mixed-integer programming problem. To facilitate the process, we put forth an entirely new paradigm nameddivide-and-rule. Specifically, we first solve the short-term optimization problem regarding user pairing as well as power allocation and the long-term decision-making problem with respect to recommendation and caching, respectively. On this basis, an iterative algorithm is developed to optimize all the optimization variables alternately. Particularly, for solving the short-timescale problem, graph theory enabled NOMA user grouping and efficient inter-group power control manners are invoked. Meanwhile, a dynamic programming approach and a complexity-controllable swap-then-compare method with convergence insurance are designed to derive the caching and recommendation policies, respectively. From Monte-Carlo simulation, we show the superiority of the proposed joint optimization method in terms of both system latency and cache hit ratio when compared to extensive benchmark strategies.

In this paper, a semantic communication framework is proposed for textual data transmission. In the studied model, a base station (BS) extracts the semantic information from textual data, and transmits it to each user. The semantic information is modeled by a knowledge graph (KG) that consists of a set of semantic triples. After receiving the semantic information, each user recovers the original text using a graph-to-text generation model. To measure the performance of the considered semantic communication framework, a metric of semantic similarity (MSS) that jointly captures the semantic accuracy and completeness of the recovered text is proposed. Due to wireless resource limitations, the BS may not be able to transmit the entire semantic information to each user and satisfy the transmission delay constraint. Hence, the BS must select an appropriate resource block for each user as well as determine and transmit part of the semantic information to the users. As such, we formulate an optimization problem whose goal is to maximize the total MSS by jointly optimizing the resource allocation policy and determining the partial semantic information to be transmitted. To solve this problem, a proximal-policy-optimization-based reinforcement learning (RL) algorithm integrated with an attention network is proposed. The proposed algorithm can evaluate the importance of each triple in the semantic information using an attention network and then, build a relationship between the importance distribution of the triples in the semantic information and the total MSS. Compared to traditional RL algorithms, the proposed algorithm can dynamically adjust its learning rate thus ensuring convergence to a locally optimal solution. Simulation results show that the proposed framework can reduce by 41.3% data that the BS needs to transmit and improve by two-fold the total MSS compared to a standard communication network without using semantic communication techniques.

The key challenges in live video multicasting include how to properly form multicast groups, select video versions and allocate wireless resources, in order to guarantee the quality of experience (QoE) while ensuring low latency delivery. To address these challenges, in this paper, a novel multicast framework that leverages the advantages of network-assisted dynamic adaptive streaming over HTTP and cloud radio access networks is proposed, where a multicast assistant server is deployed at the edge of a mobile network. Under this architecture, a joint user grouping, version selection, and bandwidth allocation method is designed to optimize the sum of users’ utilities. In particular, a two-step scheme is proposed to solve this complex problem. The number of multicast groups is first automatically determined and a user clustering method is presented. Then, group-level version selection and spectrum assignment algorithms are performed at different time scales. Simulation results demonstrate that our proposed scheme can improve at least 7% QoE compared to baseline methods.

In this paper, the problem of maximizing the wireless users’ sum-rate for uplink rate splitting multiple access (RSMA) communications is studied. In the considered model, the message intended for a single user is split into two sub-messages with separate transmit power and the base station (BS) uses a successive decoding technique to decode the received messages. To maximize each user’s transmission rate, the users must adjust their transmit power and the BS must determine the decoding order of the messages transmitted from the users to the BS. This problem is formulated as a sum-rate maximization problem with proportional rate constraints by adjusting the users’ transmit power and the BS’s decoding order. However, since the decoding order variable in the optimization problem is discrete, the original maximization problem with transmit power and decoding order variables can be transformed into a problem with only the rate splitting variable. Then, the optimal rate splitting of each user is determined. Given the optimal rate splitting of each user and a decoding order, the optimal transmit power of each user is calculated. Next, the optimal decoding order is determined by an exhaustive search method. To further reduce the complexity of the optimization algorithm used for sum-rate maximization in RSMA, a user pairing based algorithm is introduced, which enables two users to use RSMA in each pair and also enables the users in different pairs to be allocated with orthogonal frequency. For comparisons, the optimal sum-rate maximizing solutions with proportional rate constraints are obtained for non-orthogonal multiple access (NOMA), frequency division multiple access (FDMA), and time division multiple access (TDMA). Simulation results show that RSMA can achieve up to 10.0, 22.2, and 81.2 percent gains in terms of sum-rate compared to NOMA, FDMA, and TDMA.

Visible light positioning and computer vision-based localization have the potential to be cost-effective technologies for accurate indoor localization. However, the feasibility of existing methods in this domain is limited. In this paper, a novel visible light communication (VLC)-assisted perspective-four-line algorithm (V-P4L) is proposed for practical indoor localization. The basic idea of V-P4L is to jointly use VLC and computer vision techniques to achieve high localization accuracy regardless of LED height differences. In particular, the space-domain information is first exploited to estimate the orientation and coordinate information of a single rectangular LED luminaire in the camera coordinate system based on plane geometry theory and solid geometry theory. Then, by using time-domain information transmitted by VLC and the estimated luminaire information, the proposed V-P4L can estimate the position and pose of the camera using single-view geometry theory and the linear least square (LLS) method. To further mitigate the effect of height differences among LEDs on localization accuracy, a correction algorithm based on the LLS method and a simple optimization method is proposed. Due to the combination of time- and space-domain information, V-P4L can achieve accurate localization using a single luminaire without limitation on the correspondences between the features and their projections in conventional perspective-n-line (PnL) algorithms. Simulation results show that the position error caused by the proposed V-P4L algorithm is always less than 15 cm and the orientation error is always less than 4° using popular indoor luminaires. Experimental results with real hardware show that the average position error is less than 3 cm under both similar and different heights for the LEDs.

In this paper, the problem of enhancing the quality of virtual reality (VR) services is studied for an indoor terahertz (THz)/visible light communication (VLC) wireless network. In the studied model, small base stations (SBSs) transmit high-quality VR images to VR users over THz bands and light-emitting diodes (LEDs) provide accurate indoor positioning services for them using VLC. Here, VR users move in real time and their movement patterns change over time according to their applications, where both THz and VLC links can be blocked by the bodies of VR users. To control the energy consumption of the studied THz/VLC wireless VR network, VLC access points (VAPs) must be selectively turned on so as to ensure accurate and extensive positioning for VR users. Based on the user positions, each SBS must generate corresponding VR images and establish THz links without body blockage to transmit the VR content. The problem is formulated as an optimization problem whose goal is to maximize the average number of successfully served VR users by selecting the appropriate VAPs to be turned on and controlling the user association with SBSs. To solve this problem, a policy gradient-based reinforcement learning (RL) algorithm that adopts a meta-learning approach is proposed. The proposed meta policy gradient (MPG) algorithm enables the trained policy to quickly adapt to new user movement patterns. In order to solve the problem of maximizing the average number of successfully served users for VR scenarios with large numbers of users, a low-complexity dual method based MPG algorithm (D-MPG) with a low complexity is proposed. Simulation results demonstrate that, compared to a baseline trust region policy optimization algorithm (TRPO), the proposed MPG and D-MPG algorithms yield up to 26.8% and 21.9% improvement in the average number of successfully served users as well as 81.2% and 87.5% gains in the convergence speed, respectively.

This paper investigates the problem of resource allocation for a wireless communication network with distributed reconfigurable intelligent surfaces (RISs). In this network, multiple RISs are spatially distributed to serve wireless users and the energy efficiency of the network is maximized by dynamically controlling the on-off status of each RIS as well as optimizing the reflection coefficients matrix of the RISs. This problem is posed as a joint optimization problem of transmit beamforming and RIS control, whose goal is to maximize the energy efficiency under minimum rate constraints of the users. To solve this problem, two iterative algorithms are proposed for the single-user case and multi-user case. For the single-user case, the phase optimization problem is solved by using a successive convex approximation method, which admits a closed-form solution at each step. Moreover, the optimal RIS on-off status is obtained by using the dual method. For the multi-user case, a low-complexity greedy searching method is proposed to solve the RIS on-off optimization problem. Simulation results show that the proposed scheme achieves up to 33% and 68% gains in terms of the energy efficiency in both single-user and multi-user cases compared to the conventional RIS scheme and amplify-and-forward relay scheme, respectively.

The deployment of future intelligent transportation systems is contingent upon seamless and reliable operation of connected and autonomous vehicles (CAVs). One key challenge in developing CAVs is the design of an autonomous controller that can accurately execute near real-time control decisions, such as a quick acceleration when merging to a highway and frequent speed changes in a stop-and-go traffic. However, the use of conventional feedback controllers or traditional learning-based controllers, solely trained by each CAV’s local data, cannot guarantee a robust controller performance over a wide range of road conditions and traffic dynamics. In this paper, a new federated learning (FL) framework enabled by large-scale wireless connectivity is proposed for designing the autonomous controller of CAVs. In this framework, the learning models used by the controllers are collaboratively trained among a group of CAVs. To capture the varying CAV participation in the FL training process and the diverse local data quality among CAVs, a novel dynamic federated proximal (DFP) algorithm is proposed that accounts for the mobility of CAVs, the wireless fading channels, as well as the unbalanced and non-independent and identically distributed data across CAVs. A rigorous convergence analysis is performed for the proposed algorithm to identify how fast the CAVs converge to using the optimal autonomous controller. In particular, the impacts of varying CAV participation in the FL process and diverse CAV data quality on the convergence of the proposed DFP algorithm are explicitly analyzed. Leveraging this analysis, an incentive mechanism based on contract theory is designed to improve the FL convergence speed. Simulation results using real vehicular data traces show that the proposed DFP-based controller can accurately track the target CAV speed over time and under different traffic scenarios. Moreover, the results show that the proposed DFP algorithm has a much faster convergence compared to popular FL algorithms such as federated averaging (FedAvg) and federated proximal (FedProx). The results also validate the feasibility of the contract-theoretic incentive mechanism and show that the proposed mechanism can improve the convergence speed of the DFP algorithm by 40% compared to the baselines.

The threat of data-poisoning backdoor attacks on learning algorithms typically comes from the labeled data. However, in deep semi-supervised learning (SSL), unknown threats mainly stem from the unlabeled data. In this paper, we propose a novel deep hidden backdoor (DeHiB) attack scheme for SSL-based systems. In contrast to the conventional attacking methods, the DeHiB can inject malicious unlabeled training data to the semi-supervised learner so as to enable the SSL model to output premeditated results. In particular, a robust adversarial perturbation generator regularized by a unified objective function is proposed to generate poisoned data. To alleviate the negative impact of the trigger patterns on model accuracy and improve the attack success rate, a novel contrastive data poisoning strategy is designed. Using the proposed data poisoning scheme, one can implant the backdoor into the SSL model using the raw data without hand-crafted labels. Extensive experiments based on CIFAR10 and CIFAR100 datasets demonstrated the effectiveness and crypticity of the proposed scheme.

In this paper, the deployment of federated learning (FL) is investigated in an energy harvesting wireless network in which the base station (BS) is equipped with a massive multiple-input multiple-output (MIMO) system and a set of users powered by independent energy harvesting sources to cooperatively perform FL. Since a certain number of users may not be served due to interference and energy constraints, a joint energy management and user scheduling problem is considered. This problem is formulated as an optimization problem whose goal is to minimize the FL training loss via optimizing user scheduling. To determine the effect of various wireless factors (transmit power and number of scheduled users) on training loss, the convergence rate of the FL algorithm is analyzed. Given this analytical result, the original user scheduling and energy management optimization problem can be decomposed, simplified and solved. Simulation results show that the proposed algorithm can reduce training loss compared to a standard FL algorithm.

In this paper, a semantic communication framework is proposed for wireless networks. In the proposed framework, a base station (BS) extracts the semantic information from textual data, and, transmits it to each user. This semantic information is modeled by a knowledge graph (KG) and hence, the semantic information consists of a set of semantic triples. After receiving the semantic information, each user recovers the original text using a graph-to-text generation model. To measure the performance of the studied semantic communication system, a metric of semantic similarity (MSS) that jointly captures the semantic accuracy and completeness of the recovered text is proposed. Due to wireless resource limitations, the BS can only transmit partial semantic information to each user so as to satisfy the transmission delay constraint. Hence, the BS must select an appropriate resource block for each user and determine partial semantic information to be transmitted. This problem is formulated as an optimization problem whose goal is to maximize the total MSS by optimizing the resource allocation policy and determining the partial semantic information to be transmitted. To solve this problem, a policy gradient-based reinforcement learning (RL) algorithm integrated with the attention network is proposed. The proposed algorithm can evaluate the importance of each triple in the semantic information using an attention network and then, build a relationship between the importance distribution of the triples in the semantic information and the total MSS. Simulation results demonstrate that the proposed semantic communication framework can reduce the size of data that the BS needs to transmit by up to 46% and yield a two-fold improvement in the total MSS compared to a standard communication network that does not consider semantic communications.

This paper investigates the optimization of physical layer security in multiple-input multiple-output (MIMO) enabled visible light communication (VLC) networks. In the considered model, one transmitter equipped with light-emitting diodes (LEDs) intends to send confidential messages to legitimate users while one eavesdropper attempts to eavesdrop on the communication between the transmitter and legitimate users. This security problem is formulated as an optimization problem whose goal is to minimize the sum mean-square-error (MSE) of all legitimate users while meeting the MSE requirement of the eavesdropper thus ensuring the security. To solve this problem, the original optimization problem is first transformed to a convex problem using successive convex approximation. An iterative algorithm with low complexity is proposed to solve this optimization problem. Simulation results show that the proposed algorithm can reduce the sum MSE of legitimate users by up to 40% compared to a conventional zero forcing scheme.

Federated learning (FL) is widely used in privacy sensitive applications for isolated data islands, with the aim of achieving distributed model training, privacy enhancement and model sharing. Electromyographic (EMG) signals are a type of data collected from wearable sensors of subjects which are distributed on multiple devices, highly personalized and play an important role in several applications including prosthetic hand control, sign languages, grasp recognition, etc. This paper utilizes the FL method to detect single and combined finger movements based on EMG signals. The existing research on FL for wearable healthcare faces challenges of variable probability distributions of data, the need for prerequisite knowledge of server model and computational burdens in parameter transmission. To address these problems, this paper proposes a communication efficient FL framework in which each device only needs to transmit the weight matrices of local models to the server for model aggregation. To further reduce the FL transmission delay, a joint learning and resource allocation problem is formulated via optimizing transmit power of each device, time allocation, and user selection. To solve the delay minimization problem, the objective function is first converted to a tractable expression and then the difference of two convex functions programming is adopted. Simulation results using real EMG signals show that the proposed FL framework with personalized training process successfully detects single and combined finger movements for distributed users. Two public EMG datasets with 10 and 15 different finger movements are employed. Over 98% overall test accuracy is achieved in both datasets which surpasses the conventional learning framework by 1.6% and 0.5% on average. Different scenarios with regard to access points and users are investigated and the convexity of the proposed model is discussed.

This paper investigates the deployment of federated learning (FL) over an over-the-air computation (AirComp) and intelligent reflecting surface (IRS) based wireless network. In the considered system, devices transmit locally trained machine learning (ML) models to the base station (BS) which aggregates the received ML models and generates a shared global ML model. The devices can directly transmit ML models to the BS or using IRS. Meanwhile, AirComp is used to aggregate ML models that are transmitted from the devices to the BS. To minimize the energy consumption of devices, an energy minimization problem is formulated, which jointly optimizes the device selection, phase shift matrix, decoding vector, and power control. To seek the solution, the original optimization problem is divided into four sub-problems. Then the fractional program, greedy algorithm, matrix derivation, and weighted minimum mean square error methods are used to compute the phase shift matrix, device selection vector, decoding vector, and transmit power, respectively. Simulation results show that the proposed algorithm can reduce 11.2% energy consumption of devices compared to an FL algorithm that is implemented at a network without any IRSs.

In this paper, layered min-sum (MS) iterative decoding is formulated as a customized neural network following the sequential scheduling of check node (CN) updates. By virtue of the lifting structure of protograph low-density parity-check (LDPC) codes, identical network parameters are shared among all derived edges originating from the same edge in the protograph, which makes the number of learn- able parameters manageable. The proposed neural layered MS decoder can support arbitrary codelengths consequently. Moreover, an iteration-wise greedy training method is proposed to tune the parameters such that it avoids the vanishing gradient problem and accelerates the decoding convergence.

In this paper, the implementation of a distributed primal-dual algorithm over realistic wireless networks is investigated. In the considered model, the users and one base station (BS) cooperatively perform a distributed primal-dual algorithm for controlling and optimizing wireless networks. In particular, each user must locally update the primal and dual variables and send the updated primal variables to the BS. The BS aggregates the received primal variables and broadcasts the aggregated variables to all users. Since all of the primal and dual variables as well as aggregated variables are transmitted over wireless links, the imperfect wireless links will affect the solution achieved by the distributed primal-dual algorithm. Therefore, it is necessary to study how wireless factors such as transmission errors affect the implementation of the distributed primal-dual algorithm and how to optimize wireless network performance to improve the solution achieved by the distributed primal-dual algorithm. To address these challenges, the convergence rate of the primal-dual algorithm is first derived in a closed form while considering the impact of wireless factors such as data transmission errors. Based on the derived convergence rate, the optimal transmit power and resource block allocation schemes are designed to minimize the gap between the target solution and the solution achieved by the distributed primal-dual algorithm. Simulation results show that the proposed distributed primal-dual algorithm can reduce the gap between the target and obtained solution by up to 52% compared to the distributed primal-dual algorithm without considering imperfect wireless transmission.

We consider the problem of convergence time minimization for federated learning (FL) implemented in wireless systems. In such setups, each wireless edge device transmits its local FL model parameters to a base station (BS). The BS then uses the received FL parameters to generate a common FL model and broadcasts it to all edge devices. Since the FL parameters must be transmitted over wireless links, the convergence time depends not only on the number of training steps, but also on the FL parameter transmission delay at each training step, which can be substantial when conveying a large number of parameters. In addition, due to limited wireless resources such as spectrum, only a subset of edge devices can participate in each FL training step, which can further increase convergence time. Our goal therefore is to optimize wireless resource management and user selection for FL, as well as limit the volume of transmitted FL parameters. In this paper, three schemes for facilitating communication efficient FL are introduced: First, a probabilistic device selection scheme is designed such that the devices that can significantly improve the convergence speed and training loss have high probabilities for FL parameter transmission. Then, given the subset of participating devices, an efficient wireless resource allocation scheme is developed. Finally, a quantization method is proposed to reduce the data size. Simulation results demonstrate that the proposed FL method can improve handwritten digit identification accuracy and convergence delay by up to 3% and 90% compared to the conventional FL.

In this paper, a lifelong learning problem is studied for an Internet of Things (IoT) system. In the considered model, each IoT device aims to balance its information freshness and energy consumption tradeoff by controlling its computational resource allocation at each time slot under dynamic environments. An unmanned aerial vehicle (UAV) is deployed as a flying base station so as to enable the IoT devices to adapt to novel environments. To this end, a new lifelong reinforcement learning algorithm, used by the UAV, is proposed in order to adapt the operation of the devices at each visit by the UAV. By using the experience from previously visited devices and environments, the UAV can help devices adapt faster to future states of their environment. To do so, a knowledge base shared by all devices is maintained at the UAV. Simulation results show that the proposed algorithm can converge 25% to 50% faster than a policy gradient baseline algorithm that optimizes each device’s decision making problem in isolation.

In this paper, the problem of enhancing the quality of virtual reality (VR) services is studied for an indoor terahertz (THz)/visible light communication (VLC) wireless network. In the studied model, small base stations (SBSs) transmit high-quality VR images to users over THz bands and light-emitting diodes (LEDs) provide accurate indoor positioning services for VR users using VLC. Here, VR users move in real time and their movement patterns change over time according to their application. Both THz and VLC links can be blocked by the bodies of VR users. To control the energy consumption of the studied THz/VLC wireless VR network, VLC access points (VAPs) must be selectively turned on so as to ensure accurate and extensive positioning for VR users. Based on the user positions, each SBS must generate corresponding VR images and build THz links without body blockage to transmit the VR content. The problem is formulated as an optimization problem whose goal is to maximize the sum successful transmission probability of all VR users by selecting the appropriate VAPs to be turned on and controlling the user association with SBSs. To solve this problem, a policy gradient-based reinforcement learning (RL) algorithm using meta-learning framework is proposed. The proposed algorithm can effectively solve the formulated problem and enable the trained policy to quickly adapt to new user movement patterns. Simulation results demonstrate that, compared to a baseline trust region policy optimization algorithm (TRPO), the proposed meta-learning solution yields a 78% improvement in the convergence speed and about 16.4% improvement in the sum successful transmission probabilities of all VR users.

Limited radio frequency (RF) resources restrict the number of users that can participate in federated learning (FL) thus affecting FL convergence speed and performance. In this paper, we first introduce visible light communication (VLC) as a supplement to RF in FL and build a hybrid VLC/RF communication system, in which each indoor user can use both VLC and RF to transmit its FL model parameters. Then, the problem of user selection and bandwidth allocation is studied for FL implemented over a hybrid VLC/RF system aiming to optimize the FL performance. The problem is first separated into two subproblems. The first subproblem is a user selection problem with a given bandwidth allocation, which is solved by a traversal algorithm. The second subproblem is a bandwidth allocation problem with a given user selection, which is solved by a numerical method. The final user selection and bandwidth allocation are obtained by iteratively solving these two subproblems. Simulation results show that the proposed FL algorithm that efficiently uses VLC and RF for FL model transmission can improve the prediction accuracy by up to 10% compared with a conventional FL system using only RF.

In this article, a joint task, spectrum, and transmit power allocation problem is investigated for a wireless network in which the base stations (BSs) are equipped with mobile-edge computing (MEC) servers to jointly provide computational and communication services to users. Each user can request one computational task from three types of computational tasks. Since the data size of each computational task is different, as the requested computational task varies, the BSs must adjust their resource (subcarrier and transmit power) and task allocation schemes to effectively serve the users. This problem is formulated as an optimization problem whose goal is to minimize the maximal computational and transmission delay among all users. A multistack reinforcement learning (RL) algorithm is developed to solve this problem. Using the proposed algorithm, each BS can record the historical resource allocation schemes and users’ information in its multiple stacks to avoid learning the same resource allocation scheme and users’ states, thus improving the convergence speed and learning efficiency. The simulation results illustrate that the proposed algorithm can reduce the number of iterations needed for convergence and the maximal delay among all users by up to 18% and 11.1% compared to the standard$Q$-learning algorithm.

In this article, the problem of minimizing energy and time consumption for task computation and transmission in mobile-edge computing-enabled balloon networks is investigated. In the considered network, high-altitude balloons (HABs), acting as flying wireless base stations, can use their powerful computational capabilities to process the computational tasks offloaded from their associated users. Since the data size of each user’s computational task varies over time, the HABs must dynamically adjust their resource allocation schemes to meet the users’ needs. This problem is posed as an optimization problem, whose goal is to minimize the energy and time consumption for task computation and transmission by adjusting the user association, service sequence, and task allocation schemes. To solve this problem, a support vector machine (SVM)-based federated learning (FL) algorithm is proposed to determine the user association proactively. The proposed SVM-based FL method enables HABs to cooperatively build an SVM model that can determine all user associations without any transmissions of either user historical associations or computational tasks to other HABs. Given the predictions of the optimal user association, the service sequence and task allocation of each user can be optimized so as to minimize the weighted sum of the energy and time consumption. Simulations with real-city cellular traffic data show that the proposed algorithm can reduce the weighted sum of the energy and time consumption of all users by up to 15.4% compared to a conventional centralized method.

Analyzing massive amounts of data using complex machine learning models requires significant computational resources. The conventional approach to such problems involves centralizing training data and inference processes in the cloud, i.e., in data centers. However, with the proliferation of mobile devices and increasing application of the Internet-of-Things (IoT) paradigm, very large amounts of data are collected at the edges of wireless networks, and due to privacy constraints and limited communication resources, it is undesirable or impractical to upload this data from mobile devices to the cloud for centralized learning. This problem can be solved by distributed learning at the network edge, by which edge devices collaboratively train a shared learning model using real-time mobile data. The avoidance of raw-data uploading not only helps to preserve privacy but may also alleviate network-traffic congestion and minimize latency. With that said, distributed training still requires a substantial amount of information exchange between devices and edge servers over wireless links. In the process, wireless impairments such as noise, interference, and imperfect knowledge of channel states can significantly slow down distributed learning (e.g., convergence speed) and degrades its performance (e.g., learning accuracy). This makes it crucial to optimize wireless network performance so as to support the efficient deployment of distributed learning algorithms. On the other hand, distributed learning algorithms provide a powerful tool-set for solving complex problems in wireless communication and networking. One important framework, called federated learning (FL), enables users to collaboratively learn a shared model while helping to preserve local data privacy. The application of FL can endow edge devices with capabilities of user behavior prediction, user identification, and wireless environment analysis. As another example, distributed reinforcement learning is capable of leveraging distributed computation power and data to solve complex optimization and control problems that arise in various use cases, such as network control, user clustering, resource management, and interference alignment. To cover this paradigm of distributed learning over wireless networks, this two-part Special Issue features papers dealing with two main research challenges: a) optimization of wireless network performance for efficient implementation of distributed learning in wireless networks, and b) distributed learning for solving communication problems and optimizing network performance.

The next-generation of wireless networks will enable many machine learning (ML) tools and applications to efficiently analyze various types of data collected by edge devices for inference, autonomy, and decision making purposes. However, due to resource constraints, delay limitations, and privacy challenges, edge devices cannot offload their entire collected datasets to a cloud server for centrally training their ML models or inference purposes. To overcome these challenges, distributed learning and inference techniques have been proposed as a means to enable edge devices to collaboratively train ML models without raw data exchanges, thus reducing the communication overhead and latency as well as improving data privacy. However, deploying distributed learning over wireless networks faces several challenges including the uncertain wireless environment (e.g., dynamic channel and interference), limited wireless resources (e.g., transmit power and radio spectrum), and hardware resources (e.g., computational power). This paper provides a comprehensive study of how distributed learning can be efficiently and effectively deployed over wireless edge networks. We present a detailed overview of several emerging distributed learning paradigms, including federated learning, federated distillation, distributed inference, and multi-agent reinforcement learning. For each learning framework, we first introduce the motivation for deploying it over wireless networks. Then, we present a detailed literature review on the use of communication techniques for its efficient deployment. We then introduce an illustrative example to show how to optimize wireless networks to improve its performance. Finally, we introduce future research opportunities. In a nutshell, this paper provides a holistic set of guidelines on how to deploy a broad range of distributed learning frameworks over real-world wireless communication networks.

The recent development of deep learning methods provides a new approach to optimize the belief propagation (BP) decoding of linear codes.However, the limitation of existing works is that the scale of neural networks increases rapidly with the codelength, thus they can only support short to moderate codelengths.From the point view of practicality, we propose a high-performance neural min-sum (MS) decoding method that makes full use of the lifting structure of protograph low-density parity-check (LDPC) codes.By this means, the size of the parameter array of each layer in the neural decoder only equals the number of edge-types for arbitrary codelengths.In particular, for protograph LDPC codes, the proposed neural MS decoder is constructed in a special way such that identical parameters are shared by a bundle of edges derived from the same edge-type.To reduce the complexity and overcome the vanishing gradient problem in training the proposed neural MS decoder, an iteration-byiteration (i.e., layer-by-layer in neural networks) greedy training method is proposed.With this, the proposed neural MS decoder tends to be optimized with faster convergence, which is aligned with the early termination mechanism widely used in practice.To further enhance the generalization ability of the proposed neural MS decoder, a codelength/rate compatible training method is proposed, which randomly selects samples from a set of codes lifted from the same base code.As a theoretical performance evaluation tool, a trajectory-based extrinsic information transfer (T-EXIT) chart is developed for various decoders.Both T-EXIT and simulation results show that the optimized MS decoding can provide faster convergence and up to 1dB gain compared with the plain MS decoding and its variants with only slightly increased complexity.In addition, it can even outperform the sum-product algorithm for some short codes.

In this paper, the problem of the trajectory design for a group of energy-constrained drones operating in dynamic wireless network environments is studied. In the considered model, a team of drone base stations (DBSs) is dispatched to cooperatively serve clusters of ground users that have dynamic and unpredictable uplink access demands. In this scenario, the DBSs must cooperatively navigate in the considered area to maximize coverage of the dynamic requests of the ground users. This trajectory design problem is posed as an optimization framework whose goal is to find optimal trajectories that maximize the fraction of users served by all DBSs. To find an optimal solution for this non-convex optimization problem under unpredictable environments, a value decomposition based reinforcement learning (VD-RL) solution coupled with a meta-training mechanism is proposed. This algorithm allows the DBSs to dynamically learn their trajectories while generalizing their learning to unseen environments. Analytical results show that, the proposed VD-RL algorithm is guaranteed to converge to a locally optimal solution of the non-convex optimization problem. Simulation results show that, even without meta-training, the proposed VD-RL algorithm can achieve a 53.2% improvement of the service coverage and a 30.6% improvement in terms of the convergence speed, compared to baseline multi-agent algorithms. Meanwhile, the use of the meta-training mechanism improves the convergence speed of the VD-RL algorithm by up to 53.8% when the DBSs must deal with a previously unseen task.

In this paper, the sum-rate maximization problem is studied for wireless networks that use downlink rate splitting multiple access (RSMA). In the considered model, the base station (BS) divides the messages that can be transmitted to its users into a “private” part and a “common” part. Here, the common message is a message that multiple users want to receive and the private message is a message that is dedicated to only a specific user. The RSMA mechanism enables a BS to adjust the split of common and private messages so as to control the interference by decoding and treating interference as noise and, thus optimizing the data rate of users. To maximize the users' sum-rate, the network can determine the rate allocation for the common message to meet the rate demand, and adjust the transmit power for the private message to reduce the interference. This problem is formulated as an optimization problem whose goal is to maximize the sum-rate of all users. To solve this nonconvex maximization problem with a single-antenna BS, the optimal power used for transmitting the private message to the users is first obtained in closed form for a given rate allocation and common message power. Based on the optimal private message transmit power, the optimal rate allocation is then derived under a fixed common message transmit power. Subsequently, an iterative algorithm is proposed to obtain a suboptimal solution of common message transmit power. To solve this nonconvex maximization problem with a multiple-antenna BS, a successive convex approximation method is utilized. Simulation results show that the RSMA can achieve up to 15.6% and 21.5% gains in terms of data rate compared to non-orthogonal multiple access (NOMA) and orthogonal frequency-division multiple access (OFDMA), respectively.

In this paper, the convergence time of federated learning (FL), when deployed over a realistic wireless network, is studied. In particular, a wireless network is considered in which wireless users transmit their local FL models (trained using their locally collected data) to a base station (BS). The BS, acting as a central controller, generates a global FL model using the received local FL models and broadcasts it back to all users. Due to the limited number of resource blocks (RBs) in a wireless network, only a subset of users can be selected to transmit their local FL model parameters to the BS at each learning step. Moreover, since each user has unique training data samples, the BS prefers to include all local user FL models to generate a converged global FL model. Hence, the FL training loss and convergence time will be significantly affected by the user selection scheme. Therefore, it is necessary to design an appropriate user selection scheme that can select the users who can contribute toward improving the FL convergence speed more frequently. This joint learning, wireless resource allocation, and user selection problem is formulated as an optimization problem whose goal is to minimize the FL convergence time and the FL training loss. To solve this problem, a probabilistic user selection scheme is proposed such that the BS is connected to the users whose local FL models have significant effects on the global FL model with high probabilities. Given the user selection policy, the uplink RB allocation can be determined. To further reduce the FL convergence time, artificial neural networks (ANNs) are used to estimate the local FL models of the users that are not allocated any RBs for local FL model transmission at each given learning step, which enables the BS to improve the global model, the FL convergence speed, and the training loss. Simulation results show that the proposed approach can reduce the FL convergence time by up to 56% and improve the accuracy of identifying handwritten digits by up to 3%, compared to a standard FL algorithm.

In this article, the problem of training federated learning (FL) algorithms over a realistic wireless network is studied. In the considered model, wireless users execute an FL algorithm while training their local FL models using their own data and transmitting the trained local FL models to a base station (BS) that generates a global FL model and sends the model back to the users. Since all training parameters are transmitted over wireless links, the quality of training is affected by wireless factors such as packet errors and the availability of wireless resources. Meanwhile, due to the limited wireless bandwidth, the BS needs to select an appropriate subset of users to execute the FL algorithm so as to build a global FL model accurately. This joint learning, wireless resource allocation, and user selection problem is formulated as an optimization problem whose goal is to minimize an FL loss function that captures the performance of the FL algorithm. To seek the solution, a closed-form expression for the expected convergence rate of the FL algorithm is first derived to quantify the impact of wireless factors on FL. Then, based on the expected convergence rate of the FL algorithm, the optimal transmit power for each user is derived, under a given user selection and uplink resource block (RB) allocation scheme. Finally, the user selection and uplink RB allocation is optimized so as to minimize the FL loss function. Simulation results show that the proposed joint federated learning and communication framework can improve the identification accuracy by up to 1.4%, 3.5% and 4.1%, respectively, compared to: 1) An optimal user selection algorithm with random resource allocation, 2) a standard FL algorithm with random user selection and resource allocation, and 3) a wireless optimization algorithm that minimizes the sum packet error rates of all users while being agnostic to the FL parameters.

In this paper, the problem of energy efficient transmission and computation resource allocation for federated learning (FL) over wireless communication networks is investigated. In the considered model, each user exploits limited local computational resources to train a local FL model with its collected data and, then, sends the trained FL model to a base station (BS) which aggregates the local FL model and broadcasts it back to all of the users. Since FL involves an exchange of a learning model between users and the BS, both computation and communication latencies are determined by the learning accuracy level. Meanwhile, due to the limited energy budget of the wireless users, both local computation energy and transmission energy must be considered during the FL process. This joint learning and communication problem is formulated as an optimization problem whose goal is to minimize the total energy consumption of the system under a latency constraint. To solve this problem, an iterative algorithm is proposed where, at every step, closed-form solutions for time allocation, bandwidth allocation, power control, computation frequency, and learning accuracy are derived. Since the iterative algorithm requires an initial feasible solution, we construct the completion time minimization problem and a bisection-based algorithm is proposed to obtain the optimal solution, which is a feasible solution to the original energy minimization problem. Numerical results show that the proposed algorithms can reduce up to 59.5% energy consumption compared to the conventional FL method.

This paper investigates the problem of resource allocation for a wireless communication network with distributed reconfigurable intelligent surfaces (RISs). In this network, multiple RISs are spatially distributed to serve wireless users and the energy efficiency of the network is maximized by dynamically controlling the on-off status of each RIS as well as optimizing the reflection coefficient matrix of the RISs. This problem is posed as a joint optimization problem of transmit power and RIS control, whose goal is to maximize the energy efficiency under minimum rate constraints of the users. To solve this problem, an alternating algorithm is proposed by solving two sub-problems iteratively. The phase optimization sub-problem is solved by using a successive convex approximation method, which admits a closed-form solution at each step. Moreover, the RIS on-off optimization sub-problem is solved by using the dual method. Simulation results show that the proposed scheme achieves up to 27% and 68% gains in terms of the energy efficiency compared to the conventional RIS scheme and amplify-and-forward relay scheme, respectively.

In this paper, the design of an optimal trajectory for an energy-constrained drone operating in dynamic network environments is studied. In the considered model, a drone base station (DBS) is dispatched to provide uplink connectivity to ground users whose demand is dynamic and unpredictable. In this case, the DBS's trajectory must be adaptively adjusted to satisfy the dynamic user access requests. To this end, a metalearning algorithm is proposed in order to adapt the DBS's trajectory when it encounters novel environments, by tuning a reinforcement learning (RL) solution. The meta-learning algorithm provides a solution that adapts the DBS in novel environments quickly based on limited former experiences. The meta-tuned RL is shown to yield a faster convergence to the optimal coverage in unseen environments with a considerably low computation complexity, compared to the baseline policy gradient algorithm. Simulation results show that, the proposed meta-learning solution yields a 25% improvement in the convergence speed, and about 10% improvement in the DBS' communication performance, compared to a baseline policy gradient algorithm. Meanwhile, the probability that the DBS serves over 50% of user requests increases about 27%, compared to the baseline policy gradient algorithm.

In this paper, the problem of minimizing the weighted sum of age of information (AoI) and total energy consumption of Internet of Things (IoT) devices is studied. In particular, each IoT device monitors a physical process that follows nonlinear dynamics. As the dynamic of the physical process varies over time, each device must sample the real-time status of the physical system and send the status information to a base station (BS) so as to monitor the physical process. The dynamics of the realistic physical process will influence the sampling frequency and status update scheme of each device. In particular, as the physical process varies rapidly, the sampling frequency of each device must be increased to capture these physical dynamics. Meanwhile, changes in the sampling frequency will also impact the energy usage of the device. Thus, it is necessary to determine a subset of devices to sample the physical process at each time slot so as to accurately monitor the dynamics of the physical process using minimum energy. This problem is formulated as an optimization problem whose goal is to minimize the weighted sum of AoI and total device energy consumption. To solve this problem, a machine learning framework based on the repeated update Q-learning (RUQL) algorithm is proposed. The proposed method enables the BS to overcome the biased action selection problem (e.g., an agent always takes a subset of actions while ignoring other actions), and hence, dynamically and quickly finding a device sampling and status update policy so as to minimize the sum of AoI and energy consumption of all devices. Simulations with real data of PM 2.5 pollution in Beijing from the Center for Statistical Science at Peking University show that the proposed algorithm can reduce the sum of AoI by up to 26.9% compared to the conventional Q-learning method.

Traditional deep learning models are trained on centralized servers using labeled sample data collected from edge devices. This data often includes private information, which the users may not be willing to share. Federated learning (FL) is an emerging approach to train such learning models without requiring the users to share their possibly private labeled data. In FL, each user trains its copy of the learning model locally. The server then collects the individual updates and aggregates them into a global model. A major challenge that arises in this method is the need of each user to efficiently transmit its learned model over the throughput limited uplink channel. In this work, we tackle this challenge using tools from quantization theory. In particular, we identify the unique characteristics associated with conveying trained models over rate-constrained channels, and characterize a suitable quantization scheme for such setups. We show that combining universal vector quantization methods with FL yields a decentralized training system, which is both efficient and feasible. We also derive theoretical performance guarantees of the system. Our numerical results illustrate the substantial performance gains of our scheme over FL with previously proposed quantization approaches.

In this paper, the sum-rate maximization problem is studied for wireless networks that use downlink rate splitting multiple access (RSMA). In the considered model, each base station (BS) divides the messages that must be transmitted to its users into a “private” part and a “common” part. Here, the common message is a message that all users want to receive and the private message is a message that is dedicated to only a specific user. The RSMA mechanism enables a BS to adjust the split of common and private messages so as to control the interference by decoding and treating interference as noise and, thus optimizing the data rate of users. To maximize the users' sum-rate, the network can determine the rate allocation for the common message to meet the rate demand, and adjust the transmit power for the private message to reduce the interference. This problem is formulated as an optimization problem whose goal is to maximize the sum-rate of all users. To solve this nonconvex maximization problem, the optimal power used for transmitting the private message to the users is first obtained in closed form for a given rate allocation and common message power. Based on the optimal private message transmission power, the optimal rate allocation is then derived under a fixed common message transmission power. Subsequently, a one-dimensional search algorithm is proposed to obtain the optimal solution of common message transmission power. Simulation results show that the RSMA can achieve up to 19.6% and 23.5% gains in terms of data rate compared to non-orthogonal multiple access (NOMA) and orthogonal frequency-division multiple access (OFDMA), respectively.

In this paper, the convergence time of federated learning (FL), when deployed over a realistic wireless network, is studied. In particular, with the considered model, wireless users transmit their local FL models (trained using their locally collected data) to a base station (BS). The BS, acting as a central controller, generates a global FL model using the received local FL models and broadcasts it back to all users. Due to the limited number of resource blocks (RBs) in a wireless network, only a subset of users can be selected and transmit their local FL model parameters to the BS at each learning step. Meanwhile, since each user has unique training data samples and the BS must wait to receive all users' local FL models to generate the global FL model, the FL performance and convergence time will be significantly affected by the user selection scheme. In consequence, it is necessary to design an appropriate user selection scheme that enables all users to execute an FL scheme and efficiently train it. This joint learning, wireless resource allocation, and user selection problem is formulated as an optimization problem whose goal is to minimize the FL convergence time while optimizing the FL performance. To address this problem, a probabilistic user selection scheme is proposed using which the BS will connect to the users, whose local FL models have large effects on its global FL model, with high probabilities. Given the user selection policy, the uplink RB allocation can be determined. To further reduce the FL convergence time, artificial neural networks (ANNs) are used to estimate the local FL models of the users that are not allocated any RBs for local FL model transmission, which enables the BS to include more users' local FL models to generate the global FL model so as to improve the FL convergence speed and performance. Simulation results show that the proposed ANN-based FL scheme can reduce the FL convergence time by up to 53.8%, compared to a standard FL algorithm.

In this paper, the problem of minimizing energy consumption for task computation and transmission in a cellular network with mobile edge computing (MEC) capabilities is studied. In the considered network, each user needs to process a computational task at each time slot. A part of the task can be transmitted to a base station (BS) that can use its powerful computational ability to process the tasks offloaded from its users. Since the data size of each user's computational task varies over time, the BSs must dynamically adjust the resource allocation scheme to meet the users' needs. This problem is posed as an optimization problem whose goal is to minimize the energy consumption for task computing and transmission via adjusting user association scheme as well as their task and power allocation scheme. To solve this problem, a support vector machine (SVM)-based federated learning (FL) is proposed to determine the user association proactively. Given the user association, the BS can collect the information related to the computational tasks of its associated users using which, the transmit power and task allocation of each user will be optimized and the energy consumption of each user is also minimized. The proposed SVM-based FL method enables the BS and users to cooperatively build a global SVM model that can determine all users' association without any transmission of users' historical association and computational task offloading. Simulations using real data on city cellular traffic from the OMNILab at Shanghai Jiao Tong University show that the proposed algorithm can reduce the users' energy consumption by up to 20.1% compared to the conventional centralized SVM method.

Unmanned aerial vehicle (UAV) swarms must exploit machine learning (ML) in order to execute various tasks ranging from coordinated trajectory planning to cooperative target recognition. However, due to the lack of continuous connections between the UAV swarm and ground base stations (BSs), using centralized ML will be challenging, particularly when dealing with a large volume of data. In this paper, a novel framework is proposed to implement distributed federated learning (FL) algorithms within a UAV swarm that consists of a leading UAV and several following UAVs. Each following UAV trains a local FL model based on its collected data and then sends this trained local model to the leading UAV who will aggregate the received models, generate a global FL model, and transmit it to followers over the intra-swarm network. To identify how wireless factors, like fading, transmission delay, and UAV antenna angle deviations resulting from wind and mechanical vibrations, impact the performance of FL, a rigorous convergence analysis for FL is performed. Then, a joint power allocation and scheduling design is proposed to optimize the convergence rate of FL while taking into account the energy consumption during convergence and the delay requirement imposed by the swarm's control system. Simulation results validate the effectiveness of the FL convergence analysis and show that the joint design strategy can reduce the number of communication rounds needed for convergence by as much as 35% compared with the baseline design.

In this paper, the problem of joint subcarrier and power allocation is studied for multi-cell orthogonal frequency-division multiplexing (OFDM) systems. This joint subcarrier and power resource allocation problem is formulated as an optimization problem whose goal is to maximize the system spectral efficiency. To solve the proposed problem, the original optimization problem is first decomposed into two subproblems: subcarrier allocation and power allocation. By solving these two subproblems, an initial subcarrier and power allocation scheme is accordingly obtained. An multi-agent reinforcement learning (MARL) algorithm is proposed to further increase the spectral efficiency. In particular, using the proposed MARL algorithm, each BS can adapt its allocation scheme according to the wireless environmental states. Numerical results show that the proposed MARL method can achieve up to 53.6% gain in terms of spectral efficiency compared to the conventional scheme. The proposed MARL scheme also converges more rapidly than the conventional single-agent Q-learning approach.

In this paper, a power efficient deployment for visible light communication (VLC)-enabled unmanned aerial vehicles (UAVs) is studied. In the studied model, each UAV can provide communication service for ground users and illumination builds the VLC links between UAVs and users. Hence, each UAV’s signal transmission and illumination will affect other UAVs’ signal transmission and illumination. Therefore, to deploy VLC-enabled UAVs so as to efficiently service the ground users, the interference caused by the signal transmission and illumination of UAVs must be considered. This problem is formulated as an optimization problem whose goal is to optimize the deployment of UAVs so as to minimize the power consumption for signal transmission and illumination. An iterative algorithm is first proposed to transform the optimization problem into a series of interdependent subproblems, and the transformed problems are then solved by the Lagrangian dual method. In addition, convergence and complexity of the algorithm are also analyzed. Numerical results show that the proposed scheme can reduce at least 53.7% power consumption when compared to the baselines with UAVs at the center of each sub-area.

This paper investigates the energy efficiency maximization problem in a downlink reconfigurable intelligent surface (RIS) assisted visible light communication (VLC) system. The energy efficiency maximization problem is formulated via jointly optimizing time allocation, power control, phase shit matrix under the unique power constraints in VLC. To solve this non-convex energy efficiency maximization problem, the original problem is first simplified to an equivalent problem with a smaller number of variables. Then, an alternating algorithm with low complexity is accordingly proposed to obtain a suboptimal solution via iteratively solving the joint time allocation and power control subproblem, and the phase shift matrix adjustment subproblem. The simulation results show that the proposed algorithm can achieve up to 0.127dB gain in terms of energy efficiency compared to the conventional interior point method.

In this paper, the optimization of the system energy efficiency (EE) is studied for a reconfigurable intelligent surface (RIS) assisted full-deplex (FD) communication system. In the studied model, two devices communicate with each other using one RIS under the FD mode. Each of the devices will receive not only the message from the other device but also the self-interference. The main problem of this work is to maximize EE by jointly optimizing the reflection coefficients matrix and the transmit power of devices. To solve this problem, a nonlinear fractional programming based algorithm is used to transform the fractional optimization problem into a subtractive problem. Then the transmit power and the RIS phase shifts matrix are optimized by an iterative method. Simulation results show that the proposed scheme can achieve up to 200% gain in terms of EE compared to a conventional RIS assisted half-duplex mode.

For crowded and hotspot area, unmanned aerial vehicles (UAVs) are usually deployed to increase the coverage rate. In the considered model, there are three types of services for UAV assisted communication: control message, non-realtime communication, and real-time communication, which can cover most of the actual demands of users in a UAV assisted communication system. A bandwidth allocation problem is considered to minimize the total energy consumption of this system while satisfying the requirements. Two techniques are introduced to enhance the performance of the system. The first method is to categorize the ground users into multiple user groups and offer each group a unique RF channel with different bandwidth. The second method is to deploy more than one UAVs in the system. Bandwidth optimization in each scheme is proved to be a convex problem. Simulation results show the superiority of the proposed schemes in terms of energy consumption.

In this paper, the problem of trajectory design for energy harvesting unmanned aerial vehicles (UAVs) is studied. In the considered model, the UAV acts as a moving base station to serve the ground users, while collecting energy from the charging stations located at the center of a user group. Meanwhile, to serve ground users and harvest energy, the UAV must be examined and repaired regularly. In consequence, it is necessary to optimize the trajectory design of the UAV while jointly considering the maintenance costs, the number of users that are served by the UAV, and the energy consumption and harvesting. To capture the relationship among these factors, we first model the completion of service and the harvested energy as reward, and the energy consumption during the deployment as cost. Then, the deployment profitability is defined as the reward to the cost of the UAV trajectory. Based on this definition, the trajectory design problem is formulated as an optimization problem whose goal is to maximize the deployment profitability of the UAV. To solve this problem, a foraging algorithm is proposed to find the optimal trajectory so as to maximize the deployment profitability. The proposed algorithm can find the optimal trajectory for the UAV with a polynomial time complexity. Fundamental analysis shows that the proposed algorithm can achieve the maximal deployment profitability. Simulation results show that the proposed algorithm can effectively reduce the operation time and achieve up to 25.6% gain in terms of the deployment profitability compared to Q-learning algorithm.

In this paper, the problem of enhancing the virtual reality (VR) experience for wireless users is investigated by minimizing the occurrence of breaks in presence (BIP) that can detach the users from their virtual world. To measure the BIP for wireless VR users, a novel model that jointly considers the VR application type, transmission delay, VR video quality, and users' awareness of the virtual environment is proposed. In the developed model, base stations (BSs) transmit VR videos to the wireless VR users using directional transmission links so as to provide high data rates for the VR users, thus, reducing the number of BIP for each user. Since the body movements of a VR user may result in a blockage of its wireless link, the location and orientation of VR users must also be considered when minimizing BIP. The BIP minimization problem is formulated as an optimization problem which jointly considers the predictions of users' locations, orientations, and their BS association. To predict the orientation and locations of VR users, a distributed learning algorithm based on the machine learning framework of deep echo state networks (ESNs) is proposed. The proposed algorithm uses federated learning to enable multiple BSs to locally train their deep ESNs using their collected data and cooperatively build a learning model to predict the entire users' locations and orientations. Using these predictions, the user association policy that minimizes BIP is derived. Simulation results demonstrate that the developed algorithm reduces the users' BIP by up to 16% and 26%, respectively, compared to centralized ESN and deep learning algorithms.

In this paper, the problem of user association and resource allocation is studied for an integrated satellite-drone network (ISDN). In the considered model, drone base stations (DBSs) provide downlink connectivity to ground users whose demand cannot be satisfied by terrestrial small cell base stations (SBSs). Meanwhile, a satellite system and a set of terrestrial macrocell base stations (MBSs) are used to provide resources for backhaul connectivity for both DBSs and SBSs. For this scenario, one must jointly consider resource management over satellite-DBS/SBS backhaul links, MBS-DBS/SBS terrestrial backhaul links, and DBS/SBS-user radio access links as well as user association with DBSs and SBSs. This joint user association and resource allocation problem is modeled using a competitive market setting in which the transmission data is considered as a good that is being exchanged between users, DBSs, and SBSs that act as “buyers”, and DBSs, SBSs, MBSs, and the satellite that act as “sellers”. In this market, the quality-of-service (QoS) is used to capture the quality of the data transmission (defined as good), while the energy consumption the buyers use for data transmission is the cost of exchanging a good. According to the quality of goods, sellers in the market propose quotations to the buyers to sell their goods, while the buyers purchase the goods based on the quotation. The buyers profit from the difference between the earned QoS and the charged price, while the sellers profit from the difference between earned price and the energy spent for data transmission. The buyers and sellers in the market seek to reach a Walrasian equilibrium, at which all the goods are sold, and each of the devices' profit is maximized. A heavy ball based iterative algorithm is proposed to compute the Walrasian equilibrium of the formulated market. Analytical results show that, with well-defined update step sizes, the proposed algorithm is guaranteed to reach one Walrasian equilibrium. Simulation results show that, at the achieved Walrasian equilibrium solution, the proposed algorithm can yield a two-fold gain in terms of the number of radio access links with a data rate of over 40 Mbps, and a three-fold gain in terms of the number of backhaul links with a data rate greater than 1.6 Gbps.

In this paper, the problem of dynamical deployment of unmanned aerial vehicles (UAVs) equipped with visible light communication (VLC) capabilities for optimizing the energy efficiency of UAV-enabled networks is studied. In the studied model, the UAVs can simultaneously provide communications and illumination to service ground users. Since ambient illumination increases the interference over VLC links while reducing the illumination threshold of the UAVs, it is necessary to consider the illumination distribution of the target area for UAV deployment optimization. This problem is formulated as an optimization problem which jointly optimizes UAV deployment, user association, and power efficiency while meeting the illumination and communication requirements of users. To solve this problem, an algorithm that combines the machine learning framework of gated recurrent units (GRUs) with convolutional neural networks (CNNs) is proposed. Using GRUs and CNNs, the UAVs can model the long-term historical illumination distribution and predict the future illumination distribution. Given the prediction of illumination distribution, the original nonconvex optimization problem can be divided into two sub-problems and is then solved using a low-complexity, iterative algorithm. Then, the proposed algorithm enables UAVs to determine the their deployment and user association to minimize the total transmit power. Simulation results using real data from the Earth observations group (EOG) at NOAA/NCEI show that the proposed approach can achieve up to 68.9% reduction in total transmit power compared to a conventional optimal UAV deployment that does not consider the illumination distribution and user association.

In this paper, the problem of maximizing sum-rate for uplink rate splitting multiple access (RSMA) communications is studied. In the considered model, each user transmits two messages to the base station (BS) with separate transmit power and the BS will use a successive decoding technique to decode the received messages. To maximize each user's transmission rate, the users must adjust their transmit power and the BS must determine the decoding order of the messages transmitted from the users to the BS. This problem is formulated as a sum-rate maximization problem with proportional rate constraints by adjusting the users' transmit power and the BS's decoding order. However, since the decoding order variable in the optimization problem is discrete, the original minimization problem with transmit power and decoding order variables can be transformed into a problem with only the rate splitting variable. Then, the optimal rate splitting of each user is determined. Given the optimal rate splitting of each user and a decoding order, the optimal transmit power of each user is determined. Next, the optimal decoding order is determined by an exhaustive search method. To further reduce the complexity of the optimization algorithm used for sum-rate maximization in RSMA, a user pairing based algorithm is introduced, which enables two users to use RSMA in each pair and also enables the users in different pairs to be allocated with orthogonal frequency. Simulation results show that RSMA can achieve up to 10.0%, 22.2%, and 83.7% gains in terms of rate compared to non-orthogonal multiple access (NOMA), frequency division multiple access (FDMA), and time division multiple access (TDMA).

In this paper, the problem of training federated learning (FL) algorithms over a realistic wireless network is studied. In particular, in the considered model, wireless users perform an FL algorithm that trains their local FL models using their own data and send the trained local FL models to a base station (BS) that will generate a global FL model and send it back to the users. Since all training parameters are transmitted over wireless links, the quality of the training will be affected by wireless factors such as packet errors and availability of wireless resources. Meanwhile, due to the limited wireless bandwidth, the BS must select an appropriate subset of users to execute the FL learning algorithm so as to build a global FL model accurately. This joint learning, wireless resource allocation, and user selection problem is formulated as an optimization problem whose goal is to minimize an FL loss function that captures the performance of the FL algorithm. To address this problem, a closed-form expression for the expected convergence rate of the FL algorithm is first derived to quantify the impact of wireless factors on FL. Then, based on the expected convergence rate of the FL algorithm, the optimal transmit power for each user is derived, under a given user selection and uplink resource block (RB) allocation scheme. Finally, the user selection and uplink RB allocation is optimized so as to minimize the FL loss function. Simulation results show that the proposed joint federated learning and communication framework can reduce the FL loss function value by up to 10% and 16%, respectively, compared to 1) an optimal user selection algorithm with random resource allocation and 2) a random user selection and resource allocation algorithm.

In this paper, the problem of enhancing the virtual reality (VR) experience for wireless users is investigated by minimizing the occurrence of breaks in presence (BIPs) that can detach the users from their virtual world. To measure the BIPs for wireless VR users, a novel model that jointly considers the VR applications, transmission delay, VR video quality, and users' awareness of the virtual environment is proposed. In the developed model, the base stations (BSs) transmit VR videos to the wireless VR users using directional transmission links so as to increase the data rate of VR users, thus, reducing the number of BIPs for each user. Therefore, the mobility and orientation of VR users must be considered when minimizing BIPs, since the body movements of a VR user may result in blockage of its wireless link. The BIP problem is formulated as an optimization problem which jointly considers the predictions of users' mobility patterns, orientations, and their BS association. To predict the orientation and mobility patterns of VR users, a distributed learning algorithm based on the machine learning framework of deep echo state networks (ESNs) is proposed. The proposed algorithm uses concept from federated learning to enable multiple BSs to locally train their deep ESNs using their collected data and cooperatively build a learning model to predict the entire users' mobility patterns and orientations. Using these predictions, the user association policy that minimizes BIPs is derived. Simulation results demonstrate that the developed algorithm reduces the users' BIPs by up to 16% and 26%, respectively, compared to centralized ESN and deep learning algorithms.

In this paper, the problem of optimizing the deployment of unmanned aerial vehicles (UAVs) equipped with visible light communication (VLC) capabilities is studied. In the studied model, the UAVs can simultaneously provide communications and illumination to service ground users. Ambient illumination increases the interference over VLC links while reducing the illumination threshold of the UAVs. Therefore, it is necessary to consider the illumination distribution of the target area for UAV deployment optimization. This problem is formulated as an optimization problem whose goal is to minimize the total transmit power while meeting the illumination and communication requirements of users. To solve this problem, an algorithm based on the machine learning framework of gated recurrent units (GRUs) is proposed. Using GRUs, the UAVs can model the longterm historical illumination distribution and predict the future illumination distribution. In order to reduce the complexity of the prediction algorithm while accurately predicting the illumination distribution, a Gaussian mixture model (GMM) is used to fit the illumination distribution of the target area at each time slot. Based on the predicted illumination distribution, the optimization problem is proved to be a convex optimization problem that can be solved by using duality. Simulations using real data from the Earth observations group (EOG) at NOAA/NCEI show that the proposed approach can achieve up to 22.1% reduction in transmit power compared to a conventional optimal UAV deployment that does not consider the illumination distribution. The results also show that UAVs must hover at areas having strong illumination, thus providing useful guidelines on the deployment of VLCenabled UAVs.

In this paper, the problem of content caching and transmission is studied for a wireless virtual reality (VR) network in which cellular-connected unmanned aerial vehicles (UAVs) capture videos on live games or sceneries and transmit them to small base stations (SBSs) that service the VR users. To meet the VR delay requirements, the UAVs can extract specific visible content from the original 360° VR data and send this visible content to the users so as to reduce the traffic load over backhaul and radio access links. To further alleviate the UAV-SBS backhaul traffic, the SBSs can also cache the popular contents that users request. This joint content caching and transmission problem is formulated as an optimization problem whose goal is to maximize the users' reliability, defined as the probability that the content transmission delay of each user satisfies the instantaneous VR delay target. To address this problem, a distributed deep learning algorithm that brings together new neural network ideas from liquid state machine (LSM) and echo state networks (ESNs) is proposed. The proposed algorithm enables each SBS to predict the users' reliability so as to find the optimal contents to cache and content transmission format for each cellular-connected UAV. Simulation results show that the proposed algorithm yields 25.4% gain in terms of reliability compared to Q-learning.

In this paper, the problem of 360° image transmission is studied for a wireless network of virtual reality (VR) users that communicate with cellular base stations (BSs). The VR users will send their uplink tracking information to the BS and receive the VR images in the downlink. To satisfy VR users' delay target, the BSs can change the image transmission format for each image requested by users so as to reduce the downlink traffic load. Meanwhile, the VR users can directly rotate the already received VR image and use the rotated VR images at a later time to further reduce the downlink traffic load. This 360° image transmission and image rotation problem is then formulated as an optimization problem whose goal is to maximize the users' successful transmission probability which is defined as the probability that the delay of tracking information and image transmission for each VR user satisfies the VR delay requirement. A liquid state machine (LSM) based transfer learning algorithm is proposed to solve this optimization problem. The proposed LSM-baseda transfer learning algorithm enables each BS to transfer the already learned successful transmission to the new successful transmission that must be learned so as to increase the convergence speed. Simulation results show that the proposed algorithm achieves 14.9% gain in terms of successful transmission probability compared to Q-learning.

In this paper, the problem of content caching and transmission is studied for a wireless virtual reality (VR) network in which cellular-connected unmanned aerial vehicles (UAVs) capture videos on live games or sceneries and transmit them to small base stations (SBSs) that service the VR users. To meet the VR delay requirements, the UAVs can extract specific visible content (e.g., user field of view) from the original 360° VR data and send this visible content to the users so as to reduce the traffic load over backhaul and radio access links. The extracted visible content consists of 120° horizontal and 120° vertical images. To further alleviate the UAV-SBS backhaul traffic, the SBSs can also cache the popular contents that users request. This joint content caching and transmission problem are formulated as an optimization problem whose goal is to maximize the users' reliability defined as the probability that the content transmission delay of each user satisfies the instantaneous VR delay target. To address this problem, a distributed deep learning algorithm that brings together new neural network ideas from liquid state machine (LSM), and echo state networks (ESNs) is proposed. The proposed algorithm enables each SBS to predict the users' reliability so as to find the optimal contents to cache and content transmission format for each cellular-connected UAV. Analytical results are derived to expose the various network factors that impact content caching and content transmission format selection. Simulation results show that the proposed algorithm yields 25.4% and 14.7% gains, in terms of reliability compared to Q-learning and a random caching algorithm, respectively.

Providing seamless connectivity for wireless virtual reality (VR) users has emerged as a key challenge for future cloud-enabled cellular networks. In this paper, the problem of wireless VR resource management is investigated for a wireless VR network in which VR contents are sent by a cloud to cellular small base stations (SBSs). The SBSs will collect tracking data from the VR users, over the uplink, in order to generate the VR content and transmit it to the end-users using downlink cellular links. For this model, the data requested or transmitted by the users can exhibit correlation, since the VR users may engage in the same immersive virtual environment with different locations and orientations. As such, the proposed resource management framework can factor in such spatial data correlation, so as to better manage uplink and downlink traffic. This potential spatial data correlation can be factored into the resource allocation problem to reduce the traffic load in both the uplink and downlink. In the downlink, the cloud can transmit 360° contents or specific visible contents (e.g., user field of view) that are extracted from the original 360° contents to the users according to the users' data correlation so as to reduce the backhaul traffic load. In the uplink, each SBS can associate with the users that have similar tracking information so as to reduce the tracking data size. This data correlation-aware resource management problem is formulated as an optimization problem whose goal is to maximize the users' successful transmission probability, defined as the probability that the content transmission delay of each user satisfies an instantaneous VR delay target. To solve this problem, a machine learning algorithm that uses echo state networks (ESNs) with transfer learning is introduced. By smartly transferring information on the SBS's utility, the proposed transfer-based ESN algorithm can quickly cope with changes in the wireless networking environment due to users' content requests and content request distributions. Simulation results demonstrate that the developed algorithm achieves up to 15.8% and 29.4% gains in terms of successful transmission probability compared to Q-learning with data correlation and Q-learning without data correlation, respectively.

In this paper, the problem of joint caching and resource allocation is investigated for a network of cache-enabled unmanned aerial vehicles (UAVs) that service wireless ground users over the LTE licensed and unlicensed bands. The considered model focuses on users that can access both licensed and unlicensed bands while receiving contents from either the cache units at the UAVs directly or via content server-UAV-user links. This problem is formulated as an optimization problem, which jointly incorporates user association, spectrum allocation, and content caching. To solve this problem, a distributed algorithm based on the machine learning framework of liquid state machine (LSM) is proposed. Using the proposed LSM algorithm, the cloud can predict the users' content request distribution while having only limited information on the network's and users' states. The proposed algorithm also enables the UAVs to autonomously choose the optimal resource allocation strategies that maximize the number of users with stable queues depending on the network states. Based on the users' association and content request distributions, the optimal contents that need to be cached at UAVs and the optimal resource allocation are derived. Simulation results using real datasets show that the proposed approach yields up to 17.8% and 57.1% gains, respectively, in terms of the number of users that have stable queues compared with two baseline algorithms: Q-learning with cache and Q-learning without cache. The results also show that the LSM significantly improves the convergence time of up to 20% compared with conventional learning algorithms such as Q-learning.

In this paper, the problem of resource management is studied for a network of wireless virtual reality (VR) users communicating using an unmanned aerial vehicle (UAV)- enabled LTE over unlicensed (LTE-U) network. In the studied model, {the UAVs act as VR control centers that collect tracking information from the VR users over the wireless uplink and, then, send the constructed VR images to the VR users over an LTE-U downlink.} Therefore, resource allocation in such a UAV-enabled LTE-U network must jointly consider the uplink and downlink links over both licensed and unlicensed bands. In such a VR setting, the UAVs can dynamically adjust the data size of each VR image by tuning its quality and format. By doing so, the UAVs can adjust the transmitted data size according to the spectrum allocated to each user so as to meet the delay requirement. Therefore, resource allocation must also take into account the image quality and format. This VR-centric resource allocation problem is formulated as a noncooperative game that enables a joint allocation of licensed and unlicensed spectrum bands, as well as a dynamic adaptation of VR image quality and format. To solve this game, a learning algorithm based on the machine learning tools of echo state networks (ESNs) with leaky integrator neurons is proposed. Unlike conventional ESN learning algorithms that are suitable for discrete-time systems, the proposed algorithm can dynamically adjust the update speed of the ESN's state and, hence, it can enable the UAVs to learn the continuous dynamics of their associated VR users. Simulation results show that the proposed algorithm achieves up to 14% and 27.1% gains in terms of total VR QoE for all users compared to Q-learning using LTE-U and Q-learning using LTE.

In this paper, the echo state network (ESN) memory capacity, which represents the amount of input data an ESN can store, is analyzed for a new type of deep ESNs. In particular, two deep ESN architectures are studied. First, a parallel deep ESN is proposed in which multiple reservoirs are connected in parallel allowing them to average outputs of multiple ESNs, thus decreasing the prediction error. Then, a series architecture ESN is proposed in which ESN reservoirs are placed in cascade that the output of each ESN is the input of the next ESN in the series. This series ESN architecture can capture more features between the input sequence and the output sequence thus improving the overall prediction accuracy. Fundamental analysis shows that the memory capacity of parallel ESNs is equivalent to that of a traditional shallow ESN, while the memory capacity of series ESNs is smaller than that of a traditional shallow ESN. In terms of normalized root mean square error, simulation results show that the parallel deep ESN achieves 38.5% reduction compared to the traditional shallow ESN while the series deep ESN achieves 16.8% reduction.

In this paper, the problem of resource management is studied for a network of wireless virtual reality (VR) users communicating over small cell networks (SCNs). In order to capture the VR users' quality-of-service (QoS) in SCNs, a novel VR model, based on multi-attribute utility theory, is proposed. This model jointly accounts for VR metrics, such as tracking accuracy, processing delay, and transmission delay. In this model, the small base stations (SBSs) act as the VR control centers that collect the tracking information from VR users over the cellular uplink. Once this information is collected, the SBSs will then send the 3-D images and accompanying audio to the VR users over the downlink. Therefore, the resource allocation problem in VR wireless networks must jointly consider both the uplink and downlink. This problem is then formulated as a noncooperative game and a distributed algorithm based on the machine learning framework of echo state networks (ESNs) is proposed to find the solution of this game. The proposed ESN algorithm enables the SBSs to predict the VR QoS of each SBS and is guaranteed to converge to mixed-strategy Nash equilibrium. The analytical result shows that each user's VR QoS jointly depends on both VR tracking accuracy and wireless resource allocation. Simulation results show that the proposed algorithm yields significant gains, in terms of VR QoS utility, that reach up to 22.2% and 37.5%, respectively, compared with Q-learning and a baseline proportional fair algorithm. The results also show that the proposed algorithm has a faster convergence time than Q-learning and can guarantee low delays for VR services.

In this paper, the problem of resource management is studied for a network of wireless virtual reality (VR) users communicating over small cell networks (SCNs). In order to capture the VR users' quality-of-service (QoS), a novel VR model, based on multi-attribute utility theory, is proposed. This model jointly accounts for VR metrics such as tracking accuracy, processing delay, and transmission delay. In this model, the small base stations (SBSs) act as the VR control centers that collect the tracking information from VR users over the cellular uplink. Once this information is collected, the SBSs will then send the three dimensional images and accompanying surround stereo audio to the VR users over the downlink. Therefore, the resource allocation problem in VR wireless networks must jointly consider both the uplink and downlink. This problem is then formulated as a noncooperative game and a distributed algorithm based on the machine learning framework of echo state networks (ESNs) is proposed to find the solution of this game. The proposed ESN algorithm enables the SBSs to predict the VR QoS of each SBS and guarantees the convergence to a mixed-strategy Nash equilibrium. Simulation results show that the proposed algorithm yields significant gains, in terms of total utility value of VR QoS, that reach up to 22% compared to Q-learning. The results also show that the proposed algorithm has a faster convergence time than Q- learning and can guarantee low delays for VR services.

In this paper, the problem of joint caching and resource allocation is investigated for a network of cache-enabled unmanned aerial vehicles (UAVs) that service wireless ground users over the LTE licensed and unlicensed (LTE-U) bands. The considered model focuses on users that can access both licensed and unlicensed bands while receiving contents through UAV cache-user links and content server-UAV-user links. This problem is formulated as an optimization problem which jointly incorporates user association, spectrum allocation, and content caching. To solve this problem, a distributed algorithm based on the machine learning framework of liquid state machine (LSM) is proposed. Using the proposed LSM algorithm, the cloud can predict the users' content request distribution while having only limited information on the network's and users' states. The proposed algorithm also enables the UAVs to autonomously choose the optimal resource allocation strategies depending on the network states. Simulation results using real datasets show that the proposed approach yields up to 33.3% and 50.3% gains, respectively, in terms of the number of users that have stable queues compared to two baseline algorithms: Q-learning with cache and Q-learning without cache. The results also show that LSM significantly improves the convergence time of up to 33.3% compared to Q-learning.

In this paper, the problem of proactive deployment of cache-enabled unmanned aerial vehicles (UAVs) for optimizing the quality-of-experience (QoE) of wireless devices in a cloud radio access network is studied. In the considered model, the network can leverage human-centric information, such as users' visited locations, requested contents, gender, job, and device type to predict the content request distribution, and mobility pattern of each user. Then, given these behavior predictions, the proposed approach seeks to find the user-UAV associations, the optimal UAVs' locations, and the contents to cache at UAVs. This problem is formulated as an optimization problem whose goal is to maximize the users' QoE while minimizing the transmit power used by the UAVs. To solve this problem, a novel algorithm based on the machine learning framework of conceptor-based echo state networks (ESNs) is proposed. Using ESNs, the network can effectively predict each user's content request distribution and its mobility pattern when limited information on the states of users and the network is available. Based on the predictions of the users' content request distribution and their mobility patterns, we derive the optimal locations of UAVs as well as the content to cache at UAVs. Simulation results using real pedestrian mobility patterns from BUPT and actual content transmission data from Youku show that the proposed algorithm can yield 33.3% and 59.6% gains, respectively, in terms of the average transmit power and the percentage of the users with satisfied QoE compared with a benchmark algorithm without caching and a benchmark solution without UAVs.

Uplink-downlink decoupling in which users can be associated to different base stations in the uplink and downlink of heterogeneous small cell networks (SCNs) has attracted significant attention recently. However, most existing works focus on simple association mechanisms in LTE SCNs that operate only in the licensed band. In contrast, in this paper, the problem of resource allocation with uplink-downlink decoupling is studied for an SCN that incorporates LTE in the unlicensed band. Here, the users can access both licensed and unlicensed bands while being associated to different base stations. This problem is formulated as a noncooperative game that incorporates user association, spectrum allocation, and load balancing. To solve this problem, a distributed algorithm based on the machine learning framework of echo state networks (ESNs) is proposed. This proposed algorithm allows the small base stations to autonomously choose their optimal resource allocation strategies given only limited information on the network's and users' states. It is shown that the proposed algorithm converges to a stationary mixed-strategy distribution, which constitutes a mixed strategy Nash equilibrium for their studied game. Simulation results show that the proposed approach yields significant gain, in terms of the sum-rate of the 50th percentile of users, that reaches up to 167% compared with a Q-learning algorithm. The results also show that the ESN significantly provides a considerable reduction of information exchange for the wireless network.

In this paper, the problem of proactive caching is studied for cloud radio access networks (CRANs). In the studied model, the baseband units (BBUs) can predict the content request distribution and mobility pattern of each user and determine which content to cache at remote radio heads and the BBUs. This problem is formulated as an optimization problem, which jointly incorporates backhaul and fronthaul loads and content caching. To solve this problem, an algorithm that combines the machine learning framework of echo state networks (ESNs) with sublinear algorithms is proposed. Using ESNs, the BBUs can predict each user's content request distribution and mobility pattern while having only limited information on the network's and user's state. In order to predict each user's periodic mobility pattern with minimal complexity, the memory capacity of the corresponding ESN is derived for a periodic input. This memory capacity is shown to capture the maximum amount of user information needed for the proposed ESN model. Then, a sublinear algorithm is proposed to determine which content to cache while using limited content request distribution samples. Simulation results using real data from Youku and the Beijing University of Posts and Telecommunications show that the proposed approach yields significant gains, in terms of sum effective capacity, that reach up to 27.8% and 30.7%, respectively, compared with two baseline algorithms: random caching with clustering and random caching without clustering.

Uplink-downlink decoupling in which users can be associated to different base stations in the uplink and downlink in heterogeneous small cell networks (SCNs) has attracted significant attention recently. However, most existing works focus on simple association mechanisms in LTE SCNs that operate only in the licensed band. In contrast, in this paper, the problem of resource allocation with uplink-downlink decoupling is studied for an SCN that incorporates LTE in the unlicensed band (LTE-U). Here, the users can access both licensed and unlicensed bands while being associated to different base stations. This problem is formulated as an optimization problem which jointly incorporates user association, spectrum allocation, and load balancing. To solve this problem, a distributed algorithm based on the machine learning framework of echo state networks is proposed using which the small base stations autonomously choose their optimal bands allocation strategies while having only limited information on the network's and users' states. Simulation results show that the proposed approach yields significant gains, in terms of total rate, that reach up to 41% and 54%, respectively, compared to Q-learning and nearest neighbor algorithms. The results also show that ESN significantly improves convergence time of up to 17% compared to Q-learning.

In the practical heterogeneous cellular networks, a macro base station (MBS) is usually not located at the center of the macrocell and the distances from the MBS to its edges are also different. For this reason, the tri-sectoring method defined by 3GPP which divides three equal sectors and allocates each sector the same power may severely degrade the communication performance of the edge users. In this paper, we propose a novel tri-sectoring method and a MBS sector power allocation scheme for orthogonal frequency division multiple access based downlink of MBSs under co-channel deployment in heterogeneous cellular networks. We first evaluate the performance of 3GPP tri-sectoring method by using a hexagonal grid model and a Matern hard-core process (MHP) model, respectively, to demonstrate the inapplicability of 3GPP tri-sectoring method to the practical MHP model. Then, we devise a novel tri- sectoring method which considers load balancing and the directional radiation pattern of antennas. At last, a MBS sector power allocation scheme is proposed to control their downlink transmit power according to the downlink outage probability of edge macrocell users. Simulation results show that the proposed methods can improve the throughput of femtocell users and area spectral efficiency.

This paper is focused on the issue of complexity and low accuracy of downlink (DL) power control in dense heterogeneous network. A novel power control algorithm based on the interference statistic properties that is accurate and results in easy-to-evaluate interference is proposed. Compared to the recent work on DL power control using complex iterations to manege interference, the proposed algorithm differs in two key features. First, the interference statistic model based on the stochastic geometry is exploited to estimate cross-tier interference that follows alpha stable distribution. Second, a centralized power control algorithm with the complementary cumulative distribution function (CCDF) of alpha stable distribution is utilized to constrain interference effectively. Simulation results show that the proposed algorithm can maintain the outage probability of macrocell user (MUE) within a certain range and improve the throughput with less exchange of information.