Search

An introduction of intelligent interconnectivity for people and things has posed higher demands and more challenges for sixth-generation (6G) networks, such as high spectral efficiency and energy efficiency (EE), ultralow latency, and ultrahigh reliability. Cell-free (CF) massive multiple-input-multiple-output (mMIMO) and reconfigurable intelligent surface (RIS), also called intelligent reflecting surface (IRS), are two promising technologies for coping with these unprecedented demands. Given their distinct capabilities, integrating the two technologies to further enhance wireless network performances has received great research and development attention. In this article, we provide a comprehensive survey of research on RIS-aided CF mMIMO wireless communication systems. We first introduce system models focusing on system architecture and application scenarios, channel models, and communication protocols. Subsequently, we summarize the relevant studies on system operation and resource allocation, providing in-depth analyses and discussions. Following this, we present practical challenges faced by RIS-aided CF mMIMO systems, particularly those introduced by RIS, such as hardware impairments (HIs) and electromagnetic interference (EMI). We summarize the corresponding analyses and solutions to further facilitate the implementation of RIS-aided CF mMIMO systems. Furthermore, we explore an interplay between RIS-aided CF mMIMO and other emerging 6G technologies, such as millimeter wave (mmWave) and terahertz (THz), simultaneous wireless information and power transfer (SWIPT), next-generation multiple access (NGMA), and unmanned aerial vehicle (UAV). Finally, we outline several research directions for future RIS-aided CF mMIMO systems.

This paper considers cell-free multiple-input multiple-output (MIMO) systems with multi-antenna access points (APs) and multi-antenna users in constrained spaces. Two main effects emerge in such a space-constrained design: spatial correlation and mutual coupling. We analytically study the resulting performance with conjugate beamforming and reducing inter-antenna distance. We derive the closed-form expression for the spectral efficiency (SE) as a function of the spatial correlation and mutual coupling matrices. Additionally, we consider a practical power consumption model to investigate the energy efficiency (EE) with power control coefficients. The obtained ergodic and analytical results will show essential insights into the system performance. The decreasing inter-antenna distance introduces performance loss, while an appropriate number of APs could balance the SE and EE trade-off. The number of users improves the SE performance, while an optimal number of antennas per user can be selected to achieve maximum SE performance. Moreover, more users will introduce a smaller optimal number of antennas per user.

The flexible-position multiple-input multiple-output (FLP-MIMO) -- used in, for example, fluid antennas and movable antennas -- is a promising technology for future wireless communications. This is due to the fact that the positions of antennas at the transceiver and reflector can be dynamically optimized using FLP-MIMO to achieve better channel conditions and, as such, can provide high spectral efficiency (SE) and energy efficiency (EE) gains with fewer antennas. In this article, we introduce the fundamentals of FLP-MIMO systems, including hardware design, structure design, and potential applications. We shall demonstrate that FLP-MIMO, using fewer flexible antennas, can match the channel hardening achieved by a large number of fixed antennas. We will then analyze the SE-EE relationship for FLP-MIMO and fixed-position MIMO. Furthermore, we will design the optimal trajectory of flexible antennas to maximize system sum SE or total EE at a fixed travel distance of each antenna. Finally, several important research directions regarding FLP-MIMO communications are presented to facilitate further investigation.

The recent evolution of generative artificial intelligence (GAI) leads to the emergence of groundbreaking applications such as ChatGPT, which not only enhances the efficiency of digital content production, such as text, audio, video, or even network traffic data, but also enriches its diversity. Beyond digital content creation, GAI’s capability in analyzing complex data distributions offers great potential for wireless communications, particularly amidst a rapid expansion of new physical layer communication technologies. For example, the diffusion model can learn input signal distributions and use them to improve the channel estimation accuracy, while the variational autoencoder can model channel distribution and infer latent variables for blind channel equalization. Therefore, this paper presents a comprehensive investigation of GAI’s applications for communications at the physical layer, ranging from traditional issues, including signal classification, channel estimation, and equalization, to emerging topics, such as intelligent reflecting surfaces and joint source channel coding. We also compare GAI-enabled physical layer communications with those supported by traditional AI, highlighting GAI’s inherent capabilities and unique contributions in these areas. Finally, the paper discusses open issues and proposes several future research directions, laying a foundation for further exploration and advancement of GAI in physical layer communications. IEEE

In this paper, we propose an online federated learning framework with massive random access, aiming to learn a sequence of global models using local data that are sequentially collected by massive edge devices. As only a subset of devices is capable of collecting data and performing local model update at any specific moment, the communication pattern between the edge server and devices is random and sporadic, which is referred to as sporadic local updates. This motivates us to adopt a two-phase grant-free random access scheme that consists of the activity detection and model transmission phases to facilitate efficient communication between the edge server and devices. We first provide the regret analysis for online federated learning, and derive the optimality gap in terms of successful transmission probabilities. Then, we characterize the achievable transmission rate of each active device using random matrix theory and establish the relationship between the pilot length and the outage probability. Furthermore, we propose an optimal pilot length design by minimizing the optimality gap. To validate our scheme, we provide comprehensive experimental results that demonstrate the superiority of the proposed scheme over traditional schemes in various online tasks. IEEE

Hard-delay constrained wireless communication has attracted considerable recent attention because it holds the promise of playing a vital role in wireless Internet of Things (IoT) systems for supporting time-sensitive tasks. Hard-delay constrained communication refers to the case in which the delay-violation probability of packets is zero with a given deadline. How to strike the optimal power-latency-throughput tradeoff with a hard-delay constraint remains open. In this paper, we aim to characterize the hard-delay constrained capacity with a deadline which covers one or multiple coherence time of the fading channel. Specifically, we first conceive a low-complexity and yet sub-optimal cross-layer scheduling scheme to obtain an analytical bound of the hard-delay constrained capacity. Saddlepoint approximation is adopted to obtain its hard-delay constrained throughput as a function of the tolerated delay and average power, which provides us with properties of the achievable bound of the hard-delay constrained capacity. Further, we investigate the optimal joint channel and queue-aware scheduling to derive the hard-delay constrained capacity. In particular, by quantifying channel and queue states and recalling the optimality of threshold-based policies, we approximate the optimal hard-delay constrained scheduling by a deterministic policy obtained based on the quantized Constrained Markov Decision Process. More structures of this optimal scheduling policy are revealed through curve fitting by dividing system states into distinct regions. Finally, the hard-delay constrained capacity is presented as a function of both the average power and maximum delay, with the assistance of both theoretical analysis from the achievable bound and curve fitting. IEEE

Edge caching is a promising solution for next-generation networks by empowering caching units in small-cell base stations (SBSs), which allows user equipments (UEs) to fetch users’ requested contents that have been pre-cached in SBSs. It is crucial for SBSs to predict accurate popular contents through learning while protecting users’ personal information. Traditional federated learning (FL) can protect users’ privacy but the data discrepancies among UEs can lead to a degradation in model quality. Therefore, it is necessary to train personalized local models for each UE to predict popular contents accurately. In addition, the cached contents can be shared among adjacent SBSs in next-generation networks, thus caching predicted popular contents in different SBSs may affect the cost to fetch contents. Hence, it is critical to determine where the popular contents are cached cooperatively. To address these issues, we propose a cooperative edge caching scheme based on elastic federated and multi-agent deep reinforcement learning (CEFMR) to optimize the cost in the network. We first propose an elastic FL algorithm to train the personalized model for each UE, where adversarial autoencoder (AAE) model is adopted for training to improve the prediction accuracy, then a popular content prediction algorithm is proposed to predict the popular contents for each SBS based on the trained AAE model. Finally, we propose a multi-agent deep reinforcement learning (MADRL) based algorithm to decide where the predicted popular contents are collaboratively cached among SBSs. Our experimental results demonstrate the superiority of our proposed scheme to existing baseline caching schemes. IEEE

The rapid advancement of artificial intelligence technologies has given rise to diversified intelligent services, which place unprecedented demands on massive connectivity and gigantic data aggregation. However, the scarce radio resources and stringent latency requirement make it challenging to meet these demands. To tackle these challenges, over-the-air computation (AirComp) emerges as a potential technology. Specifically, AirComp seamlessly integrates the communication and computation procedures through the superposition property of multiple-access channels, which yields a revolutionary multiple-access paradigm shift from “compute-after-communicate” to “compute-when-communicate”. By this means, AirComp enables spectral-efficient and low-latency wireless data aggregation by allowing multiple devices to occupy the same channel for transmission. In this paper, we aim to present the recent advancement of AirComp in terms of foundations, technologies, and applications. The mathematical form and communication design are introduced as the foundations of AirComp, and the critical issues of AirComp over different network architectures are then discussed along with the review of existing literature. The technologies employed for the analysis and optimization on AirComp are reviewed from the information theory and signal processing perspectives. Moreover, we present the existing studies that tackle the practical implementation issues in AirComp systems, and elaborate the applications of AirComp in Internet of Things and edge intelligent networks. Finally, potential research directions are highlighted to motivate the future development of AirComp. IEEE

As a promising learning paradigm integrating computation and communication, federated learning (FL) proceeds the local training and the periodic sharing from distributed clients. Due to the non-i.i.d. data distribution on clients, FL model suffers from the gradient diversity, poor performance, bad convergence, etc. In this work, we aim to tackle this key issue by adopting importance sampling (IS) for local training. We propose importance sampling federated learning (ISFL), an explicit framework with theoretical guarantees. Firstly, we derive the convergence theorem of ISFL to involve the effects of local importance sampling. Then, we formulate the problem of selecting optimal IS weights and obtain the theoretical solutions. We also employ a water-filling method to calculate the IS weights and develop the ISFL algorithms. The experimental results on CIFAR-10 fit the proposed theorems well and verify that ISFL reaps better performance, convergence, sampling efficiency, as well as explainability on non-i.i.d. data. To the best of our knowledge, ISFL is the first non-i.i.d. FL solution from the local sampling aspect which exhibits theoretical compatibility with neural network models. Furthermore, as a local sampling approach, ISFL can be easily migrated into other emerging FL frameworks. IEEE

With the growing popularity of wearable devices, body-centric networks have become the focus of Internet of Things (IoT) research. However, malicious eavesdroppers and attackers pose threats to user privacy and network secrecy. Fortunately, physical layer security (PLS) communication and covert communication (CC) have been introduced and can be used in body-centric networks. However, network performance of both secrecy techniques has not been analyzed with an accurate wireless fading model. To fill this research gap, we study a body-centric IoT communication system with information secrecy features based on PLS and CC techniques. By adopting the Alternate Rician Shadowed fading model, we derive closed-form expressions for the secrecy outage probability and secrecy rate in PLS, and the detection error probability and covert rate in CC. To provide more explicit guidance, an algorithm for the selection of PLS and CC techniques is proposed, which aims to reach a high transmission performance state while ensuring communication security and covertness. The secrecy rate and covert rate are analytically and empirically compared. We insightfully find that, with the help of a friendly jammer, CC performs better than PLS, especially with high transmit power. However, an upper boundary of transmit power exists to ensure communication covertness in CC. IEEE

This paper investigates the energy-efficient coordinated beamforming design for multi-pair multiple-input single-output (MISO) networks with passive eavesdroppers. To be practical, it is assumed that only channel distribution information (CDI) of the network is known by the transmitters/sources, and the dynamic energy consumption model (DECM) is employed. In order to achieve a green network design, an energy efficiency (EE) maximization problem is formulated subjecting to the individual available power constraints, the rate outage probability constraints, and the information leakage probability constraints. To solve the formulated non-convex problem, semidefinite relaxation (SDR) and first-order lower bound are applied to transform the problem, and then an efficient algorithm is proposed based on successive convex approximation (SCA) and Dinkelbach's approaches. The proposed algorithm is theoretically proved to converge to a stationary point of the considered problem. Further, a distributed version of the proposed algorithm is designed, with which each transmitter is able to optimize its own beamforming vector with local CDI. Moreover, the computational complexities and the signaling overheads of the two developed algorithms are analyzed and compared. Simulation results show that both algorithms achieve good EE performance, and the EE performance achieved by the distributed algorithm is very similar to that achieved by the centralized one. Additionally, it is shown that similar to the conventional scenarios without eavesdroppers, the achieved system EE also has a saturation point w.r.t. the available power of the transmitters, and by employing our proposed algorithms, the network security is significantly enhanced. IEEE

Channel capacity estimation plays a crucial role in beyond 5G intelligent communications. Despite its significance, this task is challenging for a majority of channels, especially for the complex channels not modeled as the well-known typical ones. Recently, neural networks have been used in mutual information estimation and optimization. They are particularly considered as efficient tools for learning channel capacity. In this paper, we propose a cooperative framework to simultaneously estimate channel capacity and design the optimal codebook. First, we will leverage MIM-based GAN, a novel form of generative adversarial network (GAN) using message importance measure (MIM) as the information distance, into mutual information estimation, and develop a novel method, named MIM-based mutual information estimator (MMIE). Then, we design a generalized cooperative framework for channel capacity learning, in which a generator is regarded as an encoder producing the channel input, while a discriminator is the mutual information estimator that assesses the performance of the generator. Through the adversarial training, the generator automatically learns the optimal codebook and the discriminator estimates the channel capacity. Numerical experiments will demonstrate that compared with several conventional estimators, the MMIE achieves state-of-the-art performance in terms of accuracy and stability. IEEE

With the sixth-generation (6G) vision of connecting everything, integrating real-time sensing, communication, computing, and control together in Internet of Everything (IoE) becomes essential to support intelligent services. Such a tendency is facing great challenges in terms of information freshness, energy sustainability, and energy efficiency (EE). Thus, network requires to satisfy multiple objectives, including low age of information (AoI) and high EE. Nevertheless, existing designs mainly focused on AoI and EE separately and has no unified rule in various wireless communications scenarios. In order to efficiently describe the system performances from both information timeliness and energy saving perspectives, this article presents a novel utility-aware performance metric, i.e., age-energy efficiency (AEE), to measure the achieved AoI gain by consuming per joule energy, which takes both age and energy into account. To show the evocativeness of AEE, we explore the AEE in several typical network scenarios, such as the point-to-point (P2P) network, the wireless powered communication network (WPCN), the mobile edge computing (MEC) network and the multi-user network, as examples. The optimal policies to maximize the AEE performance of such network scenarios are also presented. Numerical results show that the AEE is a concave function of the transmit power, and can be employed to pursue the maximal age gain by consuming as less as energy in 6G intelligent network design. Additionally, some insightful promising directions on AEE for research are also presented for 6G networks. IEEE

Federated learning (FL) is a promising distributed learning mechanism that revolutionizes our interaction with data in the IoT ecosystem. Due to the rapidly growing scale of smart devices and the limited transmission resources of networks, a simple, consistent, and scalable FL framework aiming to address the communication bottleneck is urgently needed. In this work, we propose an efficient approach with selective aggregation of models (SAMs) to mitigate the communication overload in FL systems. The introduction of SAM enables each local client to upload its model with a certain probability, resulting in a significant reduction in costly communication expenses. We design the algorithm for SAM, analyze the convergence bound on nonconvex objectives for heterogeneous data, which illustrates the impact of the selection probability as well as the set size of participating clients on the system performance, and assess the conservation for the network resource utilization by modeling queuing systems. We conduct various experiments to evaluate the performance of SAM, whose outcomes suggest that significant alleviation of the communication bottleneck can be accomplished with marginal cost of performance loss. It will also be shown that SAM is a communication-efficient method that can be freely applied to other frameworks. © 2014 IEEE.

The evolution of wireless networks gravitates towards connected intelligence, a concept that envisions seamless interconnectivity among humans, objects, and intelligence in a hyper-connected cyber-physical world. Edge artificial intelligence (Edge AI) is a promising solution to achieve connected intelligence by delivering high-quality, low-latency, and privacy-preserving AI services at the network edge. This article presents a vision of autonomous edge AI systems that automatically organize, adapt, and optimize themselves to meet users' diverse requirements, leveraging the power of large language models (LLMs), i.e., Generative Pretrained Transformer (GPT). By exploiting the powerful abilities of GPT in language understanding, planning, and code generation, as well as incorporating classic wisdom such as task-oriented communication and edge federated learning, we present a versatile framework that efficiently coordinates edge AI models to cater to users' personal demands while automatically generating code to train new models in a privacy-preserving manner. Experimental results demonstrate the system's remarkable ability to accurately comprehend user demands, efficiently execute AI models with minimal cost, and effectively create highperformance AI models at edge servers.

This paper presents a cache-aided time-domain power allocation (CaTDPA) for 5G high-speed railway communications (HSRC), where two kinds of users, online interactive application users (OIUs) and online non-interactive application users (ONIUs), are jointly taken into account. For OIUs, their minimum ground-train data rate demand is guaranteed. For ONIUs, their minimum cache-releasing data rate demand is guaranteed. To achieve the green HSRC design, an optimization problem is formulated to maximize the system energy efficiency (EE) by jointly optimizing the power allocation (PA) and cache releasing start time (CRST) subject to the constraints of total available energy, maximum transmit power, ONIUs' ground-train data rate threshold, ONIUs' cache-releasing data rate threshold, and causality of CRST. To address such a non-convex and fractional problem, a two-step solution is designed. First, with a given CRST, a Dinkelbach-based method is applied to obtain the correspondingly optimal PA. Second, the one-dimensional traversal method is used to find the optimal CRST. Experimental results show that our proposed CaTDPA achieves the maximum EE among multiple compared methods while meeting the requirements of OIUs and ONIUs. Moreover, EE will decrease as the OIUs' ground-train data rate threshold and the train's moving speed increase, while it is observed that the ONIUs' cache-releasing data rate threshold has a relatively small effect on the EE of HSRC. © 2023 IEEE.

Reliability is of paramount importance for the physical layer of wireless systems due to its decisive impact on end-to-end performance. However, the uncertainty of prevailing deep learning (DL)-based physical layer algorithms is hard to quantify due to the black-box nature of neural networks. This limitation is a major obstacle that hinders their practical deployment. In this paper, we attempt to quantify the uncertainty of an important category of DL-based channel estimators. An efficient statistical method is proposed to make blind predictions for the mean squared error of the DL-estimated channel solely based on received pilots, without knowledge of the ground-truth channel, the prior distribution of the channel, or the noise statistics. The complexity of the blind performance prediction is low and scales only linearly with the number of antennas. Simulation results for ultra-massive multiple-input multiple-output (UM-MIMO) channel estimation with a mixture of far-field and near-field paths are provided to verify the accuracy and efficiency of the proposed method.

Sensing will become an important service of future wireless networks to assist innovative applications such as autonomous driving and environment monitoring. Perceptive mobile networks (PMNs) were proposed to incorporate sensing capability into current cellular networks. However, the interference management between sensing and communication, as well as the collaborative sensing by multiple sensing nodes (SNs), faces significant challenges. In this paper, we first propose a two-stage protocol to tackle the interference between two sub-systems, where the echoes created by communication signals, i.e., interference for sensing, are estimated in the clutter estimation (CE) stage and then utilized for interference management in the target sensing (TS) stage. Then, a networked sensing detector is derived to exploit the perspectives provided by multiple SNs for sensing the same target. The macro-diversity from multiple SNs, the array gain, and the higher angular resolution from multiple receive antennas of each SN are then investigated to reveal the benefit of networked sensing. Furthermore, we derive the sufficient condition for one SN’s contribution to be positive, based on which a SN selection algorithm is proposed. To reduce the communication workload, we propose a distributed model-driven deep-learning algorithm that utilizes partially-sampled data for CE. Simulation results demonstrate the benefits of networked sensing and validate the higher efficiency of the proposed CE algorithm than existing methods.

Terahertz ultra-massive MIMO (THz UM-MIMO) is envisioned as one of the key enablers of 6G wireless networks, for which channel estimation is highly challenging. Traditional analytical estimation methods are no longer effective, as the enlarged array aperture and the small wavelength result in a mixture of far-field and near-field paths, constituting a hybrid-field channel. Deep learning (DL)-based methods, despite the competitive performance, generally lack theoretical guarantees and scale poorly with the size of the array. In this paper, we propose a general DL framework for THz UM-MIMO channel estimation, which leverages existing iterative channel estimators and is with provable guarantees. Each iteration is implemented by a fixed point network (FPN), consisting of a closed-form linear estimator and a DL-based non-linear estimator. The proposed method perfectly matches the THz UM-MIMO channel estimation due to several unique advantages. First, the complexity is low and adaptive. It enjoys provable linear convergence with a low per-iteration cost and monotonically increasing accuracy, which enables an adaptive accuracy-complexity tradeoff. Second, it is robust to practical distribution shifts and can directly generalize to a variety of heavily out-of-distribution scenarios with almost no performance loss, which is suitable for the complicated THz channel conditions. For practical usage, the proposed framework is further extended to wideband THz UM-MIMO systems with beam squint effect. Theoretical analysis and extensive simulation results are provided to illustrate the advantages over the state-of-the-art methods in estimation accuracy, convergence rate, complexity, and robustness.

A multi-unmanned aerial vehicles (UAVs)-aided secure communication network is studied, where multiple information UAVs carrying temporary aerial base stations transmit confidential information to multiple authorized receivers (ARs), and a jammer UAV is employed to send artificial noise to multiple unauthorized receivers (URs) for mitigating information leakage. Some practical constrains including the inter-UAV interference among the information UAVs and the jammer UAV, the maximal available propulsion energy at UAVs, and the curvature radius limitations of UAVs' trajectories are concurrently taken into account. In order to maximize the minimum secrecy rate among the ARs, the AR scheduling, the UAVs' power allocation and the trajectories of UAVs are jointly optimized by formulating a multi-variable optimization problem. To solve the non-convex problem efficiently, we present a block coordinate descent (BCD)-based approach, where the penalty dual decomposition (PDD)-based algorithm is designed to optimize the AR scheduling, and successive convex approximation (SCA)-based algorithm is proposed to optimize the UAVs' power allocation and the trajectories of UAVs. The complexity of the presented BCD-based approach is analyzed, which achieves polynomial complexity. Simulation results show that imposing curvature radius limitations on the UAVs' trajectory design is effective to avoid sharp turning of UAVs. Moreover, as curvature radius increases, the system max-min secrecy rate decreases. Besides, the secrecy rate performance of the system can be enhanced by exploiting one jammer UAV to interfere with the URs.

This paper investigates the age of information (AoI)-based online scheduling in multi-sensor wireless powered communication networks (WPCNs) for time-sensitive Internet of Things (IoT). Specifically, we consider a typical WPCN model, where a wireless power station (WPS) charges multiple sensor nodes (SNs) by wireless power transfer (WPT), and then the SNs are scheduled in the time domain to transmit their sampled status information with their harvested energy to a mobile edge server (MES) for decision making. For such a system, we first derive a closed-form expression of the successful data transmission probability in Nakagami-m fading channels. To pursue an efficient online scheduling policy that minimizes the Expected Weighted Sum AoI (EWSAoI) of the system, a discrete-time scheduling problem is formulated. As the problem is non-convex with non-explicit expression of the EWSAoI, we propose a Max-Weight policy based on the Lyapunov optimization theory, which schedules the SNs at the beginning of each time in terms of the one-slot conditional Lyapunov Drift. Simulations demonstrate our presented theoretical results and show that our proposed scheduling policy outperforms other baselines such as greedy policy and random round-robin (RR) policy. Especially, when the number of SNs is relatively small, the gain achieved by the proposed policy compared to the greedy policy is considerable. Moreover, some interesting insights are also observed: 1) as the number of SNs increases, the EWSAoI also increases; 2) when the transmit power is relatively small, the larger the number of SNs, the smaller the EWSAoI; 3) the EWSAoI decreases with the increment of transmit power of the WPS and then tends to be flat; 4) the EWSAoI increases with the increment of the distance between the SNs and the MES.

Currently, reinforcement learning (RL) is widely used in wireless network optimization, where the key factor is to design the efficient reward functions manually. However, the limitations of the man-made reward function are mainly that it is subject to human subjective factors and requires extensive simulations to select appropriate parameters. To cope with this, the paper proposes an inverse reinforcement learning (IRL)-based approach to optimize the transmit power control in multi-cell multi-user networks, which does not require any prior knowledge about the system and the wireless environment. An optimization problem is formulated to maximize the achievable sum information rate subject to the minimal required information rate of users. To tackle the NP-hard non-convex problem, our IRL-based approach is able to obtain rewards automatically rather than through a man-made reward function. In particular, the successive convex approximation (SCA)-based approach is adopted as the expert-policy to generate the expert data to train the automatic rewards. Simulation results support that the proposed IRL-based approach outperforms the traditional RL-based ones.

Ultra-wideband (UWB) is a popular technology for indoor positioning. However, non-line-of-sight (NLOS) propagation caused by human occlusion dramatically affects the accuracy of UWB-based indoor positioning. Most of the existing works focused on mitigating NLOS errors in the scenarios with building structure occlusion, but the NLOS mitigation under human occlusion has not been well addressed. To this end, this paper aims to mitigate the NLOS impact of human occlusion, and then proposes a method of NLOS mitigation to reduce NLOS ranging errors under human occlusion with low-cost UWB devices (i.e., NM-LUD). It takes a set of signal features extracted from low-cost devices as input, calculates their weights and mitigates the ranging error based on the features' weights. Experiment results on the two data sets collected by LinkTrack S and UML1 UWB devices show that the method reduces ranging error from 0.9009 m to 0.1435 m (about by 84.07%) and from 0.7466 m to 0.0792 m (about by 89.39%) respectively, which greatly mitigates the influence of NLOS caused by human occlusion.

This paper aims to efficiently save energy consumption of multiple-input-single-output (MISO) networks. To this end, an optimization problem is formulated to minimize the transmit power of the base station (BS) while ensuring the minimal required information rate of each user. Reinforcement learning (RL) is a significant solution to tackle this non-convex problems. Nevertheless, designing efficient reward functions that accurately describe the involved optimization problems for RL is a challenging problem, which may result in low learning efficiency and even inaccurate learning. To cope with such an issue, this paper proposes an inverse reinforcement learning (IRL)-based approach to minimize the transmit power of MISO networks, in which the generative adversarial imitation learning (GAIL) is employed as the IRL framework and the reward function is represented by an artificial neural network (ANN) model, whose parameters are learned automatically in terms of an expert policy based on the semidefinite relaxation (SDR)-based approach. Since SDR is able to achieve the near optimal solution, the learned reward function is more accurate than traditional artificially designed one. Simulations show that, the proposed IRL-based approach reaches similar energy consumption to the SDR-based approach, and reduces about 50% transmit power compared to traditional RL-based one.

This letter focuses on maximizing the energy efficiency (EE) for secure visible light communication (VLC) network with simultaneous lightwave information and power transfer (SLIPT) by optimizing the beamforming vectors and direct current (DC) bias under the constraints of the minimal rate requirement, the secure transmission requirement, the minimal energy harvesting (EH) requirement, and total power budget at the transmitters. To solve the non-convex optimization problem, we present a dual-layer iterative algorithm based on Dinkelbach’s and successive convex approximation (SCA) methods. An efficient algorithm is also designed to find a good initial point to accelerate the convergence. Simulation results show three typical phenomena: (1) the EE first remains unchanged and then decreases with the increasing EH requirement; (2) compared with the traditional sum-rate maximization design, our proposed approach achieves notable EE performance gain under the secure constraints; (3) the number of the authorized receivers, as well as the number of the unauthorized receivers, imposes significant impact on the EE performance.

Distributed machine learning is envisioned as the bedrock of future intelligent networks, where agents exchange information with each other to train models collaboratively without uploading data to a central processor. Despite its broad applicability, a downside of distributed learning is the need for iterative information exchange between agents, which may lead to high communication overhead unaffordable in many practical systems with limited communication resources. To resolve this communication bottleneck, we need to devise communication-efficient distributed learning algorithms and protocols that can reduce the communication cost and simultaneously achieve satisfactory learning/optimization performance. Accomplishing this goal necessitates synergistic techniques from a diverse set of fields, including optimization, machine learning, wireless communications, game theory, and network/graph theory. This Special Issue is dedicated to communication-efficient distributed learning from multiple perspectives, including fundamental theories, algorithm design and analysis, and practical considerations. © 1983-2012 IEEE.

This paper studies the energy-efficient cooperative base station (BS) switching-off in multi-input single-output (MISO) cellular networks, where the roaming-cost based cooperation and the cooperative beamforming among multiple mobile network operators (MNOs) are jointly designed. To make the cooperation among MNOs practical, we introduce a new constraint to make sure the cooperative profit gain of MNOs is non-negative and also formulate an optimization problem to maximize the system energy efficiency (EE) by jointly considering multiple factors, including the operation modes of BSs, the connection states between users and BSs, the beamforming vectors of multi-antenna BSs under constraints of users’ quality of service, BSs’s power budget, and the non-negative profit gain of MNOs, etc. To solve the non-convex problem, we propose an energy-efficient beamforming-aware BS switching off method (EBBSOM), in which we first design a roaming-cost-based BS switching-off algorithm (EE-BSOA) to search the feasible inactive BSs and then propose a successive convex approximation (SCA) and Dinkelbach’s method-based EE maximization beamforming algorithm (EE-BFA) to optimize beamforming vectors. In order to keep the cooperative profit gain non-negative for MNOs and also to balance the load and power consumption of BS from the profit perspective, we present a profit-wise BS switching-off priority method. We theoretically prove that the proposed EBBSOM is able to resolve the inconsistency between BS switching-off and EE maximization. Simulations show that the proposed EBBSOM enhances the system EE without degrading the economic profit gain of MNOs. Also, the proposed profit-wise BS switching-off priority enables the EBBSOM to achieve higher EE than traditional load-wise one. Furthermore, it is also observed that there exists a feasible rate price region, which is able to clearly characterize network EE and the average profit gain of MNOs simultaneously.

Efficient massive/ultra-massive multiple-input multiple-output (MIMO) detection algorithms with satisfactory performance and low complexity are critical to meet the high throughput and ultra-low latency requirements in 5G and beyond communications, given the extremely large number of antennas. In this paper, we propose a low complexity graph neural network (GNN) enhanced approximate message passing (AMP) algorithm, AMP-GNN, for massive/ultra-massive MIMO detection. The structure of the neural network is customized by unfolding the AMP algorithm and introducing the GNN module for multiuser interference cancellation. Numerical results will show that the proposed AMP-GNN significantly improves the performance of the AMP detector and achieves comparable performance as the state-of-the-art deep learning-based MIMO detectors but with reduced computational complexity. Furthermore, it presents strong robustness to the change of the number of users.

With the development of innovative applications that demand accurate environment information, for example, autonomous driving, sensing becomes an important requirement for future wireless networks. To this end, integrated sensing and communication (ISAC) provides a promising platform to exploit the synergy between sensing and communication, where perceptive mobile networks (PMNs) were proposed to add accurate sensing capability to existing wireless networks. The well-developed cellular networks offer exciting opportunities for sensing, including large coverage, strong computation, communication power, and, most importantly, networked sensing, where the perspectives from multiple sensing nodes can be collaboratively utilized for sensing the same target. However, PMNs also face big challenges, such as the inherent interference between sensing and communication, the complex sensing environment, and the tracking of high-speed targets by cellular networks. This article provides a comprehensive review on the design of PMNs, covering the popular network architectures, sensing protocols, standing research problems, and available solutions. Several future research directions that are critical for the development of PMNs are also discussed.

Existing deep learning-enabled semantic communication systems often rely on shared background knowledge between the transmitter and receiver that includes empirical data and their associated semantic information. In practice, the semantic information is defined by the pragmatic task of the receiver and cannot be known to the transmitter. The actual observable data at the transmitter can also have non-identical distribution with the empirical data in the shared background knowledge library. To address these practical issues, this paper proposes a new neural network-based semantic communication system for image transmission, where the task is unaware at the transmitter and the data environment is dynamic. The system consists of two main parts, namely the semantic coding (SC) network and the data adaptation (DA) network. The SC network learns how to extract and transmit the semantic information using a receiver-leading training process. By using the domain adaptation technique from transfer learning, the DA network learns how to convert the data observed into a similar form of the empirical data that the SC network can process without re-training. Numerical experiments show that the proposed method can be adaptive to observable datasets while keeping high performance in terms of both data recovery and task execution. © 1983-2012 IEEE.

This paper investigates reconfigurable intelligent surface (RIS)-assisted simultaneous wireless information and power transfer (SWIPT) networks with rate splitting multiple access (RSMA). An energy efficiency (EE) maximization problem is formulated subject to the power budget at the transmitter and the quality of service (QoS) requirements of both information communication and energy harvesting, where the beamforming vectors, the power splitting (PS) ratios, the common message rates, and the discrete phase shifts are jointly optimized. To tackle the non-convex problem with both discrete and continuous variables, a deep reinforcement learning-based approach is proposed with the proximal policy optimization (PPO) framework. Different from traditional optimization approaches which optimizes the beamforming vectors and phase shifts separately and alternatively, our proposed PPO-based approach optimizes all the variables in unison. Besides, to perform beamforming design in action space, the beamforming vectors for the common stream and the private stream are respectively designed based on the maximum-ratio transmission and the zero forcing to enhance both energy and information transmission. To evaluate the performance of the PPO-based approach, a successive convex approximation (SCA) and Dinkelbach’s method based solution scheme (named SCA-D scheme) is also presented. Simulation results show that the system EE obtained by the proposed PPO-based approach is close to that obtained by the SCA-D scheme while outperforming various benchmarks. The RSMA contributes to the EE of the system greatly compared with traditional scheme. As for the case of time-varying channels, the proposed PPO-based approach is with much smaller running time by only sacrificing a slight EE performance compared with the SCA-D scheme.

This paper focuses on the ultimate limit theory of image compression. It proves that for an image source, there exists a coding method with shapes that can achieve the entropy rate under a certain condition where the shape-pixel ratio in the encoder/decoder is (Formula presented.). Based on the new finding, an image coding framework with shapes is proposed and proved to be asymptotically optimal for stationary and ergodic processes. Moreover, the condition (Formula presented.) of shape-pixel ratio in the encoder/decoder has been confirmed in the image database MNIST, which illustrates the soft compression with shape coding is a near-optimal scheme for lossless compression of images. © 2022 by the authors.

Distributed learning is envisioned as the bedrock of next-generation intelligent networks, where intelligent agents, such as mobile devices, robots, and sensors, exchange information with each other or a parameter server to train machine learning models collaboratively without uploading raw data to a central entity for centralized processing. By utilizing the computation/communication capability of individual agents, the distributed learning paradigm can mitigate the burden at central processors and help preserve data privacy of users. Despite its promising applications, a downside of distributed learning is its need for iterative information exchange over wireless channels, which may lead to high communication overhead unaffordable in many practical systems with limited radio resources such as energy and bandwidth. To overcome this communication bottleneck, there is an urgent need for the development of communication-efficient distributed learning algorithms capable of reducing the communication cost and achieving satisfactory learning/optimization performance simultaneously. In this paper, we present a comprehensive survey of prevailing methodologies for communication-efficient distributed learning, including reduction of the number of communications, compression and quantization of the exchanged information, radio resource management for efficient learning, and game-theoretic mechanisms incentivizing user participation. We also point out potential directions for future research to further enhance the communication efficiency of distributed learning in various scenarios. IEEE

Federated learning (FL) has recently emerged as an innovative paradigm to train models among distributed agents. Conventional FL considers the center as an aggregator and trains from distributed data, while the collected global information at the center is not effectively utilized. Thus, the restricted information from local observations may limit the model accuracy. If FL can introduce data sets from the network server, the distributed models may be largely improved by the extra global information. Since network agents may not be completely trusted, the center cannot directly broadcast its raw data for security concern. Then, how to combine the central sets with FL? In this article, we propose to add a learning model at the center, which obtains the central sets as input. The outputs can be transmitted to network agents and integrated into local models instead of the raw data. The central and local models could be trained to form an integration for intelligent inference. Then, what is the integrated performance gain comparing with the original horizontal FL (HFL) and how to implement it? To figure out these two problems, we propose the vertical-HFL (VHFL) scheme, where models of the center and agents are trained collaboratively. We further analyze its convergence and the related communication channel, proposing the theoretical bounds to guide the network implementation of VHFL. Some simulation results will demonstrate the effectiveness of our proposed VHFL scheme. It is expected that VHFL will be an important block for the next generation of smart services.

The emerging Ultra-Reliable and Low-Latency Communication (URLLC) is expected to meet a hard or probabilistic delay constraint that plays a key role in Time Sensitive Networking (TSN) and Deterministic Networking (DetNet). In this paper, we are interested in simple bounds for delay-constrained wireless communications with deterministic or even random packet arrivals. More specifically, we present a sufficient condition and derive a legitimate data arrival rate, with which the bounded delay can be guaranteed deterministically with an average power constraint. Our derived results will show that the delay-bounded data rate increases with the average power and the tolerated latency normalized to the coherent time. Furthermore, we derive the upper and lower bounds of the delay-violation probability (DVP) when the bounded delay condition cannot be satisfied. It is revealed that in the log coordinate, the DVP as a function of the normalized tolerated latency may enjoy a non-linear decay, with a decay rate that increases with the latency bound. This is in contrast to the large deviation based performance analysis that focuses on the low-latency transmission policies achieving linearly decayed DVP only. Our result demonstrates that the joint channel-aware and queue-aware scheduling may significantly reduce the DVP, compared to the single-layer approaches.

Deep learning-based approaches have been developed to solve challenging problems in wireless communications, leading to promising results. Early attempts adopted neural network architectures inherited from applications such as computer vision. They often yield poor performance in large scale networks (i.e., poor scalability) and unseen network settings (i.e., poor generalization). To resolve these issues, graph neural networks (GNNs) have been recently adopted, as they can effectively exploit the domain knowledge, i.e., the graph topology in wireless communications problems. GNN-based methods can achieve nearoptimal performance in large-scale networks and generalize well under different system settings, but the theoretical underpinnings and design guidelines remain elusive, which may hinder their practical implementations. This paper endeavors to fill both the theoretical and practical gaps. For theoretical guarantees, we prove that GNNs achieve near-optimal performance in wireless networks with much fewer training samples than traditional neural architectures. Specifically, to solve an optimization problem on an n-node graph (where the nodes may represent users, base stations, or antennas), GNNs’ generalization error and required number of training samples are O(n) and O (n^2) times lower than the unstructured multi-layer perceptrons. For design guidelines, we propose a unified framework that is applicable to general design problems in wireless networks, which includes graph modeling, neural architecture design, and theory-guided performance enhancement. Extensive simulations, which cover a variety of important problems and network settings, verify our theory and the effectiveness of the proposed design framework. IEEE

This paper studies a simultaneous lightwave information and power transfer (SLIPT)-enabled multi-user (MU) multiple input single output (MISO) visible light communication (VLC) network, where multiple user equipments (UEs) are simultaneously allowed to receive information by the photodiode (PD) and harvest energy by the solar panel, respectively. To improve the system spectral efficiency, an achievable sum rate maximization problem is formulated subject to the minimum energy harvesting (EH) requirement of each UE, the total transmit power constraint of the LEDs and the dimming control constraint of the LEDs, by jointly optimizing the beamforming vector and the direct current (DC) bias vector of the LEDs. To be general, the practical non-linear EH model and the information capacity model of the VLC channel are adopted. To solve the non-convex optimization problem, the objective function is equivalently transformed at first by using the epigraph reformulation, and then the transformed problem is relaxed with the semi-definite relaxation (SDR) method. Based on this, an iterative algorithm is designed to approximately obtain the maximal achievable sum rate based on the successive convex approximation (SCA). Simulation results indicate that there exists a non-trivial trade-off between the achievable sum rate and the harvested energy, and that DC bias vector dominates the amount of the harvested energy compared with the beamforming vector. Besides, for a given relatively high EH requirement, the achievable sum rate increases with the increment of the dimming level, especially for relatively small dimming level. Once the dimming level is larger than a specific value, with the increment of the dimming level, more transmit power will be allocated for illumination, resulting in the decrement of the achievable sum rate. IEEE

Federated learning (FL) is a powerful distributed machine learning framework where a server aggregates models trained by different clients without accessing their private data. Hierarchical FL, with a client-edge-cloud aggregation hierarchy, can effectively leverage both the cloud server’s access to many clients’ data and the edge servers’ closeness to the clients to achieve a high communication efficiency. Neural network quantization can further reduce the communication overhead during model uploading. To fully exploit the advantages of hierarchical FL, an accurate convergence analysis with respect to the key system parameters is needed. Unfortunately, existing analysis is loose and does not consider model quantization. In this paper, we derive a tighter convergence bound for hierarchical FL with quantization. The convergence result leads to practical guidelines for important design problems such as the client-edge aggregation and edge-client association strategies. Based on the obtained analytical results, we optimize the two aggregation intervals and show that the client-edge aggregation interval should slowly decay while the edge-cloud aggregation interval needs to adapt to the ratio of the client-edge and edge-cloud propagation delay. Simulation results shall verify the design guidelines and demonstrate the effectiveness of the proposed aggregation strategy.

This paper investigates a multi-user wireless powered fog computing (FC) network, where energy-limited wireless sensor devices (WSDs) first harvest energy from a nearby hybrid access point (HAP) and then, compute their tasks locally (i.e., the local computing (LC) mode) or offload the tasks to the HAP (i.e., the FC mode) via a binary offloading policy. An optimization problem is formulated to minimize the transmit power at the HAP by jointly optimizing the time allocation ratio and the computing mode selection vector, under the energy causality constraints and the WSDs computing rate requirements constraints. To efficiently solve the formulated non-convex problem in a distributed manner, an alternating direction method of multipliers (ADMM)-based algorithm is designed. With our presented ADMM-based algorithm, each WSD is able to optimize its computing mode and offloading time with local channel state information (CSI). For comparison, a channel-sorting-based (CSB) centralized algorithm with global CSI is also designed. Simulation results show that the proposed distributed algorithm achieves the comparable performance with the centralized algorithm or by using the exhaustive search one. Moreover, to minimize the transmit power, the WSDs with the better channel quality are inclined to select the LC mode, which is much different from traditional design.

The emerging real-time wireless communication systems are expected to provide deadline assurance for delay-sensitive traffics generated from factory automation, smart grids, and automatic driving, etc. Although there has been cutting edge research on diversity-enabled deadline assurance, real-time communications may suffer from poor energy efficiency. In this paper, we present a paradigm-shift real-time wireless communication method based on matching diversity that is judiciously designed for orthogonal frequency division multi-access (OFDMA) systems. In particular, we adopt bipartite graph to formulate a unified framework for OFDMA, based on which joint subcarrier matching and power adaptation policies are conceived to provide real-time transmissions, also referred to as just-in-time services (JITS). By bridging the average power and the formula of the outage probability, we show that the deadline constraints can be satisfied with a finite average power, when the number of users in the OFDMA system is not greater than that of subcarriers with independent channel gains. Furthermore, we also derive the approximate but yet analytical results on the required average power consumption. Numerical results indicate that a substantial energy efficiency gain can be attained in real-time OFDMA systems if the subcarrier interleaving based frequency diversity is replaced by matching diversity.

As a privacy preserving framework, federated learning (FL) has been prevailing in numerous distributed scenarios. In this work, to enhance FL on non-iid data, we propose an explicit FL scheme with local importance sampling, Fed-Lis. Theoretically, we derive the convergence bound of Fed-Lis and obtain the design rule of the optimal sampling strategies. Experimentally, we formulate the algorithm and evaluate it on CIFAR-10. The results indicate that Fed-Lis reaps better accuracy, sampling efficiency, as well as robustness on non-iid data. Notably, as a non-iid FL solution from the local sampling aspect, Fed-Lis exhibits theoretical compatibility for non-convex loss functions. Furthermore, as a local sampling operation, Fed-Lis can be easily migrated into emerging FL frameworks. © 2023 IEEE.

Task-oriented communication is an emerging paradigm for next-generation communication networks, which extracts and transmits task-relevant information, instead of raw data, for downstream applications. Most existing deep learning (DL)-based task-oriented communication systems adopt a closed-world assumption, assuming either the same data distribution for training and testing, or the system could have access to a large out-of-distribution (OoD) dataset for retraining. However, in practical open-world scenarios, task-oriented communication systems will be exposed to unknown OoD data. The powerful approximation ability of learning methods may force the task-oriented communication systems to overfit the training data (i.e., in-distribution data). Therefore, these systems tend to provide overconfident judgments when encountering OoD data. Based on the information bottleneck (IB) framework, we propose a class conditional IB (CCIB) approach to address this problem, supported by information-theoretical insights. The idea is to extract distinguishable features from in-distribution data while keeping their compactness and informativeness. It is achieved by imposing the class conditional latent prior distribution and enforcing the latent of different classes to be far away from each other. Simulation results shall demonstrate that the proposed approach detects OoD data more efficiently than the baselines and state-of-the-art approaches, without compromising the rate-distortion tradeoff.

Federated learning (FL) is a privacy-preserving collaborative learning framework, and differential privacy can be applied to further enhance its privacy protection. Existing FL systems typically adopt Federated Average (FedAvg) as the training algorithm and implement differential privacy with a Gaussian mechanism. However, the inherent privacy-utility trade-off in these systems severely degrades the training performance if a tight privacy budget is enforced. Besides, the Gaussian mechanism requires model weights to be of high-precision. To improve communication efficiency and achieve a better privacy-utility trade-off, we propose a communication-efficient FL training algorithm with differential privacy guarantee. Specifically, we propose to adopt binary neural networks (BNNs) and introduce discrete noise in the FL setting. Binary model parameters are uploaded for higher communication efficiency and discrete noise is added to achieve the client-level differential privacy protection. The achieved performance guarantee is rigorously proved, and it is shown to depend on the level of discrete noise. Experimental results based on MNIST and Fashion-MNIST datasets will demonstrate that the proposed training algorithm achieves client-level privacy protection with performance gain while enjoying the benefits of low communication overhead from binary model updates.

Delay-constrained communications have attracted considerable recent attention because it holds the promise of playing a vital role in time sensitive networking (TSN) and deterministic networking (DetNet). In this paper, we investigate the tradeoff between power, latency, and throughput, which characterizes a fundamental performance limit of diversity enabled delay-bounded communications over fading channels. In particular, we are interested in a typical cross-layer scheduling policy, namely, the age-aware non-FIFO strategy, which is capable of satisfying a hard delay constraint by exploiting the physical-layer diversity methods. Saddle point approximation is adopted to obtain the analytical approximation of the average transmission power as a function of the throughput and the delay threshold normalized to the coherence time. This analytical expression characterizes the power-latency-throughput tradeoff of the diversity enabled delay-bounded communications over the fading channel. To validate our analysis, we present a discretization-based method to conduct the numerical calculation. The numerical results match well with the simulation results, which also shows that the approximation error will vanish with sufficiently small discretization granularity. © 2023 IEEE.

Federated learning (FL) has prevailed as an efficient and privacy-preserved scheme for distributed learning. In this work, we mainly focus on the optimization of computation and communication in FL from a view of pruning. By adopting layer-wise pruning in local training and federated updating, we formulate an explicit FL pruning framework, FedLP (Federated Layer-wise Pruning), which is model-agnostic and universal for different types of deep learning models. Two specific schemes of FedLP are designed for scenarios with homogeneous local models and heterogeneous ones. Both theoretical and experimental evaluations are developed to verify that FedLP relieves the system bottlenecks of communication and computation with marginal performance decay. To the best of our knowledge, FedLP is the first framework that formally introduces the layer-wise pruning into FL. Within the scope of federated learning, more variants and combinations can be further designed based on FedLP. © 2023 IEEE.

This paper studies an intelligent reflecting surface (IRS)-assisted unmanned aerial vehicle (UAV) network, where the ground users (GUs) desire to receive information from a UAV. Downlink non-orthogonal multiple access (NOMA) is considered typically with two GUs being selected according to whether a Line of Sight (LoS) link between GUs and UAV exists. As the accurate channel information of LoS or Non-Line-of-Sight (NLoS) links for multiple GUs is difficult to acquire, an approximate LoS region-based method is designed to select GUs as an alternative. In order to enhance the communication quality of the far GU, an IRS is deployed to assist the NLoS transmission. For such a system, we evaluate its outage performance in Nakagami-m fading. First, the central limit theorem (CLT) and Laplace Transform (LT) are employed to derive the channel statistics of the UAV-IRS-user link. Then, asymptotic closed-form expressions of the outage probabilities are derived for the selected GUs based on Gaussian-Chebyshev quadrature approximation. Monte Carlo simulations validate the validness of our derived outage probabilities. It shows that the approximate LoS region-based scheme provides similar outage performance laws as the accurate LoS region-based one. Moreover, the outage probabilities of selected GUs in terms of NOMA-based protocol and orthogonal multiple access (OMA)-based protocol are analyzed. Simulation results confirm that the proposed NOMA-based protocol is capable of achieving superior performance compared with the OMA-based protocol by setting power allocation factor and targeted SINR thresholds of near GU and far GU properly. Specifically, when the rate threshold of near GU is relatively large or the rate threshold of far GU is relatively small, the outage performance derived by NOMA-based protocol performs better than OMA-based protocol in most of cases. IEEE