This paper studies an integrated sensing and communications (ISAC) system for low-altitude economy (LAE), where a ground base station (GBS) provides communication and navigation services for authorized unmanned aerial vehicles (UAVs), while sensing the low-altitude airspace to monitor the unauthorized mobile target. The expected communication sum-rate over a given flight period is maximized by jointly optimizing the beamforming at the GBS and UAVs’ trajectories, subject to the constraints on the average signal-to-noise ratio requirement for sensing, the flight mission and collision avoidance of UAVs, as well as the maximum transmit power at the GBS. Typically, this is a sequential decision-making problem with the given flight mission. Thus, we transform it to a specific Markov decision process (MDP) model called episode task. Based on this modeling, we propose a novel LAE-oriented ISAC scheme, referred to as Deep LAE-ISAC (DeepLSC), by leveraging the deep reinforcement learning (DRL) technique. In DeepLSC, a reward function and a new action selection policy termed constrained noise-exploration policy are judiciously designed to fulfill various constraints. To enable efficient learning in episode tasks, we develop a hierarchical experience replay mechanism, where the gist is to employ all experiences generated within each episode to jointly train the neural network. Besides, to enhance the convergence speed of DeepLSC, a symmetric experience augmentation mechanism, which simultaneously permutes the indexes of all variables to enrich available experience sets, is proposed. Simulation results demonstrate that compared with benchmarks, DeepLSC yields a higher sum-rate while meeting the preset constraints, achieves faster convergence, and is more robust against different settings.

Mobile edge computing (MEC) empowers mobile devices (MDs) in supporting artificial intelligence (AI) applications through collaborative efforts with proximal MEC servers. Unfortunately, despite the great promise of device-edge cooperative AI inference, data privacy has been an increasing concern. In this paper, we develop a novel privacy-aware multi-device cooperative edge inference system for classification tasks, which integrates a distributed bidding mechanism for the MEC server’s computational resources. Intermediate feature compression is adopted as a principled approach to minimize data privacy leakage. To determine the bidding values and feature compression ratios, we formulate a decentralized partially observable Markov decision process (DEC-POMDP) model, for which a multi-agent deep deterministic policy gradient (MADDPG)-based algorithm is developed. Simulation results demonstrate that given a sufficient level of data privacy protection, the proposed algorithm achieves 0.31-0.95% improvements in classification accuracy compared to the approach being agnostic to wireless channel conditions. The accuracy performance of the proposed algorithm is further enhanced by 1.54-1.67% when considering the difficulties of inference data in the DEC-POMDP model.

Passenger counting is crucial for public transport vehicle scheduling and traffic capacity evaluation. However, most existing methods are either costly or with low counting accuracy, leading to the recent use of Wi-Fi signals for this purpose. In this paper, we develop an efficient edge computing-based passenger counting system consists of multiple Wi-Fi receivers and an edge server. It leverages channel state information (CSI) and received signal strength indicator (RSSI) to facilitate the collaboration among multiple receivers. Specifically, we design a novel CSI feature fusion module called Adaptive RSSI-weighted CSI Feature Concatenation, which integrates locally extracted CSI and RSSI features from multiple receivers for information fusion at the edge server. Performance of our proposed system is evaluated using a real-world dataset collected from a double-decker bus in Hong Kong, with up to 20 passengers. The experimental results reveal that our system achieves an average accuracy and F1-score of over 94 %, surpassing other cooperative sensing baselines by at least 2.27 % in accuracy and 2.34 % in F1-score.

This paper investigates the joint modulation-coding scheme (MCS) adaptation and beamforming design for multi-user multi-input single-output (MISO) systems, where one base station serves multiple user equipments (UEs) under imperfect and outdated channel state information (CSI). The sum-rate of the system is maximized while satisfying all UEs’ data rate requirements and the maximum transmit power constraint at the BS. Most existing beamforming designs overlooked that only a finite number of MCSs can be supported in practical communication systems. Moreover, previous works rely on perfect and real-time CSI for decision-making, neglecting processing delays and channel estimation errors. To circumvent the above issues, this paper puts forth an intelligent joint optimization scheme based on deep reinforcement learning (DRL) techniques. Specifically, a new DRL framework, termed constrained hybrid DRL (CHDRL), is first proposed, which incorporates Lagrangian primal-dual optimization theory and a constrained action selection policy into conventional DRL to tackle various constraints. By integrating deep Q-network (DQN) and deep deterministic policy gradient algorithms, CHDRL is capable of simultaneously optimizing MCS in the discrete action domain and beamforming in the continuous action domain. In addition, to handle the large discrete action space of DQN, we develop an action branch architecture for CHDRL to enable independent and concurrent MCS decisions at different UEs. Finally, a multi-parameter experience replay mechanism is designed to synchronously train Lagrangian multipliers and neural network parameters. Simulation results demonstrate that under imperfect and outdated CSI, CHDRL outperforms other benchmark schemes by (i) achieving a significantly higher sum-rate, (ii) meeting more UEs’ data rate requirements, and (iii) being more robust against different CSI delays and numbers of UEs.

Visual Simultaneous Localization and Mapping (vSLAM) is a prevailing technology for many emerging robotic applications. Achieving real-time SLAM on mobile robotic systems with limited computational resources is challenging because the complexity of SLAM algorithms increases over time. This restriction can be lifted by offloading computations to edge servers, forming the emerging paradigm ofedge-assisted SLAM. Nevertheless, the exogenous and stochastic input processes affect the dynamics of the edge-assisted SLAM system. Moreover, the requirements of clients on SLAM metrics change over time, exerting implicit and time-varying effects on the system. In this paper, we aim to push the limit beyond existing edge-assist SLAM by proposing a new architecture that can handle the input-driven processes and also satisfy clients’ implicit and time-varying requirements. The key innovations of our work involve a regional feature prediction method for importance-aware local data processing, a configuration adaptation policy that integrates data compression/decompression and task offloading, and an input-dependent learning framework for task scheduling with constraint satisfaction. Extensive experiments prove that our architecture improves pose estimation accuracy and saves up to 47% of communication costs compared with a popular edge-assisted SLAM system, as well as effectively satisfies the clients’ requirements.

The emergence of intelligent mobile technologies and the widespread adoption of 5G wireless networks have made Federated Learning (FL) a promising method for protecting privacy during distributed model training. However, traditional FL frameworks rely on static aggregators such as base stations, encountering obstacles such as increased energy demands, frequent disconnections, and poor model performance. To address these issues, this paper investigates an innovative aUtonomous Aerial Vehicle (UAV)-assisted FL framework, aiming to utilize UAVs as mobile model aggregators to collaborate with devices in training models, while minimizing the total energy consumption of devices and ensuring that FL can achieve the target model accuracy. By adopting the Distributed Approximate NEwton (DANE) method for local optimization, we analyze the convergence of FL and derive device scheduling constraints that aid in convergence. Accordingly, we formulate a problem of minimizing the total energy consumption of devices, integrating a constraint on global model accuracy, and jointly optimizing the UAV trajectory, device scheduling, bandwidth allocation, time slot lengths, as well as the uplink transmission power, CPU frequency, and local convergence accuracy. Then, we decompose this non-convex optimization problem into three subproblems and propose an iterative algorithm based on Block Coordinate Descent (BCD) with convergence guarantee. Simulation results indicate that, compared with various benchmark methods, our proposed UAV-assisted FL framework significantly reduces the total energy consumption of devices and achieves an improved trade-off between energy and convergence accuracy.

This paper investigates an intelligent omni-surface (IOS)-assisted integrated sensing and communication (ISAC) system, where a base station provides both target sensing and communication services with an IOS. The sensing signal-to-noise ratio (SNR) is maximized while satisfying the communication requirement by optimizing IOS configurations. Conventional approaches typically need real-time and accurate channel state information (CSI) and have high computational complexity, making them difficult to implement in realistic systems. To circumvent this problem, this paper puts forth a new framework based on deep reinforcement learning (DRL) with knowledge transfer. In particular, an online learning scheme called Deep reinforcement learning IOS-ISAC (DeepOSC), is first proposed to optimize the reflecting and refracting coefficients of the IOS. Thereafter, to enable powerful reasoning and fast decision-making, we incorporate an echo state network (ESN) with separate output into DeepOSC. To further accelerate convergence, two transfer learning approaches, namely staged policy reuse (SPR) and staged policy distillation (SPD), are developed to guide the learning process of a newly deployed agent by leveraging policies of pre-trained agents. Numerical results show that compared to various benchmarks, DeepOSC attains significant sensing and communication performance gains and is more robust against outdated CSI coefficients. In addition, in comparison to conventional neural networks, ESN shortens the run-time of DeepOSC by more than ten times and is more efficient for temporal inference. Besides, we demonstrate the capabilities of SPR and SPD in accelerating the convergence of DeepOSC.

This study addresses the core challenges in federated learning (FL), namely achieving optimal model utility, safeguarding local data privacy, and maintaining efficient communication. While previous research has focused on either the privacy-utility or communication-utility trade-offs, the investigation of simultaneously considering utility, privacy protection, and communication efficiency has been largely overlooked. In this paper, we propose a novel training framework for FL that combines communication efficiency and differential privacy. Specifically, we employ quantization and binomial noise on model updates to enhance privacy protection and communication efficiency concurrently. Through convergence and privacy analysis, we formulate an optimization problem that maximizes model utility while adhering to privacy and communication constraints. Additionally, we introduce an adaptive algorithm to determine key system parameters, including the level of quantization and privacy noise. Simulation results validate the effectiveness of our proposed FL framework and parameter optimization algorithm.

In order to control the inter-cell interference for a multi-cell multi-user multiple-input multiple-output network, we consider the precoder design for coordinated multi-point with downlink coherent joint transmission. To avoid costly information exchange among the cooperating base stations in a centralized precoding scheme, we propose a decentralized one by considering the power minimization problem. By approximating the inter-cell interference using the deterministic equivalents, this problem is decoupled to sub-problems which are solved in a decentralized manner at different base stations. Simulation results demonstrate the effectiveness of our proposed decentralized precoding scheme, where only 2 ∼ 7% more transmit power is needed compared with the optimal centralized precoder.

Because of its privacy-preserving capability, federated learning (FL) has attracted significant attention from both academia and industry. However, when being implemented over wireless networks, it is not clear how much communication error can be tolerated by FL. This paper investigates the robustness of FL to the uplink and downlink communication error. Our theoretical analysis reveals that the robustness depends on two critical parameters, namely the number of clients and the numerical range of model parameters. It is also shown that the uplink communication in FL can tolerate a higher bit error rate (BER) than downlink communication, and this difference is quantified by a proposed formula. The findings and theoretical analyses are further validated by extensive experiments.

Artificial intelligence (AI) technologies have emerged as pivotal enablers across a multitude of industries, including consumer electronics, healthcare, and manufacturing, largely due to their significant resurgence over the past decade. The transformative power of AI is primarily derived from the utilization of deep neural networks (DNNs), which require extensive data for training and substantial computational resources for processing. Consequently, DNN models are typically trained and deployed on resource-rich cloud servers. However, due to potential latency issues associated with cloud communications, deep learning (DL) workflows (e.g., DNN training and inference) are increasingly being transitioned to wireless edge networks in proximity to end-user devices (EUDs). This shift is designed to support latency-sensitive applications and has given rise to a new paradigm of edge AI, which will play a critical role in upcoming sixth-generation (6G) networks to support ubiquitous AI applications. Despite its considerable potential, edge AI faces substantial challenges, mostly due to the dichotomy between the resource limitations of wireless edge networks and the resource-intensive nature of DL. Specifically, the acquisition of large-scale data, as well as the training and inference processes of DNNs, can rapidly deplete the battery energy of EUDs. This necessitates an energy-conscious approach to edge AI to ensure both optimal and sustainable performance. In this article, we present a contemporary survey on green edge AI. We commence by analyzing the principal energy consumption components of edge AI systems to identify the fundamental design principles of green edge AI. Guided by these principles, we then explore energy-efficient design methodologies for the three critical tasks in edge AI systems, including training data acquisition, edge training, and edge inference. Finally, we underscore potential future research directions to further enhance the energy efficiency (EE) of edge AI.

There is an increasing demand of massive machine-type communication (mMTC) to provide scalable access for a large number of devices, which has prompted extensive investigation on grant-free massive random access (RA) in 5G and beyond wireless networks. Although many efficient signal processing algorithms have been developed, the limited radio resource for pilot transmission in grant-free massive RA systems makes accurate user activity detection and channel estimation challenging, which thereby compromises the communication reliability. In this paper, we adopt retransmission as a means to improve the quality of service (QoS) for grant-free massive RA. Specifically, by jointly leveraging the user activity correlation between adjacent transmission blocks and the historical channel estimation results, we first develop an activity-correlation-aware receiver for grant-free massive RA systems with retransmission based on the correlated approximate message passing (AMP) algorithm. Then, we analyze the performance of the proposed receiver, including the user activity detection, channel estimation, and data error, by resorting to the state evolution of the correlated AMP algorithm and the random matrix theory (RMT). Our analysis admits a tight closed-form approximation for frame error rate (FER) evaluation. Simulation results corroborate our theoretical analysis and demonstrate the effectiveness of the proposed receiver for grant-free massive RA with retransmission, compared with a conventional design that disregards the critical user activity correlation.

Federated learning (FL) is a distributed learning paradigm that maximizes the potential of data-driven models for edge devices without sharing their raw data. However, devices often have non-independent and identically distributed ( non-IID) data, meaning their local data distributions can vary significantly. The heterogeneity in input data distributions across devices, commonly referred to as the feature shift problem, can adversely impact the training convergence and accuracy of the global model. To analyze the intrinsic causes of the feature shift problem, we develop a generalization error bound in FL, which motivates us to propose FedCiR, a client-invariant representation learning framework that enables clients to extract informative and client-invariant features. Specifically, we improve the mutual information term between representations and labels to encourage representations to carry essential classification knowledge, and diminish the mutual information term between the client set and representations conditioned on labels to promote representations of clients to be client-invariant. We further incorporate two regularizers into the FL framework to bound the mutual information terms with an approximate global representation distribution to compensate for the absence of the ground-truth global representation distribution, thus achieving informative and client-invariant feature extraction. To achieve global representation distribution approximation, we propose a data-free mechanism performed by the server without compromising privacy. Extensive experiments demonstrate the effectiveness of our approach in achieving client-invariant representation learning and solving the data heterogeneity issue.

Federated learning (FL) has emerged as a privacy-preserving paradigm that trains neural networks on edge devices without collecting data at a central server. However, FL encounters an inherent challenge in dealing with non-independent and identically distributed (non-IID) data among devices. To address this challenge, this paper proposes a hard feature matching data synthesis (HFMDS) method to share auxiliary data besides local models. Specifically, synthetic data are generated by learning the essential class-relevant features of real samples and discarding the redundant features, which helps to effectively tackle the non-IID issue. For better privacy preservation, we propose a hard feature augmentation method to transfer real features towards the decision boundary, with which the synthetic data not only improve the model generalization but also erase the information of real features. By integrating the proposed HFMDS method with FL, we present a novel FL framework with data augmentation to relieve data heterogeneity. The theoretical analysis highlights the effectiveness of our proposed data synthesis method in solving the non-IID challenge. Simulation results further demonstrate that our proposed HFMDS-FL algorithm outperforms the baselines in terms of accuracy, privacy preservation, and complexity saving on various benchmark datasets.

Federated learning (FL) is a promising framework for privacy-preserving collaborative learning, where model training tasks are distributed to clients and only the model updates need to be collected at a server. However, when being deployed at mobile edge networks, clients may have unpredictable availability and drop out of the training process, which hinders the convergence of FL. This paper tackles such a critical challenge. Specifically, we first investigate the convergence of the classical FedAvg algorithm with arbitrary client dropouts. We find that with the common choice of a decaying learning rate, FedAvg may oscillate around a stationary point of the global loss function in the worst case, which is caused by the divergence between the aggregated and desired central update. Motivated by this new observation, we then design a novel training algorithm named MimiC, where the server modifies each received model update based on the previous ones. The proposed modification of the received model updates mimics the imaginary central update irrespective of dropout clients. The theoretical analysis of MimiC shows that divergence between the aggregated and central update diminishes with proper learning rates, leading to its convergence. Simulation results further demonstrate that MimiC maintains stable convergence performance and learns better models than the baseline methods

One of the most critical challenges for deploying distributed learning solutions, such as federated learning (FL), in wireless networks is the limited battery capacity of mobile clients. While it is a common belief that the major energy consumption of mobile clients comes from the uplink data transmission, this paper presents a novel finding, namely channel decoding also contributes significantly to the overall energy consumption of mobile clients in FL. Motivated by this new observation, we propose an energy-efficient adaptive channel decoding scheme that leverages the intrinsic robustness of FL to model errors. In particular, the robustness is exploited to reduce the energy consumption of channel decoders at mobile clients by adaptively adjusting the number of decoding iterations. We theoretically prove that wireless FL with communication errors can converge at the same rate as the case with error-free communication provided the bit error rate (BER) is properly constrained. An adaptive channel decoding scheme is then proposed to improve the energy efficiency of wireless FL systems. Experimental results demonstrate that the proposed method maintains the same learning accuracy while reducing the channel decoding energy consumption by$\sim ~20$% when compared to an existing approach.

Federated learning (FL) is a popular privacy-preserving distributed training scheme, where multiple devices collaborate to train machine learning models by uploading local model updates. To improve communication efficiency, over-the-air computation (AirComp) has been applied to FL, which leverages analog modulation to harness the superposition property of radio waves such that numerous devices can upload their model updates concurrently for aggregation. However, the uplink channel noise incurs considerable model aggregation distortion, which is critically determined by the device scheduling and compromises the learned model performance. In this paper, we propose a probabilistic device scheduling framework for over-the-air FL, namedPO-FL, to mitigate the negative impact of channel noise, where each device is scheduled according to a certain probability and its model update is reweighted using this probability in aggregation. We prove the unbiasedness of this aggregation scheme and demonstrate the convergence of PO-FL on both convex and non-convex loss functions. Our convergence bounds unveil that the device scheduling affects the learning performance through thecommunication distortionandglobal update variance. Based on the convergence analysis, we further develop a channel and gradient-importance aware algorithm to optimize the device scheduling probabilities in PO-FL. Extensive simulation results show that the proposed PO-FL framework with channel and gradient-importance awareness achieves faster convergence and produces better models than baseline methods.

Federated learning (FL) has achieved great success as a privacy-preserving distributed training paradigm, where many edge devices collaboratively train a machine learning model by sharing the model updates instead of the raw data with a server. However, the heterogeneous computational and communication resources of edge devices give rise to stragglers that significantly decelerate the training process. To mitigate this issue, we propose a novel FL framework named stochastic coded federated learning (SCFL) that leverages coded computing techniques. In SCFL, before the training process starts, each edge device uploads a privacy-preserving coded dataset to the server, which is generated by adding Gaussian noise to the projected local dataset. During training, the server computes gradients on the global coded dataset to compensate for the missing model updates of the straggling devices. We design a gradient aggregation scheme to ensure that the aggregated model update is an unbiased estimate of the desired global update. Moreover, this aggregation scheme enables periodical model averaging to improve the training efficiency. We characterize the tradeoff between the convergence performance and privacy guarantee of SCFL. In particular, a more noisy coded dataset provides stronger privacy protection for edge devices but results in learning performance degradation. We further develop a contract-based incentive mechanism to coordinate such a conflict. The simulation results show that SCFL learns a better model within the given time and achieves a better privacy-performance tradeoff than the baseline methods. In addition, the proposed incentive mechanism grants better training performance than the conventional Stackelberg game approach.

Most existing studies on joint activity detection and channel estimation for grant-free massive random access (RA) systems assume perfect synchronization among all active users, which is hard to achieve in practice. Therefore, this paper considers asynchronous grant-free massive RA systems and develops novel algorithms for joint user activity detection, synchronization delay detection, and channel estimation. In particular, the framework of orthogonal approximate message passing (OAMP) is first utilized to deal with the non-independent and identically distributed (i.i.d.) pilot matrix in asynchronous grant-free massive RA systems, and an OAMP-based algorithm capable of leveraging the common sparsity among the received pilot signals from multiple base station antennas is developed. To reduce the computational complexity, a memory AMP (MAMP)-based algorithm is further proposed that eliminates the matrix inversions in the OAMP-based algorithm. Simulation results demonstrate the effectiveness of the two proposed algorithms over the baseline methods. Besides, the MAMP-based algorithm reduces 37% of the computations while maintaining comparable detection/estimation accuracy, compared with the OAMP-based algorithm.

In the massive machine-type communication (mMTC) scenario, a large number of devices with sporadic traffic need to access the network on limited radio resources. Recently, grant-free random access has emerged as a promising mechanism for this challenging scenario, but its potential has not been fully unleashed. In particular, the available auxiliary information has not been fully exploited, including the common sparsity pattern in the received pilot and data signal, as well as the channel decoding information. This article develops advanced receivers in a holistic manner to improve the massive access performance by jointly designing activity detection, channel estimation, and data decoding. To tackle the algorithmic and computational challenges, a turbo structure is adopted at the joint receiver. For performance enhancement, all the received symbols are utilized to jointly estimate the channel state, user activity, and soft data symbols, which effectively exploits the common sparsity pattern. Meanwhile, the extrinsic information from the channel decoder will assist the joint channel estimation and data detection. To reduce the complexity, a low-cost side information (SI)-aided receiver is also proposed, where the channel decoder provides SI to update the estimates on whether a user is active or not. Simulation results show that the turbo receiver is able to reduce the activity detection, channel estimation, and data decoding errors effectively, supporting twice as many active users compared with a separate design that disregards the common sparsity. In addition, the SI-aided receiver notably outperforms the conventional methods with a relatively low complexity.

Federated edge learning (FEEL) emerges as a privacy-preserving paradigm to effectively train deep learning models from the distributed data in 6G networks. Nevertheless, the limited coverage of a single edge server results in an insufficient number of participating client nodes, which may impair the learning performance. In this paper, we investigate a novel FEEL framework, namelysemi-decentralized federated edge learning(SD-FEEL), where multiple edge servers collectively coordinate a large number of client nodes. By exploiting the low-latency communication among edge servers for efficient model sharing, SD-FEEL incorporates more training data, while enjoying lower latency compared with conventional federated learning. We detail the training algorithm for SD-FEEL with three steps, including local model update, intra-cluster, and inter-cluster model aggregations. The convergence of this algorithm is proved on non-independent and identically distributed data, which reveals the effects of key parameters and provides design guidelines. Meanwhile, the heterogeneity of edge devices may cause the straggler effect and deteriorate the convergence speed of SD-FEEL. To resolve this issue, we propose an asynchronous training algorithm with a staleness-aware aggregation scheme, of which, the convergence is also analyzed. The simulations demonstrate the effectiveness and efficiency of the proposed algorithms for SD-FEEL and corroborate our analysis.

This paper investigates task-oriented communication for multi-device cooperative edge inference, where a group of distributed low-end edge devices transmit the extracted features of local samples to a powerful edge server for inference. While cooperative edge inference can overcome the limited sensing capability of a single device, it substantially increases the communication overhead and may incur excessive latency. To enable low-latency cooperative inference, we propose a learning-based communication scheme that optimizes local feature extraction and distributed feature encoding in a task-oriented manner, i.e., to remove data redundancy and transmit information that is essential for the downstream inference task rather than reconstructing the data samples at the edge server. Specifically, we leverage Tishby’s information bottleneck (IB) principle (Tishby et al., 2000) to extract the task-relevant feature at each edge device, and adopt the distributed information bottleneck (DIB) framework of Aguerri and Zaidi, 2021, to formalize a single-letter characterization of the optimal rate-relevance tradeoff for distributed feature encoding. To admit flexible control of the communication overhead, we extend the DIB framework to a distributed deterministic information bottleneck (DDIB) objective that explicitly incorporates the representational costs of the encoded features. As the IB-based objectives are computationally prohibitive for high-dimensional data, we adopt variational approximations to make the optimization problems tractable. To compensate for the potential performance loss due to the variational approximations, we also develop a selective retransmission (SR) mechanism to identify the redundancy in the encoded features among multiple edge devices to attain additional communication overhead reduction. Extensive experiments on multi-view image classification and multi-view object recognition tasks evidence that the proposed task-oriented communication scheme achieves a better rate-relevance tradeoff than existing methods.

Grant-free massive random access (RA) is a promising protocol to support the massive machine-type communications (mMTC) scenario in 5G and beyond networks. In this paper, we focus on the error rate analysis in grant-free massive RA, which is critical for practical deployment but has not been well studied. We consider a two-phase frame structure, with a pilot transmission phase for activity detection and channel estimation, followed by a data transmission phase with coded data symbols. Considering the characteristics of short-packet transmission, we analyze the block error rate (BLER) in the finite blocklength regime to characterize the data transmission performance. The analysis involves characterizing the activity detection and channel estimation errors as well as applying the random matrix theory (RMT) to analyze the distribution of the post-processing signal-to-noise ratio (SNR). As a case study, the derived BLER expression is further simplified to optimize the pilot length. Simulation results verify our analysis and demonstrate its effectiveness in pilot length optimization.

Federated edge learning (FEEL) has drawn much attention as a privacy-preserving distributed learning framework for mobile edge networks. In this work, we investigate a novel semi-decentralized FEEL (SD-FEEL) architecture where multiple edge servers collaborate to incorporate more data from edge devices in training. Despite the low training latency enabled by fast edge aggregation, the device heterogeneity in computational resources deteriorates the efficiency. This paper proposes an asynchronous training algorithm to overcome this issue in SD-FEEL, where edge servers are allowed to independently set deadlines for the associated client nodes and trigger the model aggregation. To deal with different levels of model staleness, we design a staleness-aware aggregation scheme and analyze its convergence. Simulation results demonstrate the effectiveness of our proposed algorithm in achieving faster convergence and better learning performance than synchronous training.

Federated learning (FL) has attracted much attention as a privacy-preserving distributed machine learning framework, where many clients collaboratively train a machine learning model by exchanging model updates with a parameter server instead of sharing their raw data. Nevertheless, FL training suffers from slow convergence and unstable performance due to stragglers caused by the heterogeneous computational resources of clients and fluctuating communication rates. This paper proposes a coded FL framework to mitigate the straggler issue, namely stochastic coded federated learning (SCFL). In this framework, each client generates a privacy-preserving coded dataset by adding additive noise to the random linear combination of its local data. The server collects the coded datasets from all the clients to construct a composite dataset, which helps to compensate for the straggling effect. In the training process, the server as well as clients perform mini-batch stochastic gradient descent (SGD), and the server adds a make-up term in model aggregation to obtain unbiased gradient estimates. We characterize the privacy guarantee by the mutual information differential privacy (MI-DP) and analyze the convergence performance in federated learning. Besides, we demonstrate a privacy-performance tradeoff of the proposed SCFL method by analyzing the influence of the privacy constraint on the convergence rate. Finally, numerical experiments corroborate our analysis and show the benefits of SCFL in achieving fast convergence while preserving data privacy.

Federated edge learning (FEEL) has emerged as an effective approach to reduce the large communication latency in Cloud-based machine learning solutions, while preserving data privacy. Unfortunately, the learning performance of FEEL may be compromised due to limited training data in a single edge cluster. In this paper, we investigate a novel framework of FEEL, namely semi-decentralized federated edge learning (SD-FEEL). By allowing model aggregation across different edge clusters, SD-FEEL enjoys the benefit of FEEL in reducing the training latency, while improving the learning performance by accessing richer training data from multiple edge clusters. A training algorithm for SD-FEEL with three main procedures in each round is presented, including local model updates, intra-cluster and inter-cluster model aggregations, which is proved to converge on non-independent and identically distributed (non-IID) data. We also characterize the interplay between the network topology of the edge servers and the communication overhead of inter-cluster model aggregation on the training performance. Experiment results corroborate our analysis and demonstrate the effectiveness of SD-FFEL in achieving faster convergence than traditional federated learning architectures. Besides, guidelines on choosing critical hyper-parameters of the training algorithm are also provided.

This paper investigates task-oriented communication for edge inference, where a low-end edge device transmits the extracted feature vector of a local data sample to a powerful edge server for processing. It is critical to encode the data into aninformativeandcompactrepresentation for low-latency inference given the limited bandwidth. We propose a learning-based communication scheme that jointly optimizes feature extraction, source coding, and channel coding in a task-oriented manner, i.e., targeting the downstream inference task rather than data reconstruction. Specifically, we leverage an information bottleneck (IB) framework to formalize a rate-distortion tradeoff between the informativeness of the encoded feature and the inference performance. As the IB optimization is computationally prohibitive for the high-dimensional data, we adopt a variational approximation, namely the variational information bottleneck (VIB), to build a tractable upper bound. To reduce the communication overhead, we leverage a sparsity-inducing distribution as the variational prior for the VIB framework to sparsify the encoded feature vector. Furthermore, considering dynamic channel conditions in practical communication systems, we propose a variable-length feature encoding scheme based on dynamic neural networks to adaptively adjust the activated dimensions of the encoded feature to different channel conditions. Extensive experiments evidence that the proposed task-oriented communication system achieves a better rate-distortion tradeoff than baseline methods and significantly reduces the feature transmission latency in dynamic channel conditions.

Device-edge co-inference, which partitions a deep neural network between a resource-constrained mobile device and an edge server, recently emerges as a promising paradigm to support intelligent mobile applications. To accelerate the in-ference process, on-device model sparsification and intermediate feature compression are regarded as two prominent techniques. However, as the on-device model sparsity level and intermediate feature compression ratio have direct impacts on computation workload and communication overhead respectively, and both of them affect the inference accuracy, finding the optimal values of these hyper-parameters brings a major challenge due to the large search space. In this paper, we endeavor to develop an efficient algorithm to determine these hyper-parameters. By selecting a suitable model split point and a pair of encoder/decoder for the intermediate feature vector, this problem is casted as a sequential decision problem, for which, a novel automated machine learning (AutoML) framework is proposed based on deep reinforcement learning (DRL). Experiment results on an image classification task demonstrate the effectiveness of the proposed framework in achieving a better communication-computation trade-off and significant inference speedup against various baseline schemes.

The recent advancements of three-dimensional (3D) data acquisition devices have spurred a new breed of applications that rely on point cloud data processing. However, processing a large volume of point cloud data brings a significant workload on resource-constrained mobile devices, prohibiting from unleashing their full potentials. Built upon the emerging paradigm of device-edge co-inference, where an edge device extracts and transmits the intermediate feature to an edge server for further processing, we propose Branchy-GNN for efficient graph neural network (GNN) based point cloud processing by leveraging edge computing platforms. In order to reduce the on-device computational cost, the Branchy-GNN adds branch networks for early exiting. Besides, it employs learning-based joint source-channel coding (JSCC) for the intermediate feature compression to reduce the communication overhead. Our experimental results demonstrate that the proposed Branchy-GNN secures a significant latency reduction compared with several benchmark methods.

Massive machine-type communication (mMTC) has been regarded as one of the most important use scenarios in the fifth generation (5G) and beyond wireless networks, which demands scalable access for a large number of devices. While grant-free random access has emerged as a promising mechanism for massive access, its potential has not been fully unleashed. Particularly, the two key tasks in massive access systems, namely, user activity detection and data detection, were handled separately in most existing studies, which ignored the common sparsity pattern in the received pilot and data signal. Moreover, error detection and correction in the payload data provide additional mechanisms for performance improvement. In this paper, we propose a data-assisted activity detection framework, which aims at supporting more active users by reducing the activity detection error, consisting of false alarm and missed detection errors. Specifically, after an initial activity detection step based on the pilot symbols, the false alarm users are filtered by applying energy detection for the data symbols; once data symbols of some active users have been successfully decoded, their effect in activity detection will be resolved via successive pilot interference cancellation, which reduces the missed detection error. Simulation results show that the proposed algorithm effectively increases the activity detection accuracy, and it is able to support ∼20% more active users compared to a conventional method in some sample scenarios.

Data-driven approaches have recently emerged as promising remedies for communication system designs, which leverage deep learning techniques for automated development and optimization. In this paper, we revisit the designs of multi-input multi-output (MIMO) wireless systems and investigate the end-to-end learning for MIMO systems with temporal correlations. Our objective is to develop a MIMO transceiver to improve the communication performance by making fully use of the available temporal information. Although the end-to-end learning framework has been applied to various communication systems, existing designs largely rely on memoryless autoencoders (AEs) and overlook the time dependency. To overcome this issue, we propose a novel learning-based MIMO transceiver, namely, the TC-MIMONet, which extends the conventional memoryless AE-based transceivers by customizing two neural network components with memory. In particular, a long short-term memory (LSTM)-based CSI predictor is adopted at the transmitter, while a two-timescale LSTM-based decoder is developed for the receiver. Simulation results show that TC-MIMONet achieves significant block error rate reduction compared to two baseline schemes without utilizing the available temporal information.

To enhance the computation capability of mobile devices by offloading computation-demanding tasks to the nearby edge servers. In order to minimize the task latency and the device energy consumption, in this paper, we investigate the multi-objective resource allocation for multi-user MEC systems by adopting the system utility as the performance metric, which is a normalized weighted combination of the time and energy saving achieved by computation offloading. To provide an efficient solution, a low-complexity ranking-based algorithm is proposed based on the modified Newton method and the concept of computation offloading priority. Simulation results show that our proposed algorithm achieves a near-optimal performance and greatly outperforms a baseline algorithm with random spectrum allocation. In addition, it is demonstrated that jointly optimizing the spectrum and computational resource management policy is more critical when the number of MEC users is large.

Mobile-edge computing (MEC) has emerged as a prominent technique to provide mobile services with high computation requirement, by migrating the computation- intensive tasks from the mobile devices to the nearby MEC servers. To reduce the execution latency and device energy consumption, in this paper, we jointly optimize task offloading scheduling and transmit power allocation for MEC systems with multiple independent tasks. A low-complexity sub-optimal algorithm is proposed to minimize the weighted sum of the execution delay and device energy consumption based on alternating minimization. Specifically, given the transmit power allocation, the optimal task off loading scheduling, i.e., to determine the order of offloading, is obtained with the help of flow shop scheduling theory. Besides, the optimal transmit power allocation with a given task offloading scheduling decision will be determined using convex optimization techniques. Simulation results show that task offloading scheduling is more critical when the available radio and computational resources in MEC systems are relatively balanced. In addition, it is shown that the proposed algorithm achieves near-optimal execution delay along with a substantial device energy saving.

Mobile-edge computing (MEC) has recently emerged as a prominent technology to liberate mobile devices from computationally intensive workloads, by offloading them to the proximate MEC server. To make offloading effective, the radio and computational resources need to be dynamically managed, to cope with the time-varying computation demands and wireless fading channels. In this paper, we develop an online joint radio and computational resource management algorithm for multi-user MEC systems, with the objective of minimizing the long-term average weighted sum power consumption of the mobile devices and the MEC server, subject to a task buffer stability constraint. Specifically, at each time slot, the optimal CPU-cycle frequencies of the mobile devices are obtained in closed forms, and the optimal transmit power and bandwidth allocation for computation offloading are determined with the Gauss-Seidel method; while for the MEC server, both the optimal frequencies of the CPU cores and the optimal MEC server scheduling decision are derived in closed forms. Besides, a delay-improved mechanism is proposed to reduce the execution delay. Rigorous performance analysis is conducted for the proposed algorithm and its delay-improved version, indicating that the weighted sum power consumption and execution delay obey an [O (1/V) , O (V)] tradeoff with V as a control parameter. Simulation results are provided to validate the theoretical analysis and demonstrate the impacts of various parameters.

Mobile-edge computing (MEC) has recently emerged as a promising paradigm to liberate mobile devices from increasingly intensive computation workloads, as well as to improve the quality of computation experience. In this paper, we investigate the tradeoff between two critical but conflicting objectives in multi-user MEC systems, namely, the power consumption of mobile devices and the execution delay of computation tasks. A power consumption minimization problem with task buffer stability constraints is formulated to investigate the tradeoff, and an online algorithm that decides the local execution and computation offloading policy is developed based on Lyapunov optimization. Specifically, at each time slot, the optimal frequencies of the local CPUs are obtained in closed forms, while the optimal transmit power and bandwidth allocation for computation offloading are determined with the Gauss-Seidel method. Performance analysis is conducted for the proposed algorithm, which indicates that the power consumption and execution delay obeys an [0(1/V), 0(V)] tradeoff with V as a control parameter. Simulation results are provided to validate the theoretical analysis and demonstrate the impacts of various parameters to the system performance.

Mobile-edge computing (MEC) emerges as a promising paradigm to improve the quality of computation experience for mobile devices. Nevertheless, the design of computation task scheduling policies for MEC systems inevitably encounters a challenging two-timescale stochastic optimization problem. Specifically, in the larger timescale, whether to execute a task locally at the mobile device or to offload a task to the MEC server for cloud computing should be decided, while in the smaller timescale, the transmission policy for the task input data should adapt to the channel side information. In this paper, we adopt a Markov decision process approach to handle this problem, where the computation tasks are scheduled based on the queueing state of the task buffer, the execution state of the local processing unit, as well as the state of the transmission unit. By analyzing the average delay of each task and the average power consumption at the mobile device, we formulate a power-constrained delay minimization problem, and propose an efficient one-dimensional search algorithm to find the optimal task scheduling policy. Simulation results are provided to demonstrate the capability of the proposed optimal stochastic task scheduling policy in achieving a shorter average execution delay compared to the baseline policies.

Automatic repeat request (ARQ) is widely used in modern communication systems to improve transmission reliability. In conventional ARQ protocols developed for systems with energy-unconstrained receivers, an acknowledgement/negative-acknowledgement (ACK/NACK) message is fed back when decoding succeeds/fails. Such kind of non-adaptive feedback consumes significant amount of energy, and thus will limit the performance of systems with energy harvesting (EH) receivers. In order to overcome this limitation and to utilize the harvested energy more efficiently, we propose a novel ARQ protocol for EH receivers, where the ACK feedback can be adapted based upon the receiver's EH state. Two conventional ARQ protocols are also considered. By adopting the packet drop probability (PDP) as the performance metric, we formulate the throughput constrained PDP minimization problem for a communication link with a non-EH transmitter and an EH receiver. Optimal reception policies including the sampling, decoding and feedback strategies, are developed for different ARQ protocols. Simulation results will show that the proposed ARQ protocol not only outperforms the conventional ARQs in terms of PDP, but can also achieve a higher throughput.

Mobile-edge computing (MEC) is an emerging paradigm to meet the ever-increasing computation demands from mobile applications. By offloading the computationally intensive workloads to the MEC server, the quality of computation experience, e.g., the execution latency, could be greatly improved. Nevertheless, as the on-device battery capacities are limited, computation would be interrupted when the battery energy runs out. To provide satisfactory computation performance as well as achieving green computing, it is of significant importance to seek renewable energy sources to power mobile devices via energy harvesting (EH) technologies. In this paper, we will investigate a green MEC system with EH devices and develop an effective computation offloading strategy. The execution cost, which addresses both the execution latency and task failure, is adopted as the performance metric. A low-complexity online algorithm is proposed, namely, the Lyapunov optimization-based dynamic computation offloading algorithm, which jointly decides the offloading decision, the CPU-cycle frequencies for mobile execution, and the transmit power for computation offloading. A unique advantage of this algorithm is that the decisions depend only on the current system state without requiring distribution information of the computation task request, wireless channel, and EH processes. The implementation of the algorithm only requires to solve a deterministic problem in each time slot, for which the optimal solution can be obtained either in closed form or by bisection search. Moreover, the proposed algorithm is shown to be asymptotically optimal via rigorous analysis. Sample simulation results shall be presented to corroborate the theoretical analysis as well as validate the effectiveness of the proposed algorithm.

Hybrid energy supply (HES) wireless networks have recently emerged as a new paradigm to enable green networks, which are powered by both the electric grid and harvested renewable energy. In this paper, we will investigate two critical but conflicting design objectives of HES networks, i.e., the grid energy consumption and quality of service (QoS). Minimizing grid energy consumption by utilizing the harvested energy will make the network environmentally friendly, but the achievable QoS may be degraded due to the intermittent nature of energy harvesting. To investigate the tradeoff between these two aspects, we introduce the total service cost as the performance metric, which is the weighted sum of the grid energy cost and the QoS degradation cost. Base station assignment and power control is adopted as the main strategy to minimize the total service cost, while both cases with non-causal and causal side information are considered. With non-causal side information, a Greedy Assignment algorithm with low complexity and near-optimal performance is proposed. With causal side information, the design problem is formulated as a discrete Markov decision problem. Interesting solution structures are derived, which shall help to develop an efficient monotone backward induction algorithm. To further reduce complexity, a Look-Ahead policy and a Threshold-based Heuristic policy are also proposed. Simulation results shall validate the effectiveness of the proposed algorithms and demonstrate the unique grid energy consumption and QoS tradeoff in HES networks.

This paper addresses the joint base station (BS) assignment and power control problem in a hybrid energy supply wireless network, where an energy harvesting BS and a grid-powered BS coordinate to serve a mobile user. In order to minimize the grid energy consumption while maximizing the number of transmitted data packets, we introduce the total service cost over an N-block frame as the performance metric, which is the weighted sum of the grid energy cost and the packet drop cost. With non-causal side information (SI) available at the BSs, including energy SI and channel SI, a Greedy Assignment algorithm with low complexity and near optimal performance is proposed. For the causal SI setting, the design problem is formulated as a discrete Markov decision problem. Interesting solution structures are derived, which help develop an efficient monotone backward induction algorithm. To further reduce the complexity, a heuristic online policy is also proposed. Simulation results shall validate the effectiveness of the proposed policies and demonstrate a unique tradeoff in such networks, i.e., the tradeoff between the grid energy consumption and the provided quality of service.

Powering cellular networks with renewable energy sources via energy harvesting (EH) have recently been proposed as a promising solution for green networking. However, with intermittent and random energy arrivals, it is challenging to provide satisfactory quality of service (QoS) in EH networks. To enjoy the greenness brought by EH while overcoming the instability of the renewable energy sources, hybrid energy supply (HES) networks that are powered by both EH and the electric grid have emerged as a new paradigm for green communications. In this paper, we will propose new design methodologies for HES green cellular networks with the help of Lyapunov optimization techniques. The network service cost, which addresses both the grid energy consumption and achievable QoS, is adopted as the performance metric, and it is optimized via base station assignment and power control (BAPC). Our main contribution is a low-complexity online algorithm to minimize the long-term average network service cost, namely, the Lyapunov optimization-based BAPC (LBAPC) algorithm. One main advantage of this algorithm is that the decisions depend only on the instantaneous side information without requiring distribution information of channels and EH processes. To determine the network operation, we only need to solve a deterministic per-time slot problem, for which an efficient inner-outer optimization algorithm is proposed. Moreover, the proposed algorithm is shown to be asymptotically optimal via rigorous analysis. Finally, sample simulation results are presented to verify the theoretical analysis as well as validate the effectiveness of the proposed algorithm.

Energy harvesting (EH) has recently been attracting significant attention because of its ability to scavenge environmentally friendly energy. In this paper, we investigate the use of EH relay nodes to improve the quality of service (QoS) for relaying networks. To simplify the hardware design, we adopt a half-duplex selective decode-and-forward (SDF) relay. We propose a joint link selection and relay power allocation strategy to minimize the average outage probability. Both offline and online policies, i.e., with non-causal or causal side information about the energy state and the decoding result at the relay, are investigated by utilizing deterministic and stochastic dynamic programming (DP) algorithms, respectively. Furthermore, to reduce the complexity of the optimal online solution, we propose two low-complexity suboptimal online policies. Simulation results will show that the proposed suboptimal policies outperform the existing policies and achieve near optimal performance.

This paper addresses the optimal transmission scheduling problem in hybrid energy supply systems with the save-then-transmit protocol, where the energy supply of the transmitter comes from both the primary battery and the energy harvester. We first consider minimizing the outage probability for a given amount of battery energy by optimizing the saving factor. It is demonstrated that harvesting external energy is unnecessary for a large spectral efficiency requirement. Then, we consider joint packet scheduling and saving factor optimization to the battery energy consumption minimization (BECM) problem in both single packet arrival and burst packet arrival scenarios. Both optimal and suboptimal offline policies with full information on the traffic profile, the harvesting power, and the channel state are developed. We also propose an optimal online policy in the case that only causal information is available. Numerical results are presented that validate the effectiveness of the proposed algorithms.