Search

Sharing data across various Internet of Things (IoT) devices has been a common challenge due to efficiency, security, and stability issues. Blockchain, with security features, is considered to be a potential solution for data sharing in IoT settings. However, traditional blockchain-based solutions cannot satisfy the efficiency requirement of high-frequency data sharing among IoT devices. In this paper, we propose an efficient IoT data sharing approach by adopting the Payment Channel Network (PCN)-extended blockchain. Besides, we develop a homomorphic hashing-based transaction segmentation scheme to solve the issue of low transaction success ratio caused by channel deposit restrictions in PCN. In addition, a Multi-point Relay (MPR)-based multi-path routing scheme has been developed to ensure high-frequency transaction forwarding. The communication overhead of maintaining the routing table is reduced by our proposed Multi-point Relay Selection algorithm, and multiple alternate paths generated by Multiple Routing Path algorithm can improve the transaction success rate. Experiment evaluations have demonstrated that that our proposed approach outperforms the baseline approaches in terms of the transaction efficiency and success ratio. [ABSTRACT FROM AUTHOR]

To overcome the bottleneck of unreliable environment sensing caused by sensor failure and obstacle blockage, the cooperation among connected automated vehicles (CAVs) is crucial for the reliable and efficient raw sensing data sharing in order to guarantee the driving safety. Empowered by the narrow beamwidth and high data rate abilities, the millimeter wave (mmWave) communication technology can substantially improve the environment sensing ability among multiple CAVs. In this paper, a mmWave enabled CAVs cooperation algorithm is designed based on the proposed time-division integrated sensing and communication (TD-ISAC) system for raw sensing data sharing among CAVs. Considering various computing abilities at vehicle and infrastructure, a closed-form solution to the V2V or V2V/V2I cooperative communication mode selection is theoretically achieved based on response delay analysis to guarantee the timeliness of raw sensing data sharing. And the age of information based system status update algorithm is proposed for the V2V/V2I collaborative communication mode. The feasibility of the proposed TD-ISAC system is verified by simulation and hardware testbed results. Based on simulation results, the proposed communication mode selection algorithm can effectively minimize the response time delay in different conditions. The mmWave enabled TD-ISAC hardware testbed is developed and the position error of target detection can be reduced by 18.5 % using the sensing data fusion from two vehicles, while the communication throughput remains over 2.2 Gbps. [ABSTRACT FROM AUTHOR]

Massive machine-type communications (mMTC) are expected to support a large amount of randomly deployed users for short package transmissions. Noncoherent random access provides an efficient and practical multi-access protocol for mMTC, and also poses new challenges for the receiver design. In this paper, we leverage two well-known methods, i.e., message passing and deep learning, to jointly detect the user activity and the desired data for the noncoherent mMTC. First, by exploiting the exact distribution information of the received signal, a generalized approximate message passing (GAMP)-based algorithm is proposed, which is shown to jointly detect the user activity and the desired data by two modules: inter-user interference elimination and data detection for each user. Inspired by the two-module GAMP-based algorithm, we then propose a model-driven deep learning method, which utilizes the deep neural networks (DNNs) to approximate both the two modules. The loss function for training the DNNs is derived by formulating the two-module detection as an unconstrained optimization problem. Simulation results reveal that the proposed GAMP-based algorithm outperforms the proposed deep learning method when the channel distribution is perfectly known, while it suffers from a significant performance degradation for the case with imperfect channel distribution information. [ABSTRACT FROM AUTHOR]

In this work, we propose globally optimal power allocation strategies to maximize the users sum-rate (SR), and system energy efficiency (EE) in the downlink of single-cell multicarrier non-orthogonal multiple access (MC-NOMA) systems. Each NOMA cluster includes a set of users in which the well-known superposition coding (SC) combined with successive interference cancellation (SIC) technique is applied among them. By obtaining the closed-form expression of intra-cluster power allocation, we show that MC-NOMA can be equivalently transformed to a virtual orthogonal multiple access (OMA) system, where the effective channel gain of these virtual OMA users is obtained in closed-form. Then, the SR and EE maximization problems are solved by using very fast water-filling and Dinkelbach algorithms, respectively. The equivalent transformation of MC-NOMA to the virtual OMA system brings new theoretical insights, which are discussed throughout the paper. The extensions of our analyses to other scenarios, such as considering users rate fairness, admission control, long-term performance, and a number of future next-generation multiple access (NGMA) schemes enabling recent advanced technologies, e.g., reconfigurable intelligent surfaces are discussed. Extensive numerical results are provided to demonstrate the performance gaps among single-carrier NOMA (SC-NOMA), OMA-NOMA, and OMA. [ABSTRACT FROM AUTHOR]

Federated learning (FL) as a promising edge-learning framework can effectively address the latency and privacy issues by featuring distributed learning at the devices and model aggregation in the central server. In order to enable efficient wireless data aggregation, over-the-air computation (AirComp) has recently attracted great attention. However, fading of wireless channels can produce aggregate distortions in an AirComp-based FL scheme. In this paper, we propose a modified federated averaging (FedAvg) algorithm by introducing the local learning rates and present the convergence analysis. To combat the distortion, the local learning rate is optimized to adapt the fading channel, which is termed as dynamic learning rate (DLR). We begin our discussion by considering multiple-input-single-output (MISO) scenario, since the underlying optimization problem is convex and has a closed-form solution. Our studies are extended to a more general multiple-input-multiple-output (MIMO) case and an iterative method is derived. We also present the asymptotic analysis and give a near-optimal and closed-form receive beamforming solution when the number of antennas approaches infinity. Extensive simulation results demonstrate the effectiveness of the proposed DLR scheme in reducing the aggregate distortion and guaranteeing the testing accuracy on the MNIST and CIFAR10 datasets. In addition, the asymptotic analysis and the close-form solution are verified through numerical simulations. [ABSTRACT FROM AUTHOR]

The proliferation of Internet-of-Things (IoT) devices and cloud-computing applications over siloed data centers is motivating renewed interest in the collaborative training of a shared model by multiple individual clients via federated learning (FL). To improve the communication efficiency of FL implementations in wireless systems, recent works have proposed compression and dimension reduction mechanisms, along with digital and analog transmission schemes that account for channel noise, fading, and interference. The prior art has mainly focused on star topologies consisting of distributed clients and a central server. In contrast, this paper studies FL over wireless device-to-device (D2D) networks by providing theoretical insights into the performance of digital and analog implementations of decentralized stochastic gradient descent (DSGD). First, we introduce generic digital and analog wireless implementations of communication-efficient DSGD algorithms, leveraging random linear coding (RLC) for compression and over-the-air computation (AirComp) for simultaneous analog transmissions. Next, under the assumptions of convexity and connectivity, we provide convergence bounds for both implementations. The results demonstrate the dependence of the optimality gap on the connectivity and on the signal-to-noise ratio (SNR) levels in the network. The analysis is corroborated by experiments on an image-classification task. [ABSTRACT FROM AUTHOR]

Federated learning (FL) involves training machine learning models over distributed edge nodes (i.e., workers) while facing three critical challenges, edge heterogeneity, Non-IID data and communication resource constraint. In the synchronous FL, the parameter server has to wait for the slowest workers, leading to significant waiting time due to edge heterogeneity. Though asynchronous FL can well tackle the edge heterogeneity, it requires frequent model transfers, resulting in massive communication resource consumption. Moreover, the different relative frequency of workers participating in asynchronous updating may seriously hurt training accuracy, especially on Non-IID data. In this paper, we propose a semi-asynchronous federated learning mechanism (FedSA), where the parameter server aggregates a certain number of local models by their arrival order in each round. We theoretically analyze the quantitative relationship between the convergence bound of FedSA and different factors, e.g., the number of participating workers in each round, the degree of data Non-IID and edge heterogeneity. Based on the convergence bound, we present an efficient algorithm to determine the number of participating workers to minimize the training completion time. To further improve the training accuracy on Non-IID data, FedSA deploys adaptive learning rates for workers by their relative participation frequency. We extend our proposed mechanism to the dynamic and multiple learning tasks scenarios. Experimental results on the testbed show that our proposed mechanism and algorithms address the three challenges more effectively than the state-of-the-art solutions. [ABSTRACT FROM AUTHOR]

Federated learning has emerged as a popular technique for distributing machine learning (ML) model training across the wireless edge. In this paper, we propose two timescale hybrid federated learning (TT-HF), a semi-decentralized learning architecture that combines the conventional device-to-server communication paradigm for federated learning with device-to-device (D2D) communications for model training. In TT-HF, during each global aggregation interval, devices (i) perform multiple stochastic gradient descent iterations on their individual datasets, and (ii) aperiodically engage in consensus procedure of their model parameters through cooperative, distributed D2D communications within local clusters. With a new general definition of gradient diversity, we formally study the convergence behavior of TT-HF, resulting in new convergence bounds for distributed ML. We leverage our convergence bounds to develop an adaptive control algorithm that tunes the step size, D2D communication rounds, and global aggregation period of TT-HF over time to target a sublinear convergence rate of $\mathcal {O}(1/t)$ while minimizing network resource utilization. Our subsequent experiments demonstrate that TT-HF significantly outperforms the current art in federated learning in terms of model accuracy and/or network energy consumption in different scenarios where local device datasets exhibit statistical heterogeneity. Finally, our numerical evaluations demonstrate robustness against outages caused by fading channels, as well favorable performance with non-convex loss functions. [ABSTRACT FROM AUTHOR]

Beamforming and non-orthogonal multiple access (NOMA) serve as two potential solutions for achieving spectral efficient communication in the fifth generation and beyond wireless networks. In this paper, we jointly apply a hybrid beamforming and NOMA techniques to an unmanned aerial vehicle (UAV)-carried wireless-powered mobile edge computing (MEC) system, within which the UAV is equipped with a wireless power charger and the MEC platform delivers energy and computing services to Internet of Things (IoT) devices. Our aim is to maximize the sum computation rate at all IoT devices whilst satisfying the constraint of energy harvesting and coverage. The resultant optimization problem is non-convex involving joint optimization of the UAV’s 3D placement and hybrid beamforming matrices as well as computation resource allocation in both partial and binary offloading patterns, and thus is quite difficult to tackle directly. By applying the polyhedral annexation method and the deep deterministic policy gradient (DDPG) algorithm, we develop an effective algorithm to derive the closed-form solution for the optimal 3D deployment of the UAV, and find the solution for the hybrid beamformer. Two resource allocation algorithms for partial and binary offloading patterns are thereby proposed. Simulation results verify that our designed algorithms achieve a significant computation performance enhancement as compared to the benchmark schemes. [ABSTRACT FROM AUTHOR]

Due to line-of-sight communication links and distributed deployment, Unmanned Aerial Vehicles (UAVs) have attracted substantial interest in agile Mobile Edge Computing (MEC) service provision. In this paper, by clustering multiple users into independent communities based on their geographic locations, we design a 5G-enabled UAV-to-community offloading system. A system throughput maximization problem is formulated, subjected to the transmission rate, atomicity of tasks and speed of UAVs. By relaxing the transmission rate constraint, the mixed integer non-linear program is transformed into two subproblems. We first develop an average throughput maximization-based auction algorithm to determine the trajectory of UAVs, where a community-based latency approximation algorithm is developed to regulate the designed auction bidding. Then, a dynamic task admission algorithm is proposed to solve the task scheduling subproblem within one community. Performance analyses demonstrate that our designed auction bidding can guarantee user truthfulness, and can be fulfilled in polynomial time. Extensive simulations based on real-world data in health monitoring and online YouTube video services show that our proposed algorithm is able to maximize the system throughput while guaranteeing the fraction of served users. [ABSTRACT FROM AUTHOR]

In this paper, we investigate the resource and interference management problem in a novel scenario where multiple unmanned aerial vehicle base stations (UAV-BSs) provide cellular services to UAV users (UAV-UEs) by reusing both licensed and unlicensed spectrum. Considering the co-existence of terrestrial cellular, WiFi and UAV-BSs, a joint optimization problem is formulated for both subchannel allocation and power control of UAV-UEs over the licensed/unlicensed spectrum in order to maximize the uplink sum-rate of the multi-cell UAV-cellular network. Since the formulated problem is NP-hard, we decompose it into three sub-problems. Specifically, we first use the convex optimization and the Hungarian algorithm to obtain the global optimal of power and subchannel allocations in the licensed spectrum, respectively. Then, we propose a matching game with externalities and coalition game algorithms to obtain the Nash stable of the subchannel allocation in the unlicensed band. Local optimal power assignment in the unlicensed spectrum is obtained using the successive convex approximation (SCA) method. An iterative algorithm is thereby developed to solve the three sub-problems sequentially till reaching convergence. Simulation results show that the proposed algorithm can improve the network capacity by nearly two times than the Long Term Evolution-Advanced (LTE-A). [ABSTRACT FROM AUTHOR]

This paper investigates a dual-unmanned aerial vehicle (UAV)-enabled secure communication system, in which, a UAV moves around to send confidential messages to a mobile user while another cooperative UAV transmits artificial noise signals to confuse malicious eavesdroppers. Both UAVs have energy constraints and the location information of eavesdroppers is imperfect. We consider a worst-case secrecy rate maximization problem of the mobile user over all time slots. This optimization problem is solved by jointly designing the three-dimensional (3D) trajectory of UAVs and the time allocation (recharging and service or jamming) under practical constraints including maximum UAV speed, UAV collision avoidance, UAV positioning error, and UAV energy harvesting. Specifically, we adopt a more practical UAV-ground channel model with both large-scale and small-scale fading components. Due to the non-convex feasible region constructed by the complicated constraints, directly finding the optimal solution of the original problem is intractable. To address this issue, we decouple the original optimization problem into three subproblems and develop an iterative algorithm to find its suboptimal solution by using the block coordinate descent technique. To solve each subproblem, certain advanced optimization tools, such as integer relaxation, S-procedure, and successive convex approximation techniques, are utilized. Numerical simulation results are provided to corroborate the theoretical derivations and to evaluate the performance of the proposed algorithm. Additionally, the numerical results assist to draw new insights on the 3D UAV trajectory by comparing the performance with conventional two-dimensional (2D) schemes. [ABSTRACT FROM AUTHOR]

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

Unmanned aerial vehicle (UAV) technology is recognized as a promising solution to area coverage problems (ACPs) and has been extensively studied recently. In this paper, we study the 3D irregular terrain surface coverage problem with a hierarchical UAV swarm. We first build the 3D model of a random irregular terrain and propose a geometric way to project the 3D terrain surface into many weighted 2D patches. Then we develop a two-level hierarchical UAV swarm architecture, including the low-level follower UAVs (FUAVs) and the high-level leader UAVs (LUAVs). For FUAVs, we design a coverage trajectory algorithm to carry out specific coverage tasks within patches based on the star communication topology. For LUAVs, we propose a swarm deep Q-learning (SDQN) reinforcement learning algorithm to select patches. Moreover, an observation history model based on convolutional neural networks (CNNs) and the mean embedding method is integrated into SDQN to address the communication limitation problems of LUAVs. The numerical results show that FUAVs can cover the entire area of each patch with little redundancies, and the total coverage time of the SDQN is less than that of existing methods, which demonstrates the effectiveness of the proposed algorithms. [ABSTRACT FROM AUTHOR]

In next-generation wireless networks, high-mobility unmanned aerial vehicles (UAVs) are promising to provide content coverage, where users can receive sufficient requested content within a given time. However, trajectory planning for multiple UAVs to provide content coverage is challenging since 1) UAVs cannot provide content coverage for all users due to the limited energy and caching storage, and 2) the trajectory planning of UAV is coupled with each other. Moreover, the complete information based trajectory planning methods are unusable since UAVs cannot obtain prior information on the rapidly changing environment. In this paper, we investigate the multi-UAV trajectory planning for energy-efficient content coverage. We first formulate an energy efficiency maximization problem considering recharging scheduling, which aims to reduce the total length of trajectories of UAVs under the quality of service (QoS) constraints. To settle environment uncertainty, the trajectory planning problem is modeled as two coupled multi-agent stochastic games, whose equilibrium constitute the optimal trajectory. To obtain the equilibrium, we propose a decentralized reinforcement learning algorithm, which can decouple the two games. We prove that the proposed algorithm can converge to the optimal solution of the Bellman equation with a higher rate compared to the centralized one. Moreover, simulation results show that the energy efficiency of the proposed algorithm is smaller than 5% compared the optimal, which is obtained with the prior information of environments. [ABSTRACT FROM AUTHOR]

Unmanned aerial vehicles (UAVs) are capable of serving as flying base stations (BSs) for supporting data collection, machine learning (ML) model training, and wireless communications. However, due to the privacy concerns of devices and limited computation or communication resource of UAVs, it is impractical to send raw data of devices to UAV servers for model training. Moreover, due to the dynamic channel condition and heterogeneous computing capacity of devices in UAV-enabled networks, the reliability and efficiency of data sharing require to be further improved. In this paper, we develop an asynchronous federated learning (AFL) framework for multi-UAV-enabled networks, which can provide asynchronous distributed computing by enabling model training locally without transmitting raw sensitive data to UAV servers. The device selection strategy is also introduced into the AFL framework to keep the low-quality devices from affecting the learning efficiency and accuracy. Moreover, we propose an asynchronous advantage actor-critic (A3C) based joint device selection, UAVs placement, and resource management algorithm to enhance the federated convergence speed and accuracy. Simulation results demonstrate that our proposed framework and algorithm achieve higher learning accuracy and faster federated execution time compared to other existing solutions. [ABSTRACT FROM AUTHOR]

Mobile edge computing (MEC) has emerged as one of the key technical aspects of the fifth-generation (5G) networks. The integration of MEC with resource-constrained unmanned aerial vehicles (UAVs) greatly enables flexible resource provisioning for supporting dynamic and computation-intensive UAV applications. Existing resource trading could facilitate this paradigm with proper incentives, which, however, may often incur unexpected negotiation latency and energy consumption, trading failures and unfair pricing, due to the unpredictable nature of the resource trading process. Motivated by these challenges, an efficient futures-enabled resource trading mechanism for edge computing-assisted UAV network is proposed, where a mutually beneficial and risk-tolerable forward contract is devised to promote resource trading between an MEC server (seller) and a UAV (buyer) with multiple tasks. Two key problems i.e. futures contract design before trading, and transmission power optimization during trading are studied. By analyzing historical statistics associated with future resource supply, demand, and air-to-ground communication quality, the contract design is formulated as a multi-objective optimization problem aiming to maximize both the seller’s and the buyer’s expected utilities, while estimating their acceptable risk tolerance. Accordingly, we propose an efficient bilateral negotiation scheme to help players reach a trading consensus on the amount of resources and the relevant price. For the power optimization problem, we develop a practical algorithm that enables the buyer to determine its optimal transmission power via convex optimization techniques. Comprehensive simulations demonstrate that the proposed mechanism offers mutually beneficial utilities to players, while achieving commendable performance on trading failures and fairness, negotiation latency and cost, comparing with baseline methods. [ABSTRACT FROM AUTHOR]

A UAV-aided wireless power transfer and data collection network is studied, where it is assumed that when the harvested energy at the sensor node (SN) cannot surpass its circuit activation threshold or the received data rate at UAV falls below a minimal required rate threshold, the information outage occurs. The closed-form expressions of energy outage probability and rate outage probability are derived at first, and then the overall outage probability and coverage performance of the system are analyzed. Based on which, an optimization problem is formulated to minimize the overall outage probability by optimizing UAV’s elevation angle and the time splitting (TS) factor. Since the problem is non-convex and has no known solution, an alternating optimization (AO)-based algorithm with Golden-section (GS) based linear search method is designed to find the global optimal solution. In order to explore the maximum coverage area of the UAV for a given tolerable outage probability, another optimization problem is also formulated to maximize the coverage range by optimizing UAV’s elevation angle. By using Karush-Kuhn-Tucker (KKT) conditions, the closed-form solution of the optimal elevation angle for maximizing the coverage area is derived. Monte Carlo simulations verify the accuracy of the derived closed-form expression of the overall outage probability and the semi-closed-form expressions of the optimum UAV’s elevation angle and TS factor. It shows that there exist a unique optimum elevation angle and the TS factor to achieve the minimum overall outage probability, and significant performance gain can be obtained by using our proposed optimization scheme. The developed theoretical results can be useful to the design of UAV-aided wireless communication systems with wireless power transfer. [ABSTRACT FROM AUTHOR]

Internet adaptive video streaming is a typical form of video delivery that leverages adaptive bitrate (ABR) algorithms to provide video services with high quality of experience (QoE) for various users in diverse and unique network conditions. Such heterogeneous network environments, which can be viewed as exogenous input processes, often lead to the unstable performance of ABR algorithms. Unfortunately, learning-based ABR algorithm which generated by state-of-the-art reinforcement learning (RL) technologies achieves good average performance but fails to perform well in all kinds of network conditions. In this work, considering the video playback process as the Input-driven Markov Decision Process (IMDP), we propose $\text{A}^{2}$ BR (Adaptation of ABR), a novel meta-RL ABR approach. $\text{A}^{2}$ BR is mainly composed of an online stage and an offline stage. It leverages meta-RL to learn an initial meta-policy with various network conditions at the offline stage and makes decisions in personalized network conditions at the online stage. At the same time, we continually optimize the meta-policy to the tailor-made ABR policy for varying the current network environment within few shots. Moreover, in order to improve the learning efficiency, we fully utilize domain knowledge for implementing a virtual player to replay the previously experienced network. Using trace-driven experiments on various scenarios including different vehicles, users, network types, and heterogeneous user-preferences, we show that $\text{A}^{2}$ BR outperforming recent ABR approaches with rapidly adapting to the personalized QoE metrics and specific network conditions. Testbed experimental results also illustrate the superiority of $\text{A}^{2}$ BR in adapting to the unseen environments. [ABSTRACT FROM AUTHOR]

We propose novel sparse-graph-based transmission schemes and receiver algorithms for unsourced multiple access (UMA) in MIMO channels. The channel coherence interval is divided into a number of sub-slots and each active transmitter selects certain sub-slots to repeatedly transmit its codeword according to a sparse Tanner graph. We propose iterative receiver algorithms that at each iteration decode either a single codeword, or two or three codewords jointly, and then subtract the decoded codewords from received signals during all sub-slots. The keys to these decoders are novel blind channel estimation algorithms when the received signal contains one, two, or three codewords. We perform density evolution analysis on the proposed UMA systems to obtain the asymptotic upper bounds on the maximum achievable rates for different decoders under both regular and irregular Tanner graphs. Extensive simulation results are provided to illustrate the performance of the proposed UMA systems, and its advantages over existing compressed-sensing (CS)-based UMA schemes. [ABSTRACT FROM AUTHOR]

A reconfigurable intelligent surface (RIS) aided air-to-ground uplink non-orthogonal transmission framework is investigated for next generation multiple access. Occupying the same spectrum resource, unmanned aerial vehicle (UAV) users and ground users (GUs) are connected to terrestrial cellular networks via the uplink non-orthogonal multiple access (NOMA) protocol. As the flight safety is important for employing UAVs in civil airspace, the collision avoidance mechanism has to be considered during the flight. Therefore, a joint optimization problem of the UAV trajectory design, RIS configuration, and uploading power control is formulated for maximizing the network sum rate, while ensuring the UAV’s fight safety and satisfying the minimum data rate requirements of both the UAV and GU. The resultant problem is a sequential decision making one across multiple coherent time slots. Besides, the unknown locations of obstacles bring uncertainties into the decision making process. To tackle this challenging problem, a sample-efficient deep reinforcement learning (DRL) algorithm is proposed to optimize the UAV trajectory, RIS configuration, and power control simultaneously. Moreover, considering the ambiguous uncertainties in the environment, a distributionally robust DRL algorithm is further proposed to provide the worst-case performance guarantee. Numerical results demonstrate that the two proposed DRL algorithms outperform the conventional ones in terms of learning efficiency and robustness. It is also shown that the network sum rate is significantly improved by the proposed RIS-NOMA scheme compared to the conventional RIS-orthogonal multiple access (OMA) scheme and the case where no RIS is deployed. [ABSTRACT FROM AUTHOR]

Federated learning enables machine learning algorithms to be trained over decentralized edge devices without requiring the exchange of local datasets. Successfully deploying federated learning requires ensuring that agents (e.g., mobile devices) faithfully execute the intended algorithm, which has been largely overlooked in the literature. In this study, we first use risk bounds to analyze how the key feature of federated learning, unbalanced and non-i.i.d. data, affects agents’ incentives to voluntarily participate and obediently follow traditional federated learning algorithms. To be more specific, our analysis reveals that agents with less typical data distributions and relatively more samples are more likely to opt out of or tamper with federated learning algorithms. To this end, we formulate the first faithful implementation problem of federated learning and design two faithful federated learning mechanisms which satisfy economic properties, scalability, and privacy. First, we design a Faithful Federated Learning (FFL) mechanism which approximates the Vickrey–Clarke–Groves (VCG) payments via an incremental computation. We show that it achieves (probably approximate) optimality, faithful implementation, voluntary participation, and some other economic properties (such as budget balance). Further, the time complexity in the number of agents $K$ is $\mathcal {O}(\log (K))$. Second, by partitioning agents into several clusters, we present a scalable VCG mechanism approximation. We further design a scalable and Differentially Private FFL (DP-FFL) mechanism, the first differentially private faithful mechanism, that maintains the economic properties. Our DP-FFL mechanism enables one to make three-way performance tradeoffs among privacy, the iterations needed, and payment accuracy loss. [ABSTRACT FROM AUTHOR]

In this work, we investigate an unmanned aerial vehicle (UAV)-enabled wireless power transfer (WPT) network with multiple ground sensor nodes (SNs). A UAV is operated at a fixed altitude with a directional antenna array and is designed to wirelessly transfer energy to the SNs. We consider a non-linear energy harvesting (EH) model and a directional antenna structure of uniform linear array (ULA) where we apply an analog directional beamforming scheme. Taking the fairness issue into account, we consider a problem aiming at maximizing the minimum harvested energy among all SNs during a fixed time period by jointly optimizing the UAV trajectory and the orientation of the directional antenna on the UAV. However, the complex antenna pattern expression of analog directional beamforming and the implicit non-linear function in the EH model introduce significant difficulties in handling the non-convex problem of the joint design. To tackle these difficulties, we propose and adopt a modified approximate antenna pattern model, i.e., a modified cosine antenna pattern, and reformulate the original problem via quantizing the UAV trajectory in the time domain. Later, by employing a convex property in the EH model and a proved lemma, we successfully construct a tight convex approximation for the reformulated problem, based on which the problem can be solved via a proposed iterative algorithm and the objective converges to an efficient suboptimal solution. Finally, we provide numerical results to confirm the convergence of the proposed algorithm, examine the approximation error and evaluate the system performance. The results show the performance advantage of the directional antenna in UAV-enabled WPT networks than the omni-directional antenna case, and illustrate how the directional antenna of the UAV overcomes its coverage limitation [ABSTRACT FROM AUTHOR]

Intelligent reflecting surface (IRS) enhanced multi-unmanned aerial vehicle (UAV) non-orthogonal multiple access (NOMA) networks are investigated. A new transmission framework is proposed, where multiple UAV-mounted base stations employ NOMA to serve multiple groups of ground users with the aid of an IRS. The three-dimensional (3D) placement and transmit power of UAVs, the reflection matrix of the IRS, and the NOMA decoding orders among users are jointly optimized for maximization of the sum rate of considered networks. To tackle the formulated mixed-integer non-convex optimization problem with coupled variables, a block coordinate descent (BCD)-based iterative algorithm is developed. Specifically, the original problem is decomposed into three subproblems, which are alternately solved by exploiting the penalty-based method and the successive convex approximation technique. The proposed BCD-based algorithm is demonstrated to be able to obtain a stationary point of the original problem with polynomial time complexity. Numerical results show that: 1) the proposed NOMA-IRS scheme for multi-UAV networks achieves a higher sum rate compared to the benchmark schemes, i.e., orthogonal multiple access (OMA)-IRS and NOMA without IRS; 2) the use of IRS is capable of providing performance gain for multi-UAV networks by both enhancing channel qualities of UAVs to their served users and mitigating the inter-UAV interference; and 3) optimizing the UAV placement can make the sum rate gain brought by NOMA more distinct due to the flexible decoding order design. [ABSTRACT FROM AUTHOR]