Federated learning (FL) facilitates privacy-preserving collaborative intelligence, making it ideal for mobile edge computing (MEC)-enabled Industrial Internet of Thing (IIoT). However, the autonomy of participants leads to unstable edge associations, hampering FL deployment. Existing studies typically prioritize device incentives but overlook price competition and network congestion at the server level. To tackle these issues, we propose coMpetition sOftening and coNgestion mItigation (MONI), a communication-efficient incentive mechanism for service pricing. Specifically, MONI employs a dynamic multiteam Bertrand game model to capture boundedly rational interactions among edge servers. It leverages capacity constraints to alleviate price competition and mitigate network congestion, while preserving the uniform stability of the game. Furthermore, MONI incorporates a genetic algorithm augmented with a truncated Gaussian distribution to minimize the disconnection of roaming devices. Experiments on synthetic and real-world industrial datasets demonstrate that MONI reduces recruitment costs and network congestion, increases the number of devices by 18.37%, and boosts model performance by up to 6.39% compared to state-of-the-art benchmarks.

Mobile edge computing (MEC) has recently gained significant attention as a promising solution for processing delay sensitive and resource-intensive computational jobs. Existing system schedulers in MEC networks typically assume homogeneous service providers, uniformly distributed user equipment (UE), and identical service requirements, making them unsuitable for practical MEC scenarios where jobs are randomly generated with varying service and completion time requirements. Thus, in this work, we jointly optimize job scheduling and resource allocation in a heterogeneous multi-unmanned aerial vehicle (UAV) enabled MEC network, considering practical factors such as diverse service requirements of jobs, unknown distribution of UEs, and spatial-temporal job arrivals. We aim to reduce the overall job miss rate and the average energy consumption of both UAVs and UEs by jointly planning safe UAV trajectories and onboard resource allocation. To learn uncertain and dynamic UE-side states (e.g., job arrivals and mobility patterns) and ensure the UAV's safety during the flight, we propose a multi-agent safe reinforcement learning algorithm that combines a Shared Soft Actor-Critic architecture for extracting features of heterogeneous UAVs and a two-agent Markov Game of Intervention mechanism for collision avoidance, named SSAC-MGI. In particular, SSAC MGI further incorporates a fine-grained resource allocation scheme to improve onboard resource utilization and reduce job miss rate. Extensive real trace-driven simulations based on Alibaba cluster data validate the effectiveness and superiority of SSAC-MGI, compared with several state-of-the-art algorithms.

Mobile edge computing (MEC) is promising in handling delay-sensitive or resource-intensive tasks in mobile internet. Existing system schedulers in MEC networks usually schedule all service providers in a synchronous manner, which may not suit the practical scenario where tasks are randomly generated and require different computational resources and service times. In this work, we jointly optimize the task scheduling and resource allocation in an unmanned aerial vehicle (UAV)-enabled MEC network, where multiple UAVs asynchronously and cooperatively deliver task offloading and computing services to edge devices (EDs), for maximizing the average per-UAV energy utility and minimizing the overall task missing ratio. To enhance scheduling efficiency and jointly optimize task scheduling and resource allocation, we develop an asynchronous layered multi-agent proximal policy optimization (AL-MAPPO) algorithm, by incorporating the multi-UAV asynchronous action execution mechanism and a discrete-continuous layered action space into the general MAPPO framework. AL-MAPPO enables each UAV to perform flexible task scheduling and fine-grained resource allocation asynchronously. Extensive trace-driven simulations based on Alibaba Cluster Data V2017 validate the effectiveness of AL-MAPPO, compared with several baseline algorithms.

Federated Learning (FL) mitigates privacy leakage in decentralized machine learning by allowing multiple clients to train collaboratively locally. However, dynamic mobile networks with high mobility, intermittent connectivity, and bandwidth limitation severely hinder model updates to the cloud server. Although previous studies have typically addressed user mobility issue through task reassignment or predictive modeling, frequent migrations may result in high communication overhead. Addressing this challenge involves not only dealing with resource constraints, but also finding ways to mitigate the challenges posed by user migrations. We therefore propose a intertemporal incentive framework, FedCross, which ensures the continuity of FL tasks by migrating interrupted training tasks to feasible mobile devices. FedCross comprises two distinct stages: Specifically, in Stage 1, we address the task allocation problem across regions under resource constraints by employing a multi-objective migration algorithm to quantify the optimal task receivers. Moreover, we adopt evolutionary game theory to capture the dynamic decision-making of users, forecasting the evolution of user proportions across different regions to mitigate frequent migrations. In Stage 2, we utilize a procurement auction mechanism to allocate rewards among base stations, ensuring that those providing high-quality models receive optimal compensation. This approach incentivizes sustained user participation, thereby ensuring the overall feasibility of FedCross. Finally, experimental results validate the theoretical soundness of FedCross and demonstrate its significant reduction in communication overhead.

Mobile chargers (MCs) have been widely used in wireless rechargeable sensor networks (WRSNs) to deliver energy to sensor nodes. This paper concerns the fundamental problem of dispatching the minimum number of MCs to charge nodes within a large-scale WRSN, i.e., given a set of rechargeable nodes, we aim to minimize the total number of dispatched MCs by appropriately designing the charging path of each dispatched MC, such that the charging demand of each node is satisfied. Due to its complexity, we solve this problem by first dividing it into two subproblems, i.e., charging points selection and charging paths design, which are both NP-hard. Then, we propose a computational geometry-based two-step heuristic algorithm to solve the two subproblems respectively. In the first step, we develop a peeling-off searching algorithm (POSA) to determine the charging points where MCs can stop to charge nodes within their charging ranges, by jointly considering the charging efficiency and moving distance. In the second step, we gradually assign the determined charging points to each dispatched MC while constructing the corresponding charging path. During the path construction, we first generate a shortest closed tour connecting all the currently assigned charging points and then use a break-and-tie method to insert the depot to form the charging path. Extensive evaluations validate the superiority of our proposed algorithm, compared with some other algorithms.

With the rise of federated learning (FL) in the realm of machine learning for data privacy protection, its unique distributed data processing characteristics have garnered widespread attention. However, the implementation of FL faces many challenges, as achieving a balance between data privacy, model security, and system efficiency is difficult, often requiring the sacrifice of efficiency for privacy and security. Moreover, this process typically assumes the existence of a trusted server for coordination. Addressing these challenges, this article proposes a privacy-preserved and efficient FL framework with blockchain (PEFL). PEFL utilizes blockchain and differential privacy techniques to coordinate privacy protection among clients, and filters out anomalous model parameters through an aggregation-side detection algorithm to resist poisoning attacks. Under the assumption of an untrusted server, we design the model-validated fault-tolerant federation (MFF) consensus mechanism based on a committee, balancing efficiency expectations to regulate the server and ensure the reliability of the training process. Through experiments on the MNIST and CIFAR10 datasets, and comparison with typical FL schemes, PEFL demonstrates better defense against various attack models. Besides, it achieves higher training efficiency while ensuring privacy security.

Federated edge learning (FEL) enables Industrial Internet of Things (IIoT) devices to collaboratively train machine learning models without exposing their local data. However, insecure communication environments pose significant threats to the security of model transmission in FEL. Signcryption, as a novel cryptographic primitive, can provide confidentiality, integrity, and other security guarantees for model transmission. Nevertheless, most existing signcryption schemes are designed for a single recipient and therefore cannot meet the multi-recipient requirements of FEL. Additionally, these schemes lack mechanisms for revoking signcryption privileges, which allows malicious edge nodes to continue participating in model transmission and disrupt the training of the global model. To address these challenges, this paper proposes the Lightweight and Efficient Signcryption for Federated Edge Learning in IIoT (LES), which achieves efficient one-to-many signcryption by leveraging bilinear pairings and Lagrange interpolation. LES balances computational and communication overhead while ensuring security. Moreover, the LES scheme incorporates blockchain technology and the Chinese Remainder Theorem to enable revocation of signcryption privileges, preventing compromised edge nodes from continuing to engage in model transmission. Formal security proofs of the LES scheme are provided. A comprehensive comparison between LES and eight representative signcryption schemes proposed in recent years highlights the feasibility of LES and its clear advantages in terms of computational and communication overhead. Under partial participation, LES achieves at least a 29.1% reduction in computational cost and an 81.8% reduction in communication cost compared with the most efficient single recipient scheme among the eight evaluated.

Although promising, federated edge learning (FEL) is being plagued by unreliable clients with low-quality parameters due to tight edge association and frequent edge aggregation. Existing efforts mainly focus on setting thresholds or identifying malicious behaviors to resist unreliable clients, which comes at the cost of losing their training samples and leads to unsustainable and collaborative inefficiencies. To tackle this issue, we propose the first sustainable contract, named FedSC, which allows for sustaining truthful contributions in more general conditions including clients’ multidimensional attributes and imperfect system monitoring. Specifically, by modeling the long-term strategic behaviors of self-interested clients as a Markov decision process, we quantify the impact of client behavior on their utilities and derive the critical conditions that make the rating-based contract sustainable, thereby promoting honest participation as the optimal choice for strategic clients. Since directly deriving the optimal design of FedSC under multiple constraints and nonlinear coupling of parameters is intractable, we characterize the impact of design parameters on objective function and analytically prove the existence of closed solution. Then, through a low-time-complexity greedy-based algorithm, the optimality of sustainable contracts under different system errors is guaranteed. Extensive experiments using both synthetic and real datasets demonstrate the effectiveness and superiority of FedSC compared to the state-of-the-art baselines. Excitingly, FedSC can reduce the number of free-riders up to 34.52% and improve the amount of contributed data and model performance up to 22.98% and 8.62%, respectively.

Although Federated Learning (FL) offers significant potential for developing model marketplaces through collaborative training and privacy preservation, challenges such as insufficient training data and arbitrage issues severely impede the development of FL-based model marketplaces. Existing studies either lack satisfactory security guarantees or are too profit-driven to address potential arbitrage issues. In this paper, we propose a novel Personalized prIvacy-prEserving inCentive mEchanism named PIECE, with the aim of achieving social optimality while avoiding arbitrage. Specifically, we first formulate a dual-objective optimization problem to simultaneously maximize social utility and model performance while ensuring arbitrage-free conditions through differential privacy. Due to dynamic model training and heterogeneous privacy budgets that complicate the design of arbitrage-free properties, we model the transformation between local and global privacy requirements across scenarios as a privacy choice game. This game guarantees the identification of a constraint to generate desired model versions based on Nash equilibrium. Next, by generalizing the properties of different data-owner groups under equilibrium conditions, we prove that the dual-objective optimization problem is always conflict-free, thus allowing transformation into a social optimal problem without arbitrage. Furthermore, to tackle the significant difficulty in characterizing the model revenue and interpolating pricing, we propose a two-stage solution based on subadditivity relaxation. The first stage establishes a set of ideal prices as the target, while the second stage establishes polynomial-time solvability and provides rigorous arbitrage-free boundaries. Finally, comprehensive experiments on four real-world datasets validate the efficacy of PIECE. The results indicate a minimum 8% boost in model revenue within the specified marketplace scale, and a maximum 16.67% improvement in model performance compared to the state-of-the-art baselines.

Consensus mechanism is the foundational protocol for achieving distributed consistency among replicas in a blockchain network. A well-designed consensus mechanism needs to balance performance such as complexity, consensus mechanism initiative and dynamic adaptability. Based on Hot-Stuff (a BFT-like consensus with O(n) complexity), we propose a practical and robust consensus mechanism, namely Practical and Robust HotStuff, denoted as PRO-HotStuff. Firstly, PRO-HotStuff redesigns a pacemaker that simultaneously supports replica synchronization and quorum certificate caching, and thus achieves practical view change with O(n) communication complexity while avoiding the additional phase introduced by HotStuff. Secondly, PRO-HotStuff gives the leader election basis by introducing the theory of planed behavior (TPB) and a reputation mechanism. It facilitates restricting the malicious replicas while encouraging the trustworthy replicas, thus to enhance the robustness of PRO-HotStuff. Thirdly, the implementation design of PRO-HotStuff as well as its reconfiguration mechanism for dynamic adaptability is presented. Proofs of correctness of PRO-HotStuff are also provided. Finally, experiments demonstrate that compared to existing HotStuff-like consensus mechanisms, PRO-HotStuff has significant advantages in terms of consensus performance, security, and dynamic adaptability.

In this work, we study the problem of dispatching an unmanned aerial vehicle (UAV) for data collection of Internet of Things (IoT) devices, where a UAV departs from a data center, then visits some IoT devices for data collection and finally returns to the data center. Different from most existing works on UAV-enabled data collection, we assume that the UAV’s collection point, i.e., the location where the UAV stays during the data collection process, can be deployed anywhere within the communication range of each IoT device, rather than being assumed to be in a fixed position. This new assumption is motivated by the fact that the collection point has a great impact on both time and energy consumption of the UAV during its data collection tour. Thus, in this work, we focus on minimizing the UAV’s task completion time and energy consumption during a data collection tour, by jointly optimizing the UAV’s collection point for each IoT device, flight trajectory and flight speed. We formulate this problem as a multiobjective optimization problem, which is solved by executing the following three successive steps: 1) we first employ the ant colony optimization (ACO) algorithm to decide the UAV’s visiting order of all IoT devices; 2) we then reduce the searching space of the collection point for each visited IoT device by using geometric theory and reformulate the original problem; and 3) we finally develop an enhanced multiobjective particle swarm optimization (EMOPSO) algorithm by incorporating a novel gbest selection strategy to identify the optimal collection point for each visited IoT device, based on which the corresponding flight trajectory as well as the flight speed is calculated. We refer to the above three-step hybrid algorithm as ACO-EMOPSO-G. Extensive evaluations validate the superiority of ACO-EMOPSO-G in terms of the tradeoff between the UAV’s task completion time and energy consumption, compared with some other data collection approaches.

To realize carbon emission reduction, restricting regional carbon emissions while meeting electricity usage is a critical but not trivial problem. In this paper, we propose a game-based pricing scheme for joint carbon emission rights (CER) and electricity trading between the electricity prosumers within a microgrid. For modeling and theoretical analysis, we first introduce the utility functions of electricity producers and consumers, which are determined by CER and electricity prices in a coupled way. Then, the multi-leader multi-follower (MLMF) Stackelberg game and non-cooperative game are employed to formulate the electricity and CER pricing and trading, respectively. The game equilibriums convince that optimal prices for both electricity and CER exist to satisfy electricity usage while meeting the carbon emission restriction. For implementation, the blockchain with smart contracts is developed to undertake the CER and electricity trading in a transparent and credible way. A prototype system based on Fabric blockchain verifies the feasibility of the proposed scheme, which demonstrated a five-fold increase in the economics and electricity generation utility of the microgrid and achieved a 2% reduction in carbon emissions compared to the baseline model.

Linking medical data silos for medical model learning and sharing makes for better healthcare for humanity. Before that, two critical issues must be solved, i.e., patient privacy protection and data contributors’ rights and interests. This paper proposes an evolutionary medical data modeling and sharing (EMDMS) framework. Specifically, EMDMS adopts a federated learning scheme to coordinate the decentralized medical model learning and model aggregation without the leakage of raw data. A dual-loop federated learning mechanism with a tailored control strategy is developed for the realization of evolutionary model learning with the consideration of the ever-growing medical data. Then, a long-term pricing and revenue distribution strategy is designed for evolutionary model sharing, thus to make the medical model self-growth. It not only ensures fair benefits for data contributors but also enables low-cost sharing of models for public welfare. EMDMS runs on the sharded blockchain to support parallel tasks where dedicated smart contracts are implemented for EMDMS to guarantee security and trustworthiness. A prototype system with simulations on the Fed-ISIC2019 dataset demonstrates the effectiveness of EMDMS and its advantages over some existing typical solutions.

Wireless rechargeable sensor networks (WRSNs) are promising in maintaining sustainable large-area monitoring tasks. Mobile chargers (MCs) are commonly used in WRSNs to replenish energy to nodes due to its flexibility and easy maintenance. Most existing works on WRSNs focus on designing offline or model-based online charging methods, which need the exact system information to conduct the optimization. However, in practical WRSNs, the exact system information such as the nodes' locations and energy consumption rates may not be easily accessible to the optimizer due to their unpredictability and high dynamics. Thus, in this work, we jointly optimize the MC's trajectory design and charging scheduling in a general and practical WRSN with inaccessibility to the exact system information, such that the charging utility of the MC is maximized. To address this problem, we introduce the model-free reinforcement learning (RL) technique, which enables the MC to learn to jointly optimize its moving trajectory and charging scheduling by interacting with the environment and tracking feedback signals from nodes and obstacles in real time. Specifically, we develop a soft actor-critic based mobile security policy intervened algorithm (SAC-MSPI) based on a novel safe RL framework, which maximizes the MC's charging utility while maintaining the safe movement (not hitting obstacles) for the MC during the entire charging period. Extensive evaluation results show that the proposed SAC-MSPI algorithm outperforms existing main RL solutions and traditional algorithms with respect to the charging utility maximization as well as the collision avoidance.

In this work, we study the problem of dispatching multiple unmanned aerial vehicles (UAVs) for data collection in internet of things (IoT), where each UAV departs from its start point, visits some IoT devices for data collection and returns to its destination point. Considering the UAV’s limited onboard energy and the time required to collect data from all IoT devices, it is essential to appropriately assign the data collection task for each UAV, such that none of the dispatched UAVs consumes excessive energy and the maximum task completion time among all UAVs is minimized. To optimize those two conflicting objectives, we focus on minimizing the maximum task completion time and the maximum energy consumption among all UAVs, by jointly designing the flight trajectory, hovering positions for data collection and flight speed of each UAV. We formulate this problem as a multi-objective optimization problem with the aim of obtaining a set of Pareto-optimal solutions in terms of time or energy dominance. Due to the NP-hardness and complexity of the formulated problem, we propose a multi-strategy multi-objective ant colony optimization algorithm (MSMOACO), which is developed based on a constrained ant colony optimization algorithm with a fitnessguided mutation strategy and an adaptive hovering strategy being delicately incorporated, to solve the problem. To accommodate the practical scenario, we also design a novel geometry-based collision avoidance strategy to reduce the possibility of collisions among UAVs. Extensive evaluations validate the effectiveness and superiority of the proposed MSMOACO, compared with previous approaches.

Although federated learning (FL) enables collaborative training across multiple data silos in a privacy-protected manner, naively minimizing the aggregated loss to facilitate an efficient federation may compromise its fairness. Many efforts have been devoted to maintaining similar average accuracy across clients by reweighing the loss function while clients’ potential contributions are largely ignored. This, however, is often detrimental since treating all clients equally will harm the interests of those clients with more contribution. To tackle this issue, we introduce utopian fairness to expound the relationship between individual earning and collaborative productivity, and proposeFederated-UtoPia (FedUP), a novel FL framework that balances both efficient collaboration and fair aggregation. For the distributed collaboration, we model the training process among strategic clients as a supermodular game, which facilitates a rational incentive design through the optimal reward. As for the model aggregation, we design a weight attention mechanism to compute the fair aggregation weights by minimizing the performance bias among heterogeneous clients. Particularly, we utilize the alternating optimization theory to bridge the gap between collaboration efficiency and utopian fairness, and theoretically prove that FedUP has fair model performance with fast-rate training convergence. Extensive experiments using both synthetic and real datasets demonstrate the superiority of FedUP.

Effective incentive mechanisms are invaluable in crowdsensing to stimulate the enthusiasm of strategic users. However, existing work focusing on multi-task allocation with the objective of purely maximizing the social utility may result in the problem of unbalanced allocation, which may damage the social fairness. This motivates us to introduce proportional fairness into the design of a novel fairness-aware incentive mechanism for the first time. Specifically, we first model the interaction of multi-task allocation in crowdsensing as a multi-requester multi-worker Stackelberg game, and then transform the fairness-aware multi-task allocation problem into a fairness-aware incentive mechanism design problem. Next, we prove that there is a unique Stackelberg equilibrium, and also show that it can be efficiently derived through cautiously proposed algorithms. Since the existing equilibrium may not be optimal, we further design a secondary allocation rule to maximize both social utility and system performance, while achieving proportional fairness at a minimum cost. Finally, extensive experiments using both synthetic and real-world datasets demonstrate the superiority of our proposed mechanism compared to the state of the arts.

In this paper, we study an unmanned aerial vehicle (UAV)-enabled wireless rechargeable sensor network (WRSN), where a rotary-wing UAV travels along a fixed trajectory while providing wireless charging services for a set of sensor nodes deployed on the ground. Given the practical speed-related flight energy model, we focus on minimizing the UAV’s flight energy during a time-bounded charging tour by appropriately controlling the UAV’s travelling speed, such that the charging demand of each node is satisfied. We first investigate the optimal speed control with the minimized flight energy on arbitrarily-shaped trajectories in a 2D space. We adopt the spatial discretization to tackle the non-convexity of the formulated problem, which is then solved by interior-point method with the provable upper bound of the UAV’s flight energy. Next, we develop the optimal speed control for the UAV to travel along a 1D trajectory, i.e., a straight line, which is commonly seen in many UAV applications. Extensive evaluations validate the effectiveness of our speed control design in terms of the UAV’s flight energy minimization.

Energy harvesting technology enables wireless sensor networks (WSNs) to be self-sustainable, for maintaining long-term key performance indicators, such as the data throughput and sensing coverage. Due to the highly dynamic and complex environment, energy sources (ES) cannot provide stable energy supply, which needs the efficient learning algorithm to enable system adaptations. This article reports on the development of reinforcement learning (RL) methodology to long-term data collection in self-sustainable WSNs. Specifically, we consider the WSN as a 2-D rectangular region, where a mobile sensor (MS) can harvest energy from ambient environments while transmitting the collected data to a fixed sink. Due to the changing environment and the mobility of the MS, the harvested energy by the MS at each slot presents spatiotemporal dynamics within the network, which severely affects the performance of data throughput from the MS to the sink. The MS’s trajectory is investigated to maximize the long-term average MS-to-sink data throughput. Due to the unknown energy arrival information as well as the locations of ESs, we formulate the problem as a Markov decision process, which is then solved with model-free RL. In particular, the deep deterministic policy gradient (DDPG) is applied to tackle the continuous and deterministic movement space. Results show that the MS can learn and optimize the moving trajectory by intelligently tracking the aggregated received energy over slots. Finally, the MS can identify and move to the optimal location where the maximized long-term average MS-to-sink data throughput is achieved. Extensive numerical evaluations are conducted to investigate the impact of various system parameters on the network performance.

Despite the rapid growth of successful examples of Federated Learning (FL), it faces the heterogeneity of data, models, and devices in emerging applications of Industrial Internet of Things (IIoT). Existing efforts mainly focus on training multiple personalized models by adopting a global, cluster, or pairwise fashion. However, the global collaboration does not work well in case of the non-IID data distribution, cluster collaboration is often inefficient due to the single cluster pattern and high computational cost, and pairwise collaboration incurs the limitations of collaboration scope and communication efficiency. To address the problems, we propose a novel personalized FL (PFL) framework with the game-theoretic insights, called group collaboration, to overcome the shortcomings of status quo. Specifically, we first formulate the group collaboration in PFL as a multileader multifollower Stackelberg game, and then develop an$\epsilon$-better response to efficiently characterize its unique equilibrium through cautiously proposing a potential function. Since the existing equilibrium may not be optimal, we further design a Robin Hood mechanism by using the idea of transferable utility to improve the performance of the training model. Meanwhile, we also prove that the new mechanism is sustainable and can converge to a stable state with an upper bound of the training loss. Last, extensive experiments on a simulated dataset and four real-world datasets demonstrate the superiority of our proposed approach compared to the state of the art.

Mobile chargers (MCs) are usually dispatched to deliver energy to sensors in wireless rechargeable sensor networks (WRSNs) due to its flexibility and easy maintenance. This paper concerns the fundamental issue of charging path DEsign with the Minimized energy cOst (DEMO), i.e., given a set of rechargeable sensors, we appropriately design the MC’s charging path to minimize the energy cost which is due to the wireless charging and the MC’s movement, such that the different charging demand of each sensor is satisfied. Solving DEMO is NP-hard and involves handling the tradeoff between the charging efficiency and the moving cost. To address DEMO, we first investigate how to identify a single charging position where the MC could stay to charge a set of sensors distributed within a small area with the maximized charging efficiency. Then, based on the result obtained in the case of optimizing a single charging position, we develop a computational geometry-based algorithm to deploy multiple charging positions within the whole network, by considering the fixed and finite charging range of the MC. We prove that the designed algorithm has the approximation ratio of$O\!\left ({\ln \!N}\right)$, where$N$is the number of sensors. Then we construct the charging path by calculating the shortest Hamiltonian cycle passing through all the deployed charging positions within the network. In addition, we investigate the impact of the network topology as well as the distribution of charging demands among sensors on the MC’s energy cost during a charging tour. Extensive evaluations validate the superiority of our path design in terms of the MC’s energy cost minimization, compared with existing main algorithms.

Mobile chargers (MCs) are usually dispatched to deliver energy to sensors in wireless rechargeable sensor networks (WRSNs) due to its flexibility and easy maintenance. This paper concerns the fundamental issue of charging path DEsign with the Minimized energy cOst (DEMO), i.e., given a set of rechargeable sensors, we appropriately design the MC’s charging path to minimize the energy cost which is due to the wireless charging and the MC’s movement, such that the different charging demand of each sensor is satisfied. Solving DEMO is NP-hard and involves handling the tradeoff between the charging efficiency and the moving cost. To address DEMO, we first develop a computational geometry-based algorithm to deploy multiple charging positions where the MC stays to charge nearby sensors. We prove that the designed algorithm has the approximation ratio of O(lnN), where N is the number of sensors. Then we construct the charging path by calculating the shortest Hamiltonian cycle passing through all the deployed charging positions within the network. Extensive evaluations validate the effectiveness of our path design in terms of the MC’s energy cost minimization.

Federated learning is an emerging paradigm to conduct the machine learning collaboratively but avoid the leakage of original data. Then, how to motivate the data owners to participate federated learning and contribute high-quality data is the crucial issue. In this article, a blockchain-based federated learning (BFL) with a reputation mechanism for high-quality model aggregation is proposed. Specifically, the blockchain transforms the federated learning into a decentralized and trustworthy manner. Over the blockchain, federated learning tasks, undertaken by smart contracts, can be conducted transparently and fairly. Besides, a reputation-constrained data contribution and reward allocation mechanism is designed to encourage data owners to participate in BFL and contribute high-quality data. The noncooperative game is adopted to analyze the behavior strategies of data owners. The existence of the unique equilibrium is proved and the equilibrium point indicates that the data owners can acquire highest reward with the contribution of the highest quality data. Thus, the model quality of BFL is guaranteed. Finally, simulations on the public data sets (MNIST and CIFAR10) demonstrate that BFL with a reputation mechanism can well promote the high-quality model aggregation of federated learning as well as can prevent malicious nodes from corrupting the training task.

Real-time fault diagnosis on vehicles can effectively avoid potential accidents, which, however, is difficult and challenging to be widely deployed due to the low computational capability and limited data storage of electric vehicles (EVs). To address this issue, we propose a vehicle-mounted fault diagnosis system with low computational complexity and small data storage, for achieving real-time monitoring of vehicle status. To facilitate the accurate and optimized feature selection, we had been collecting 6.52-GB real data from three EVs in 12 months. Motivated by those data, we first propose a multilabel feature selection algorithm to obtain the feature weights, based on which the optimal number of features is then calculated through the backpropagation neural network (BPNN), thus minimizing the computational cost of real-time fault diagnosis regarding sample dimensions. To further simplify the fault diagnosis system, i.e., reducing the minimum required capacity of data storage, we design a real-time diagnosis sliding window (RDSW) where the window moves forward as new samples arrive and the stale data outside the window are discarded. In particular, we calculate the optimal size of RDSW, which controls the minimum required number of samples to guarantee the accuracy of real-time fault diagnosis. Owing to the mechanism of RDSW, vehicles no longer need to store massive data to guarantee the accuracy of real-time fault diagnosis. In addition, the results of real-time fault diagnosis at each vehicle can be shared with other vehicles in cooperative intelligent transportation systems (C-ITS). Finally, comprehensive simulation is conducted to validate the effectiveness of the proposed diagnosis system in terms of accuracy, complexity and storage capacity.

Emerging crowdsensing paradigm enables a large number of sensing applications, where much attention is drawn to the fundamental problems of data collection and truth inference. Existing works have devised manifold techniques to discover truth from collected noisy data, but they frequently ignore various expertise of workers and dynamic information of crowdsensing system, thus leading to error-prone estimated truth and unqualified sensing data. In this paper, we design an online location-aware crowdsensing system to accurately estimate truth and efficiently assign tasks. Specifically, we unify diverse types of numerical and categorical tasks based on probabilistic graphical model, and then propose unsupervised learning methods which can dynamically infer ground truth and various worker expertise at the same time. Furthermore, we develop online task allocation schemes to gradually gather high quality data considering location awareness and inferred worker expertise. In particular, we convert the complicated task allocation into the additive form of probability improvement and entropy reduction, thereby solving the allocation problem via linearly selecting worker-task pair with low computation complexity. We finally carry out extensive evaluations using two datasets collected by our smartphones, where results demonstrate the superiority of our algorithms over the state-of-the-art approaches.

Visual tracking has achieved great progress due to numerous different algorithms. However, deep trackers based on classification or Siamese network still have their specific limitations. In this work, we show how to teach machines to track a generic object in videos like humans, who can use a few search steps to perform tracking. By constructing a Markov decision process in Deep Reinforcement Learning (DRL), our agents can learn to determine hierarchical decisions on tracking mode and motion estimation. To be specific, our Hierarchical DRL framework is composed of a Siamese-based observation network which models the motion information of an arbitrary target, a policy network for mode switch and an actor-critic network for box regression. This tracking strategy is more in line with human behavior paradigm, and is effective and efficient to cope with fast motion, background clutter and large deformations. Extensive experiments on the GOT-10k, OTB-100, UAV-123, VOT and LaSOT tracking benchmarks, demonstrate that the proposed tracker achieves state-of-the-art performance while running in real-time.

Mean field game facilitates analyzing multi-armed bandit (MAB) for a large number of agents by approximating their interactions with an average effect. Existing mean field models for multi-agent MAB mostly assume a binary reward function, which leads to tractable analysis but is usually not applicable in practical scenarios. In this paper, we study the mean field bandit game with a continuous reward function. Specifically, we focus on deriving the existence and uniqueness of mean field equilibrium (MFE), thereby guaranteeing the asymptotic stability of the multi-agent system. To accommodate the continuous reward function, we encode the learned reward into an agent state, which is in turn mapped to its stochastic arm playing policy and updated using realized observations. We show that the state evolution is upper semi-continuous, based on which the existence of MFE is obtained. As the Markov analysis is mainly for the case of discrete state, we transform the stochastic continuous state evolution into a deterministic ordinary differential equation (ODE). On this basis, we can characterize a contraction mapping for the ODE to ensure a unique MFE for the bandit game. Extensive evaluations validate our MFE characterization, and exhibit tight empirical regret of the MAB problem.

Wireless power transfer (WPT) enables a reliable and convenient charging paradigm. This article concerns the fundamental issue of energy saving in wireless rechargeable sensor networks (WRSNs), i.e., given a fixed number of rechargeable sensors (RSs) with their locations and charging demands, we focus on a minimal charging expenditure (MAP) problem with directional WPT to decrease the energy expenditure of the charger, on condition that the charging demands of all sensors are satisfied. In particular, we consider the anisotropic energy receiving property of RSs, which is closely related to the distance and the angle between the sensor and the charger antenna's orientation in directional WPT. We transform the MAP problem into an optimal function placement (OFA) problem, which can be geometrically analyzed in a rectangular coordinate system and is NP-hard. First, we study the OFA problem in the case of uniformly distributed sensors with identical charging demands, we develop the uniform charging strategy (UCS) to bound the total charging expenditure as Θ(1) for any number of sensors N. Based on the acquired insights, we further studied the OFA problem when the distribution of charging demands is Gaussian. We bound the total charging expenditure as Θ(1) for any number of sensors N, by developing the layered charging strategy (LCS). Extensive simulation results confirmed the performance of our design compared with two baseline algorithms. Both of the theoretical and simulations results reveal that the total energy expenditure of the charger is strongly related to the sensors' charging demands, however, is less affected by the number of sensors in the network.

This article reports on the development of a deep Q-learning approach to long-term energy collection in self-sustainable sensor networks, which consists of two static chargers (SCs) and one rechargeable mobile sensor (MS). In particular, we assume that the SCs can harvest energy from the ambient environment and charge the MS via electromagnetic (EM) radiation. As the energy harvesting (EH) process is random and the radiated energy fades over distance, the achievable energy by the MS at each slot demonstrates spatiotemporal dynamics in a certain area. Thus, we focus on the problem of trajectory optimization for an autonomous MS to maximize the long-term average achievable energy per slot from both chargers. Due to the inaccessible charger-side information, such as the EH profile and locations of SCs as well as the transmit power, we introduce deep Q-learning, a model-free reinforcement learning approach, based on which the MS can learn and optimize the moving trajectory by intelligently tracking the aggregated received EM signal without any other explicit external information. Simulation results show that the MS can identify the best energy collecting location and finally moves there along the learned trajectory. We also investigate the impact of system parameters, such as initial position and moving cost per unit distance on the performance of the proposed training algorithm, such as convergence rate and stability via extensive numerical evaluations.

Recently, Siamese networks based tracking algorithms have shown favorable performance. Latest work focuses on better feature embedding and target state estimation, which greatly improves the accuracy. Nevertheless, the simple cross-correlation operation of the features between a fixed template and the search region limits their robustness and discrimination capability. In this paper, we pay more attention to learn an outstanding similarity measure for robust tracking. We propose a novel relation network that can be integrated on top of previous trackers without any need for further training of the siamese networks, which achieves a superior discriminative ability. During online inference, we utilize the feedback from high-confidence tracking results to obtain an additional template and update it, which improves the robustness and generalization. We implement two versions of the proposed approach with the SiamFC-based tracker and SiamRPN-based tracker to validate the strong compatibility of our algorithm. Extensive experimental results on several tracking benchmarks indicate that the proposed method can effectively improve the performance and robustness of the underlying trackers without reducing speed too much, and performs superiorly against the state-of-the-art trackers.

Crowdsensing paradigm facilitates a wide range of data collection, where great efforts have been made to address its fundamental issues of matching workers to their assigned tasks and processing the collected data. In this paper, we reexamine these issues by considering the spatio-temporal worker mobility and task arrivals, which more fit the actual situation. Specifically, we study the location-aware and location diversity based dynamic crowdsensing system, where workers move over time and tasks arrive stochastically. We first exploit offline crowdsensing by proposing a combinatorial algorithm, for efficiently distributing tasks to workers. After that, we mainly study the online crowdsensing, and further consider an indispensable aspect of worker's fair allocation. Apart from the stochastic characteristics and discontinuous coverage, the non-linear expectation is incurred as a new challenge concerning fairness issue. Based on Lyapunov optimization with perturbation parameters, we propose online control policy to overcome those challenges. Hereby, we can maintain system stability and achieve a time average sensing utility arbitrarily close to the optimum. Finally, we propose an optimization framework to aggregate the sensing data which can estimate worker expertise and task truth simultaneously. Performance evaluations on real and synthetic data set validate the proposed algorithm, where 80 percent gain of fairness is achieved at the expense of 12 percent loss of sensing value on average.

Due to the random and dynamic energy-harvesting process, it is challenging to conduct optimal rate control in Energy-Harvesting Communication Systems (EHCSs). Existing works mainly focus on two cases: (1) the traffic load is infinite (as long as there is energy, there is data to transmit), in which the objective is to optimize the rate control policy subject to the dynamic energy arrivals, thus maximizing the average system throughput; and (2) the traffic load is finite, in which the objective is to optimize the rate control policy, thus minimizing the time by which all packets are delivered. In this work, we focus on the optimal rate control of EHCSs from another important and practical perspective, where the data and energy arrivals are both random. Given any deadline of T , our goal is to maximize the total throughput in [0, T ]. Specifically, two scenarios are considered: (1) energy is ready before the transmission; and (2) energy arrives randomly during the transmission. In both scenarios, we assume that the data arrive randomly during the transmission. For the first scenario, we develop a novel Stepwise Searching Algorithm (SSA) based on the cumulative curve methodology, which is shown to achieve the optimal solution and the complexity grows only linearly with the problem size. In addition, the SSA can provide a simple and appealing graphical visualization of approximating the optimal solution. For the second scenario, we provide a simplified case study that can be solved by the SSA with low computation overhead and demonstrate the difficulties in solving the general setting, which initiates a first step toward the full understanding of the scenario when energy arrives randomly during the transmission.

Crowdsensing paradigm facilitates a wide range of data collection, where great efforts have been made to address its fundamental issue of matching workers to their assigned tasks. In this paper, we reexamine this issue by considering the spatiotemporal worker mobility and task arrivals, which more fits the actual situation. Specifically, we study the location-aware and location diversity based dynamic crowdsensing system, where workers move over time and tasks arrive stochastically. We first exploit offline crowdsensing by proposing a combinatorial algorithm, for efficiently distributing tasks to workers. After that, we mainly study the online crowdsensing, and further consider an indispensable aspect of worker's fair allocation. Apart from the stochastic characteristics and discontinuous coverage, the nonlinear expectation is incurred as a new challenge concerning fairness issue. Based on Lyapunov optimization with perturbation parameters, we propose online control policy to overcome those challenges. Hereby we can maintain system stability and achieve a time average sensing utility arbitrarily close to the optimum. Performance evaluation on real data set validates the proposed algorithm, where 116% gain of fairness is achieved at the expense of 12% loss of sensing value on average.

This paper investigates the multicast capacity of static wireless social networks. We adopt the two-layer network model, which includes the social layer and the networking layer. In the social layer, the social group size of each source node is modeled as power-law distribution. Moreover, the rank-based model is utilized to describe the relation between source and destinations in the networking layer. Based on the two-layer network model, the probability density function (PDF) of the destination positions is analyzed and verified by numerical simulation, which is different from the traditional ad hoc networks. According to the PDF, the bound of the network capacity is derived, and we propose a Euclidean minimum-spanning-tree-based transmission scheme, which is proved to achieve the order of capacity bound for most cases. Finally, the capacity of social networks is compared to the traditional multicast ad hoc networks, which indicates that the capacity scaling performs better in social networks than traditional ones. To our best knowledge, this is the first work of analyzing the impact on the capacity of social relation and group size in multicast ad hoc networks for the rank-based model.

Abstract With the prevalence of mobile devices, it is of much interest to study the properties of mobile ad hoc networks. In this paper, we extend the concept of diameter from static ad hoc network to mobile ad hoc network, which is the expected number of rounds for one node to transmit a message to all other nodes in the network, reflecting the worst end‐to‐end delay between any two node. Specifically, we investigate the diameter of identically and independently mobility model in cell‐partitioned network and random walk mobility model in two‐dimensional torus network, achieving the boundary , when (k=Ω(n)), andO(klog2k), respectively, wherenis the number of nodes andkis the number of cells of network and especially under random walk mobility model . A comparison is made among the diameter of mobile ad hoc networks under identically and independently mobility model, random walk mobility model and static ad hoc network, showing that mobility dramatically decreases the diameter of the network and speed is an essential and decisive factor of diameter. Copyright © 2016 John Wiley & Sons, Ltd.

In this paper,1we investigate the throughput and delay in heterogeneous cognitive radio networks (HCRN), where the data source and the destination (S-D) is heterogeneously distributed following a rank based model and secondary users (SUs) provide relay service for primary users (PUs). We consider two scenarios: 1) PUs and SUs are both static; and 2) PUs are static and SUs are mobile. For scenario 1, we show that the primary network throughput is the same for different heterogeneous extents of S-D distribution owing to the flexible assistance of SUs, while the throughput of secondary networks is proven to be changing with the S-D heterogeneity exponent α, which depicts the variation of different heterogeneous extents of S-D distribution. In addition, the delay of both primary and secondary networks are shown to be altering with α. Further, we reveal that the number of SUs required to assist PUs can be dramatically reduced when considering the S-D heterogeneity, while achieving the same primary network throughput. For scenario 2, we utilize a modified uniform mobility (MUM) model to depict the motion of SUs and mainly focus on the analysis of throughput and delay for primary networks. It shows that the primary network throughput is also free of the heterogeneous extent of S-D distribution, while the delay changes with α. Due to the mobility of SUs, a better delay-throughput tradeoff of primary networks is achieved compared with that in scenario 1.

Cognitive radio (CR) technique is considered an effective mechanism to relieve the spectrum scarcity issue, where the secondary users (SUs) can utilize the idle spectrum of the primary users (PUs). How the performance of the wireless network will be influenced by the introduction of CR technique has been attracting much attention in past years. While many efforts have been made to study the cognitive radio network, where the data source and the destination (S-D) is homogeneously distributed, the research on cognitive radio networks (CRN) with heterogeneous S-D distribution is still very limited. In this paper, we investigate the throughput and delay scaling law in the heterogeneous cognitive radio network (HCRN), where the S-D pair follows a rank based model and SUs provide relay service for PUs in reciprocating the utilization of PUs' idle spectrum. By applying a cellular TDMA scheduling scheme, we show that the primary network throughput is the same for different heterogeneous extents of S-D distribution owing to the flexible assistance of SUs, while the throughput of secondary networks is proven to be changing with respect to the S-D heterogeneity exponent denoted by α. In addition, the delay scaling are derived for both primary and secondary networks and shown to be altering in accordance with α. Further, we reveal that the density of SUs required to assist PUs can be dramatically reduced when considering the S-D heterogeneity, while achieving the same primary network throughput.

In this paper, we study the throughput and delay in wireless cognitive social networks. Specifically, we consider a common scenario for cognitive radio networks (CRNs) where the primary and secondary networks operate at the same time and space and share the spectrum. On this basis, we integrate a social relationship into the CRN where each source node selects its destination upon a rank-based model, which captures the social characteristic well. By applying a cellular time-division multiple-access scheduling scheme, we first characterize the distinct traffic pattern caused by the social relationships between nodes. Then, we derive the achievable throughput and delay for both primary and secondary networks under the new network setting. In addition, we also study the cognitive social networks with infrastructure where I = o1(n) base stations are regularly deployed within the primary network. Given a probabilistic routing strategy, throughput of the proposed network is recalculated. Particularly, due to the social relationships between nodes, we reveal that a larger I is required if we expect a significant capacity gain within the primary network compared with previous works.