Recently, large models have shown significant potential for smart healthcare. However, the deployment of Large Vision-Language Models (LVLMs) for clinical services is currently hindered by three critical challenges: a tendency to hallucinate answers not grounded in visual evidence, the inefficiency of fixed-depth reasoning, and the difficulty of multi-institutional collaboration. To address these challenges, in this paper, we develop MedAlign, a novel framework to ensure visually accurate LVLM responses for Medical Visual Question Answering (Med-VQA). Specifically, we first propose a multimodal Direct Preference Optimization (mDPO) objective to explicitly align preference learning with visual context. We then design a Retrieval-Aware Mixture-of-Experts (RA-MoE) architecture that utilizes image and text similarity to route queries to a specialized and context-augmented LVLM (i.e., an expert), thereby mitigating hallucinations in LVLMs. To achieve adaptive reasoning and facilitate multi-institutional collaboration, we propose a federated governance mechanism, where the selected expert, fine-tuned on clinical datasets based on mDPO, locally performs iterative Chain-of-Thought (CoT) reasoning via the local meta-cognitive uncertainty estimator. Extensive experiments on three representative Med-VQA datasets demonstrate that MedAlign achieves state-of-the-art performance, outperforming strong retrieval-augmented baselines by up to 11.85% in F1-score, and simultaneously reducing the average reasoning length by 51.60% compared with fixed-depth CoT approaches.

In serverless vehicular edge computing (SVEC), a variety of vehicular services are encapsulated into the containers deployed on accessible edge computing nodes such as roadside edge servers and nearby vehicular terminals, aiming to bring remarkable benefits to the service management, e.g., simplifying the infrastructure management, improving the resource utilization, and dynamically scaling up or down in response to the resource demand. However, there still exists a challenging service scheduling problem between the requester vehicles and available SVEC processors, due to the the dynamic vehicle mobility and heterogeneous edge computing environment. In the problem, a set of request vehicles can locally process the service requests, or offload them to a nearest edge server and peripheral vehicular terminals. We particularly consider the essential difference of the edge server and hardware-constrained vehicular terminals in the storage capacity and computing capabilities for running the containers, and aim to minimize the total service cost of all requester vehicles subject to the mobility constraints of the vehicles. To address the problem, we propose a diffusion-based deep reinforcement learning (DRL) approach to quickly learn a high-accuracy solution. Numerical results demonstrate that compared with the baseline DRL approaches, the proposed approach has great advantages in both the learning accuracy and convergence rate.

The rapid development of autonomous driving technologies and the expansion of the Internet of Things (IoT) have intensified the demand for timely and accurate vehicular perception, highlighting the potential of leveraging vehicular edge computing (VEC) systems to support perception tasks. Unmanned aerial vehicles (UAVs), owing to their flexible mobility and line-of-sight advantages, have emerged as promising IoT-enabling aerial platforms to enhance both vehicular perception and computation capabilities in VEC environments. In this paper, we propose an accuracy-oriented and computation-efficient framework for air-ground cooperative sensing and computing, wherein a UAV cooperates with a group of connected and autonomous vehicles (CAVs) to collect sensing data of the objects around them, followed by data fusion and computation for object classification. We formulate a joint optimization problem involving UAV trajectory planning and sensing task placement, aiming to minimize the sensing accuracy error and task processing delay. The joint optimization problem is reformulated as a Markov decision process (MDP), where a penalty term for constraint violations is incorporated into the reward function to ensure feasibility. Furthermore, we develop an improved twin delayed deep deterministic policy gradient (TD3)-based algorithm for UAV-assisted cooperative sensing and computing to derive an efficient UAV trajectory control and subtask placement strategy. Results demonstrate that the proposed algorithm achieves superior performance compared to baselines in terms of convergence speed, training stability, and cost-saving, validating its applicability in dynamic UAV-assisted VEC environments.

Dispersed computing has emerged as a promising paradigm that leverages underutilized resources from massive Internet of Things devices (IoTDs) to enhance the computing capacity at the network edge. However, existing works about the dispersed computing overlook the heterogeneous computing environment with parallel and serial computations and task reliability requirements for the hardware-constrained IoTDs, and they lack multi-objective optimization approaches to optimize the task offloading. To address the challenges, we propose a comprehensive scheme to achieve a delay-aware and economic-aware dispersed computing paradigm by using a multi-objective optimization approach. Particularly, we consider parallel processing at an edge server and serial processing at the lightweight IoTDs, and leverage the task redundancy to satisfy the task reliability requirements on the IoTD side. We further formulate a constrained multi-objective optimization problem (CMOP) aiming at jointly optimizing the task assignment, bandwidth allocation, and CPU frequency allocation to simultaneously minimize the total delay cost and the total charge cost of the tasks. To address the CMOP, we propose an improved constrained multi-objective evolutionary algorithm that employs a dual-population cooperative mechanism between two populations and a repairing constraint-handling technique. The dual-population cooperative mechanism can balance convergence toward Pareto optimality and solution diversity maintenance. The repairing constraint-handling technique is designed to guide solutions toward feasible regions, achieving efficient exploration of complex constrained search spaces. Simulation results demonstrate the superiority of our algorithm in seeking the better-converged and better-distributed Pareto optimal solutions to well address the tradeoffs between the two objectives.

In long-distance and long-duration flight missions of unmanned aerial vehicles (UAVs), optimal scheduling of flight speed and energy replenishment is crucial to ensure flight efficiency and safety. This paper focuses on a UAV-based patrol inspection system, where a UAV is scheduled to visit multiple task nodes that are geographically distributed in the communication coverage of a base station (BS). The UAV hovers at each task node, performing data collection and data processing. The BS is equipped with a mobile edge computing (MEC) server and a battery swapping station, offering computation and energy support to the UAV. A decision-making model customized for the UAV is proposed, jointly optimizing flight speed selection, battery swapping, and task offloading to minimize the UAV's total operational cost in its flight. By introducing virtual nodes in the flight network, we construct a unidirectional extended graph, based on which the original nonconvex cost minimization problem is reformulated to a tractable mixed-integer convex problem. Further, a fast heuristic based on analytical target cascading (ATC) is developed to obtain suboptimal solutions to large-scale problems. Results demonstrate that the proposed model can lower the UAV's total operational cost by providing greater flexibility in terms of speed selection and battery swapping, and the proposed heuristic shows high computational efficiency for large-scale network scenarios.

Cooperative perception constitutes a critical technology to enhance situational awareness of vehicular users (VUs) by fusing multi-source observation data. Existing approaches employ either vehicles or road infrastructure as fusion platforms. However, vehicle-based approaches suffer from severe occlusions that compromise perception reliability, while infrastructure-based approaches are constrained by fixed coverage ranges that restrict spatial perception, thereby failing to achieve both reliable and comprehensive perception simultaneously. To overcome these limitations, we propose an uncrewed aerial vehicle (UAV)-enabled cooperative perception system where a UAV operates in a cyclic process: it adjusts its position to respond to VU requests, collects observation data, and returns the compressed fusion results to the VUs. In each cycle, we jointly optimize decisions regarding UAV trajectory, request response, data collection, compression degree of the fusion results, and resource allocation to balance fusion reliability and service latency, subject to UAV kinematics, task assignment, resource allocation, and latency constraints. We formulate this optimization problem as a dynamic constrained multi-objective optimization problem featuring cascaded dependencies where the request response, data collection, and resource allocation should be determined sequentially due to the inherent logic of cooperative perception. To solve this problem, we design an evolutionary algorithm based on a cascaded dependency generation strategy in which decision variables are generated according to their dependency order. Experimental results demonstrate the superior solution performance of our algorithm over four baseline algorithms. This study advances cooperative perception for vehicular networks by providing a UAV-enabled solution ensuring reliable fusion and timely service under dynamic traffic conditions.

The growing adoption of electric vehicles (EVs) and expansion of Internet of Things (IoT) in-vehicle applications enhance vehicle intelligence and connectivity but also drive higher demand for both charging and computing services. Charging and computing stations (CCSs), integrating bidirectional chargers and edge computing servers and allowing optimal joint energy-computation management, has been taken as an effective solution to address this demand. This article introduces a new concept called charging and computing service vehicle (CCSV) fleets, which are equipped with high-capacity batteries and edge servers, serving as mobile resources to support the stationary CCSs at different locations in a wide area. We propose a two-timescale model integrating temporal-spatial scheduling, charging/discharging management, and computation task offloading of the CCSV fleets. Our goal is to minimize the total system cost by optimizing the energy-computation coordination between the mobile CCSV fleets and the stationary CCSs. We construct an extended time-space network (TSN) with congestion nodes, providing a clearer depiction of the time-varying congestion conditions in the traffic network. For practical implementation, we develop a heuristic based on the convex-concave procedure (CCP) and penalty alternating direction method (PADM) to solve the problem quickly. Simulation results in a traffic network based on Guangzhou city demonstrate that the proposed model effectively leverages the mobility and multidimensional resources of the CCSV fleets to reduce the system cost significantly.

Connected and automated vehicles (CAVs) have emerged as an efficient solution to improve the driving experience in the intelligent transportation systems (ITSs), in which the targeted vehicle (TV) can switch between the human-driven (HD) and autonomous-driven (AD) modes to act as server or terminal in vehicular edge computing networks (VECNs). However, due to the dynamic nature of traffic networks and the moving of vehicles, distribution of computational resources is imbalanced and variable, it is a challenge to design the cooperative resource management scheme for the whole journey of vehicle users. In this article, we propose a joint driving model selection and resource management scheme for TV in each road segment, to maximize the vehicle users’ satisfaction of the whole journey. For the complex formulated joint optimization problem, we design a three-stage hierarchical optimization (3SHO) framework, using deep Q-network (DQN) for driving mode optimization in the first stage and deep deterministic policy gradient (DDPG) for optimizing resource management under different selected driving modes. And a terminal-server matching mechanism is introduced to enable dynamic service quality improvement for TV. Specially, we design a new user satisfaction function with the quality of service, traffic revenue, and the gap between expected and actual revenues of users are considered. Experimental results showcase the robust convergence of the 3SHO algorithm, the adeptness to dynamic traffic networks, and the capacity to enhance user satisfaction significantly.

Group vehicle trajectory prediction (GVTP) is important for analyzing the traffic states and optimizing the traffic management. However, existing studies have performance bottlenecks in the prediction accuracy and inference latency. To tackle the problems, we propose a linear UNet-enhanced fully connected spatial–temporal GNN (LUFC-STGNN) for GVTP. First, a spatial graph is constructed by integrating prior-based and data-driven methods to capture both explicit and implicit spatial interactions between the vehicles. After that, a comprehensive temporal graph is created to capture the varying strengths of temporal interactions between all vehicles throughout historical timestamps. Furthermore, a fully connected spatial–temporal graph combining the spatial and temporal graphs is introduced to extract the effective spatial–temporal interaction features of the vehicles through the graph convolution operation. Finally, a linear UNet-based temporal dependency encoder (LU-TDE) is designed to further enhance the model’s ability of capturing the potential temporal patterns in the vehicle interactions. The encoder with linear complexity explores the multiscale temporal dependencies from the spatial–temporal interaction features but also reducing the inference latency. Experiments results based on real-world datasets show that compared to state-of-the-art models, our model reduces the average root mean square error over the 5-s prediction horizon by 31% and 10% on the NGSIM and HighD datasets, while reducing the inference latency by at least 1.26 times.

As an emerging technology, Digital Twin (DT) can provide a virtual representation of transportation infrastructures to achieve efficient and precise management of Intelligent Transportation Systems (ITS). However, a mixed traffic scenario of coexisting intelligent connected vehicles (ICVs) and non-intelligent connected vehicles (N-ICVs) increases challenges for digital ITS. N-ICVs are unable to generate and update their DT models independently due to constrained communication and computing capabilities. It is crucial to achieve real-time DT model update and migration of N-ICVs. In this paper, we propose a cooperative perception aided DT model update and migration approach, which dispatches ICVs to cooperatively sense and transmit information of nearby N-ICVs to assist in generating N-ICVs’ DT models. In particular, with the objective of minimizing the average maximum weighted age of information (AMWAoI), we jointly optimize the cooperative ICV selection as well as the bandwidth and computation allocations while guaranteeing the perception performance. We then propose a sensing data weighted size maximization matching algorithm to achieve an optimal ICV selection strategy, and the bandwidth and computation allocations are optimized by the gradient descent algorithm. Considering the dynamic nature of vehicular networks, a deep reinforcement learning-based access selection and DT model migration algorithm is further proposed to achieve continuous service provisioning. Simulation results demonstrate that the proposed algorithm achieves the lowest AMWAoI while meeting the perception performance requirement.

Vehicle-road collaboration is an effective means of improving perception capacities and enhancing safety of intelligent connected vehicles (ICVs). A larger volume of perception data increases the accuracy and robustness of environmental understanding, but it also introduces heavier computation loads. Aiming to reduce data size while meeting perception requirements, this paper studies joint data preprocessing and offloading in vehicle-road collaboration. In the preprocessing stage, we assign different priorities to the detected objects based on their types and distances from the perceiving vehicles. We allow discarding some low-priority objects that may not need immediate attention to reduce computation loads in subsequent data processing. After object selection and downsampling on video frames, the downsized perception data is offloaded and processed collectively by ICVs and roadside units (RSUs). A nonconvex mixed-integer problem is formulated, maximizing the sum of priorities of the selected objects while satisfying constraints of time delay, bandwidth, and computing resources. A fast heuristic based on the penalty alternating direction method (PADM) and modified annealed feasibility pump (MAFP) is developed to solve the problem. Results show that the proposed method is more computationally efficient than the commercial solver in solving the priority maximization problem. Also, it can significantly reduce perception data size, enabling efficient use of the limited communication and computing resources to timely complete more high-priority tasks.

Rapid advancements in wireless communication have led to a dramatic upsurge in data volumes within mobile edge networks. These substantial data volumes offer opportunities for training Artificial Intelligence-Generated Content (AIGC) models to possess strong prediction and decision-making capabilities. AIGC represents an innovative approach that utilizes sophisticated generative AI algorithms to automatically generate diverse content based on user inputs. Leveraging mobile edge networks, mobile AIGC networks enable customized and real-time AIGC services for users by deploying AIGC models on edge devices. Nonetheless, several challenges hinder the provision of high-quality AIGC services, including issues related to the quality of sensing data for AIGC model training and the establishment of incentives for big data sharing from mobile devices to edge devices amidst information asymmetry. In this paper, we initially define a Quality of Data (QoD) metric based on the age of information to quantify the quality of sensing data. Subsequently, we propose a contract theoretic model aimed at motivating mobile devices for big data sharing. Furthermore, we employ a Proximal Policy Optimization (PPO) algorithm to determine the optimal contract. Numerical results demonstrate the efficacy and reliability of the proposed PPO-based contract model.

Collaborative Vehicular Edge Computing (CVEC) employs an edge server on the roadside unit and volunteer vehicles as processors to provide vehicle-to-infrastructure (V2I) offloading and vehicle-to-vehicle (V2V) offloading for requester vehicles in computation offloading. Since the processors have heterogeneous computing capabilities, we study a hybrid task scheduling problem to minimize the total service cost of all requester vehicles subject to feasible constraints. More specifically, the service cost of a requester vehicle is formulated as the product of the priority value and weighted sum of the delay and energy consumption of processing the task. We derive delay constraints of the V2V and V2I offloading according to the mobility of the vehicles. Furthermore, we present a deep reinforcement learning approach to solve the above problem in the dynamic vehicular environment. Particularly, we adopt the state-of-the-art Rainbow algorithm to accelerate the convergence and achieve better performance. Finally, we provide numerical results to demonstrate that our approach outperforms the baseline approaches in achieving the faster and more accurate learning.

Vehicular crowdsensing employs vehicles as mobile sensing nodes to collect road environmental information and process the collected data. To perform the delay-tolerant crowdsensing tasks in convenience, vehicles with computational demands can offload the data process tasks to a proximal edge server (ES) in a probabilistic manner after entering a parking lot. The ES determines how to price the offloading services to maximize the expected total revenue, causing a joint probabilistic data offloading and service pricing problem between the vehicles and ES. To address the problem, we adopt a Stackelberg game approach to study the interaction between them. Specifically, the ES plays as the leader to determine the uniform price for all offloading vehicles, and to equally allocate the computing resource among them. The vehicles play as the followers to optimize their offloading probabilities to minimize the expected weighted sum of task delay, energy consumption and service fee. We employ the backward induction method to analyze the unique Stackelberg equilibrium. Subsequently, a distributed algorithm is designed to reach the Stackelberg equilibrium without prior knowledge of the vehicles. Numerical results demonstrate that compared with the baseline schemes, our scheme has an advantage in improving the economic benefits of the ES.

As an emerging technology, Digital Twin (DT) can provide a virtual presentation of the physical Intelligent Trans-portation Systems (ITS) to enhance the applications of ITS such as cooperation perception. In cooperative perception, accurate location is crucial for selecting proper cooperative vehicles (CoVs) to improve the perception performance. However, due to the high mobility of vehicles, the deviation between DT and physical world may lead to non-negligible location errors, which raises the challenges for achieving efficient CoV selection in cooperative perception. In this paper, we propose a DT-empowered multi-vehicle cooperative perception system, in which the CoV selection and bandwidth allocation are jointly optimized to improve the performance of cooperative perception. Specifically, an asyn-chronous federated learning scheme is deployed in DT for location prediction to mitigate the effect of the deviation. Based on the prediction results, the problem of joint predictive scheduling and bandwidth allocation is then formulated as the average delay minimization problem while reaching the required performances. The adaptive CoV selection and bandwidth allocation algorithm based on deep reinforcement learning is proposed to find the optimal scheduling strategy. Simulation results demonstrate that the proposed algorithm achieves the lowest average delay while effectively guaranteeing the performance requirement.

The synergy between Unmanned Aerial Vehicles (UAVs) and metaverses is giving rise to an emerging paradigm named UAV metaverses, which create a unified ecosystem that blends physical and virtual spaces, transforming drone interaction and virtual exploration. UAV Twins (UTs), as the digital twins of UAVs that revolutionize UAV applications by making them more immersive, realistic, and informative, are deployed and updated on ground base stations, e.g., RoadSide Units (RSUs), to offer metaverse services for UAV Metaverse Users (UMUs). Due to the dynamic mobility of UAVs and limited communication coverages of RSUs, it is essential to perform real-time UT migration to ensure seamless immersive experiences for UMUs. However, selecting appropriate RSUs and optimizing the required bandwidth is challenging for achieving reliable and efficient UT migration. To address the challenges, we propose a tiny machine learning-based Stackelberg game framework based on pruning techniques for efficient UT migration in UAV metaverses. Specifically, we formulate a multi-leader multifollower Stackelberg model considering a new immersion metric of UMUs in the utilities of UAVs. Then, we design a Tiny Multi-Agent Deep Reinforcement Learning (Tiny MADRL) algorithm to obtain the tiny networks representing the optimal game solution. Specifically, the actor-critic network leverages the pruning techniques to reduce the number of network parameters and achieve model size and computation reduction, allowing for efficient implementation of Tiny MADRL. Numerical results demonstrate that our proposed schemes have better performance than traditional schemes.

With the advancement in battery technology and the rise of on-board computing capabilities, electric vehicles (EVs) can serve as both energy prosumers and computing nodes. The mobility of EVs allows them to perform wide-area multi-resource exchange in both electricity networks and edge computing networks. We call such a paradigm an Electric Vehicle Charging and Computing Network (EVCCN). It is considered that the EVCCN is composed of multiple charging and computing stations (CCSs) in different locations. Each CCS integrates EV chargers and an edge server, offering the interfaces for EVs to bidirectionally trade both energy and computing resources. We propose a customized model jointly optimizing the path selection, charging/discharging, and task offloading in different CCSs to minimize an EV’s travel cost (i.e., the money spent on the EV’s trip). In the proposed model, the EV consumes energy and generates data on its way to the destination, subject to travel time, energy, and data constraints. The cost minimization problem is formulated as a nonconvex mixed-integer problem from a user-centric perspective. To solve it fast in practice, we construct a new action-expanded network to simply the model and develop a heuristic based on piecewise McCormick to quickly obtain a near-optimal solution. Simulation results show that our heuristic is computationally efficient for large traffic networks compared with global solvers. We also present results in a traffic network based on Guangzhou city, which shows that our model can save 33.99% in the travel cost compared with a baseline model.

Vehicle trajectory prediction (VTP) is important for ensuring safe decision-making and planning in Internet of Vehicles (IoV). In complex traffic scenarios, accurate and reliable trajectory prediction requires comprehensive understanding of the interaction behaviors among vehicles. However, existing methods fail to effectively capture vehicle interaction features and fully explore their potential dependencies, limiting improvements in prediction accuracy. To this end, we propose a social attention network fused multipatch temporal–variable dependency (SAN-FTVD) model to tackle the above problems. In specific, we first design a variable token embedding module (VTEM) to extract the motion state information of vehicles, which independently embeds each variable of vehicle historical data into a variable token. After that, we propose a physical informed vehicle interaction encoder (PI-VIE) to capture vehicle interaction features over continuous time. The encoder is combined with physical priors to encode vehicle interaction features based on the correlations between the variable tokens. Following that, a temporal–variable dependency fusion module (TVDFM) is proposed to extract and fuse the multipatch temporal and variable dependencies, fully exploring potential dependencies in vehicle interaction features. Numerical results demonstrate that compared with the state-of-the-art model, the proposed model reduces the average prediction root mean square error over 5-s time range by 8% and 7% on two public data sets with 75% less inference cost. Furthermore, extensive ablation experiments validate the effectiveness of the above modules in the model.

An unmanned aerial vehicle (UAV)-enabled intelligent transportation system utilizes a set of UAVs to collect and process surveillance data for transportation management. Subsequently, the processing results of the UAVs are transmitted to a control center that makes a centralized transportation management decision based on the fusion of all processing results. When performing the monitoring tasks, the UAVs can access to an edge server for offloading. To reduce the energy consumption and improve the fusion performance, the control center schedules the UAVs to perform the tasks in an energy-efficient manner while synchronizing the completion time of the UAVs. As a result, the control center studies a constrained multi-objective optimization problem (CMOP), in which two objectives, i.e., the total energy consumption of the UAVs and total completion time difference among the UAVs, are simultaneously considered. To tackle the CMOP, we develop an improved constrained multi-objective evolutionary algorithm. Particularly, we design an improved genetic operator and repairing constraint-handling technique to improve the overall performance of the proposed algorithm in seeking Pareto optimal solutions for the CMOP. Numerical results demonstrate that compared with the baseline algorithms, the proposed algorithm has great advantages in finding better solutions with the enhanced diversity and convergence for the CMOP.

In this work, we investigate the challenging problem of on-demand federated learning (FL) over heterogeneous edge devices with diverse resource constraints. We propose a cost-adjustable FL framework, named AnycostFL, that enables diverse edge devices to efficiently perform local updates under a wide range of efficiency constraints. To this end, we design the model shrinking to support local model training with elastic computation cost, and the gradient compression to allow parameter transmission with dynamic communication overhead. An enhanced parameter aggregation is conducted in an element-wise manner to improve the model performance. Focusing on AnycostFL, we further propose an optimization design to minimize the global training loss with personalized latency and energy constraints. By revealing the theoretical insights of the convergence analysis, personalized training strategies are deduced for different devices to match their locally available resources. Experiment results indicate that, when compared to the state-of-the-art efficient FL algorithms, our learning framework can reduce up to 1.9 times of the training latency and energy consumption for realizing a reasonable global testing accuracy. Moreover, the results also demonstrate that, our approach significantly improves the converged global accuracy.

Multi-camera three-dimensional (3D) pose estimation (MCTPE) has already achieved very high estimation accuracy by utilizing deep neural network (DNN) based models. However, long inference latency of the utilized complex DNN models prevents the real-time deployment of MCTPE. Device-edge collaborative inference (co-inference) is a promising way to reduce the total inference latency of MCTPE, which performs one part of the inference operations on the devices and the other part of inference operations on the edge server to fully exploit computation resources of both the devices and the edge server. Besides, there is overlap between the detection ranges of different cameras in many cases. We propose the camera-selecting device-edge collaborative inference for MCTPE (CDC-MCTPE), which discards some of the raw data from parts of the cameras to reduce the inference task size without sacrificing estimation accuracy too much. In CDC-MCTPE, we formulate the joint optimization problem with regard to the model split points and camera-selecting decisions to minimize the total inference latency and the energy consumption of all devices under the constraints of the estimation accuracy. A Random-Ordered Greedy Algorithm (ROGA) is proposed to quickly solve the problem. The simulation results show that the proposed CDC-MCTPE achieves better performance compared with three benchmarks.

To provide a dependency-aware application, multiple unmanned aerial vehicles (UAVs) are employed to serve a ground user with a set of interdependent tasks. This leads to a new computing paradigm called as multi-UAV-enabled aerial edge computing (MU-AEC). For the large-scale application of MU-AEC, both the task-centric objective and UAV-centric objective should be simultaneously considered. Thus, we focus on the joint interdependent task scheduling and energy balancing for MU-AEC by using a multiobjective optimization approach, which enables a decision maker to identify the optimal solutions corresponding to the best feasible tradeoffs between the two objectives. A constrained multiobjective optimization problem involving two objectives: 1) the makespan minimization of all tasks and 2) energy balancing among different UAVs, is formulated. In the solution methodology, we propose a constrained decomposition-based multiobjective evolution algorithm. To quickly seek more superior solutions, a local search mechanism by utilizing the objective information, and an improved genetic operator are proposed for remarkable performance improvements. Finally, numerical results demonstrate that compared with the baseline algorithms, our algorithm achieves both advantages in increasing the convergence and diversity of the solutions.

This paper studies optimal day-ahead scheduling of a battery swapping and charging system (BSCS) for electric vehicles (EVs) from a new perspective of multiple decision makers. It is considered that the BSCS locally incorporates the battery swapping and charging processes, and the two processes are managed by two operators, called a battery swapping operator (BSO) and a battery charging operator (BCO), respectively. Our main contribution is to propose a bilevel model where the BSO acts as the leader to receive and serve the battery swapping requests from EV users, and the BCO acts as the follower to interact with the grid and control battery charging and discharging power. We reformulate the bilevel optimization problem into an equivalent single-level problem that is a nonconvex mixed-integer nonlinear program (MINLP), and its size can easily become very large. To solve the problem efficiently, we develop a new heuristic composed of two parts, i.e., an estimation of the integer solution and an algorithm based on the alternating direction method (ADM). The results show that the proposed heuristic performs well in solving large-scale problems, providing close-to-optimal solutions quickly. In addition, compared to a social welfare maximization model that follows most existing related works, the proposed bilevel model can increase the number of swapped-out batteries by 35% and the batteries’ average energy state by 6%, improving the quality of battery swapping services.

Model update compression is a widely used technique to alleviate the communication cost in federated learning (FL). However, there is evidence indicating that the compression-based FL system often suffers the following two issues, i) the implicit learning performance deterioration of the global model due to the inaccurate update, ii) the limitation of sharing the same compression rate over heterogeneous edge devices. In this paper, we propose an energy-efficient learning framework, named Snowball, that enables edge devices to incrementally upload their model updates in a coarse-to-fine compression manner. To this end, we first design a fine-grained compression scheme that enables a nearly continuous compression rate. After that, we investigate the Snowball optimization problem to minimize the energy consumption of parameter transmission with learning performance constraints. By leveraging the theoretical insights of the convergence analysis, the optimization problem is transformed into a tractable form. Following that, a water-filling algorithm is designed to solve the problem, where each device is assigned a personalized compression rate according to the status of the locally available resource. Experiments indicate that, compared to state-of-the-art FL algorithms, our learning framework can save five times the required energy of uplink communication to achieve a good global accuracy.

With the vehicle-to-grid and computing capabilities, a parked electric vehicle (EV) has a dual role, namely being an energy prosumer as well as a computing node for accommodating computation-offloading services. This dual-role feature of EVs yields a new computing paradigm named Electric Vehicle Edge Computing (EVEC). To ease the implementation of EVEC, we propose a fine-grained EV management approach to jointly provide parking guidance for EVs and control their charging/discharging power in parking lots. We formulate a bilevel optimization problem where the top-level problem optimizes the matching between EVs and parking lots from the perspective of computation offloading, and the bottom-level problem optimizes the control of EV charging/discharging power from the view of power networks. We transform the bilevel optimization problem into a single-level form, which is a nonconvex mixed-integer nonlinear programming problem, and we further tackle it by linearization techniques. Finally, we provide numerical results to demonstrate the efficiency and effectiveness of our approach.

To facilitate the implementation of deep learning-based vehicular applications, vehicular federated learning is introduced by integrating vehicular edge computing with the newly emerged federated learning technology. In vehicular federated learning, it is widely considered that the raw data collected by vehicles have complete ground-truth labels. This, however, is not realistic and inconsistent with the current applications. To deal with the above dilemma, a semisupervised vehicular federated learning (Semi-VFL) framework is proposed. In the framework, each vehicular client uses labeled data shared by an application provider, and its own unlabeled data to cooperatively update a global deep neural network model. Furthermore, the application provider combines the multidimensional contract theory with prospect theory (PT) to design an incentive mechanism to stimulate appropriate vehicular clients to participate in Semi-VFL. Multidimensional contract theory is used to deal with the information asymmetry scenario where the application provider is not aware of vehicular clients’ 3-D cost information, while PT is used to model the application provider’s risk-aware behavior and make the incentive mechanism more acceptable in practice. After that, a closed-form solution for the optimal contract items under PT is derived. We present the real-world experimental results to demonstrate that Semi-VFL achieves the advantages in both the test accuracy and convergence speed, in comparison with existing baseline schemes. Based on the experimental results, we further perform the simulations to verify that our incentive mechanism is efficient.

Federated learning (FL) enables devices in mobile edge computing (MEC) to collaboratively train a shared model without revealing the local data. Gradient compression could be applied to FL to alleviate the communication overheads but the existing schemes still face challenges. To deploy green MEC, we propose FedGreen, which enhances the original FL with fine-grained gradient compression to control the total energy consumption of the devices. Specifically, we introduce the relevant operations including device-side gradient reduction and server-side element-wise aggregation to facilitate the gradient compression in FL. According to a public dataset, we evaluate the contributions of the compressed local gradients with respect to different compression ratios. Furthermore, we investigate a learning accuracy-energy efficiency tradeoff problem and the optimal compression ratio and computing frequency are derived for each device. Experimental results show that given the 80% test accuracy requirement, compared with the baseline schemes, FedGreen reduces at least 32% of the total energy consumption of the devices.

Parked Vehicle (PV) assistance in vehicular edge computing and networks is proposed to exploit underutilized computing resources from PVs for enhancing the resource capacity at the edge vehicular network. Containerization is used to improve task execution of PVs with fast start-up time, less hardware overheads and safe resource isolation. To this end, we introduce a task-container matching market to provide on-demand offloading services. For network implementation, the related entities including requesters, PVs with containers as performers and a service provider are described. Considering parking behaviors and resource availability, we measure the serviceabilities of PVs to select appropriate PVs for reliable and efficient task processing. According to utility functions, preference profiles of requesters and performers in the task-container matching market are modeled through the best response analysis. Finally, we apply matching game approach to cope with associations between tasks and containers deployed inside PVs. Numerical results demonstrate that compared with baseline schemes, our scheme accomplishes more tasks and acquires a higher overall utility in computation offloading.

The drastically increasing volume and the growing trend on the types of data have brought in the possibility of realizing advanced applications such as enhanced driving safety, and have enriched existing vehicular services through data sharing among vehicles and data analysis. Due to limited resources with vehicles, vehicular edge computing and networks (VECONs) i.e., the integration of mobile edge computing and vehicular networks, can provide powerful computing and massive storage resources. However, road side units that primarily presume the role of vehicular edge computing servers cannot be fully trusted, which may lead to serious security and privacy challenges for such integrated platforms despite their promising potential and benefits. We exploit consortium blockchain and smart contract technologies to achieve secure data storage and sharing in vehicular edge networks. These technologies efficiently prevent data sharing without authorization. In addition, we propose a reputation-based data sharing scheme to ensure high-quality data sharing among vehicles. A three-weight subjective logic model is utilized for precisely managing reputation of the vehicles. Numerical results based on a real dataset show that our schemes achieve reasonable efficiency and high-level of security for data sharing in VECONs.

With the repaid development of Internet of Vehicles (IoV), more available resources and energy-efficient optimizations in resources scheduling are exactly required for large-scale network implementation for sustainable development. We observe that parked vehicles (PVs) have rich and underutilized resources for task execution. By scheduling them as general computing nodes to undertake computation tasks, we introduce a new computing paradigm, named by parked vehicular computing (PVC). There exists some challenging issues to be addressed for the facilitation of PVC. In particular, an incentive mechanism is needed to offer optimized rewards for PVs with the consideration of their parking time and energy consumption. In this paper, we investigate an energy-efficient PVC paradigm, and we design a contract-based incentive mechanism to motivate PVs to contribute their idle on-board resources. The PVs are classified into different types according to their parking time. Then, the designed contracts are assigned to different types of PVs. To realize the incentive mechanism, the optimization problem with the contract design is formulated to maximize the utility of the service provider. For optimal contract design, we solve the simplified problem by using Lagrangian multiplier method. Numerical results indicate that the proposed PVC with optimal contract design outperforms existing work in improving social welfare of resource scheduling, which takes quality-of-service and overall energy consumption into consideration. We also demonstrate that the contract-based incentive mechanism is energy-efficient and effective.

Internet of Things (IoT) provides ubiquitous intelligence and pervasive interconnections to diverse physical objects. The overall network performance of existing IoT is restricted by limited network lifetime. Hence, energy harvesting technology with energy replenishment from mobile charger is proposed to prolong the network lifetime. Energy harvesting IoT is emerged. Nodes can not only request energy replenishment from the mobile charger, but also transfer surplus energy to the mobile charger for improving energy utilization. This gives rise to bidirectional energy flows in the network. A new paradigm that energy flows coexist with data flows is further resulted in. But there exist great challenges on controlling these flows. Toward centralized flow control, we exploit software defined networking to simplify and optimize network management, thus introduce software defined energy harvesting IoT (SEANET). In our proposed architecture, the data plane, energy plane, and control plane are decoupled to support enhanced communications and flexible energy scheduling. We consider reliable communications for SEANET, and propose to relay data packets among the nodes with high reputation values and sufficient energy. In particular, reputation values of nodes are computed by the multiweighted subjective logic for higher accuracy. Besides, a Nash bargaining game is formulated to solve the benefit allocation problem for energy trading in SEANET. Numerical results indicate that SEANET improves data traffic by reducing packet loss, optimizes energy utilization, and saves energy.

As a promising branch of Internet of Things, Internet of Vehicles (IoV) is envisioned to serve as an essential data sensing and processing platform for intelligent transportation systems. In this paper, we aim to address location privacy issues in IoV. In traditional pseudonym systems, the pseudonym management is carried out by a centralized way resulting in big latency and high cost. Therefore, we present a new paradigm named Fog computing supported IoV (F-IoV) to exploit resources at the network edge for effective pseudonym management. By utilizing abundant edge resources, a privacy-preserved pseudonym (P3) scheme is proposed in F-IoV. The pseudonym management in this scheme is shifted to specialized fogs at the network edge named pseudonym fogs, which are composed of roadside infrastructures and deployed in close proximity of vehicles. P3scheme has following advantages: 1) context-aware pseudonym changing; 2) timely pseudonym distribution; and 3) reduced pseudonym management overhead. Moreover, a hierarchical architecture for P3scheme is introduced in F-IoV. Enabled by the architecture, a context-aware pseudonym changing game and secure pseudonym management communication protocols are proposed. The security analysis shows that P3scheme provides secure communication and privacy preservation for vehicles. Numerical results indicate that P3scheme effectively enhances location privacy and reduces communication overhead for the vehicles.

We propose a localized peer-to-peer (P2P) electricity trading model for locally buying and selling electricity among plug-in hybrid electric vehicles (PHEVs) in smart grids. Unlike traditional schemes, which transport electricity over long distances and through complex electricity transportation meshes, our proposed model achieves demand response by providing incentives to discharging PHEVs to balance local electricity demand out of their own self-interests. However, since transaction security and privacy protection issues present serious challenges, we explore a promising consortium blockchain technology to improve transaction security without reliance on a trusted third party. A localized P2P Electricity Trading system with COnsortium blockchaiN (PETCON) method is proposed to illustrate detailed operations of localized P2P electricity trading. Moreover, the electricity pricing and the amount of traded electricity among PHEVs are solved by an iterative double auction mechanism to maximize social welfare in this electricity trading. Security analysis shows that our proposed PETCON improves transaction security and privacy protection. Numerical results based on a real map of Texas indicate that the double auction mechanism can achieve social welfare maximization while protecting privacy of the PHEVs.

Geo-distributed mobile cloud computing (GMCC) integrates location information into mobile cloud computing, that has high potential for a large variety of applications. In a vehicular environment, a GMCC provides a large number of resources to vehicles that are geographically close to them. However, there are few studies that focus on security and privacy issues in a GMCC scenario. Vehicles need sufficient pseudonyms to periodically change for privacy preservation. In this paper, we focus on pseudonym management in GMCC system for vehicular environment. We design a three-layer on-demand pseudonym system to manage the pseudonyms. Moreover, we propose a secure pseudonym distribution scheme for secure communication among vehicles. As the number of demanded pseudonyms varies with traffic loads in different clouds, we use a newsvendor model to address the optimal on-demand pseudonym distribution problem. Numerical results indicate our proposed schemes not only improve utility of the clouds, but also maximize utilization of the pseudonyms.

Cloud-enabled vehicular network is an emerging paradigm which utilizes cloud computing to enhance the performance of vehicular network. But some issues still need to be addressed and we focus on the pseudonym resources management, which is crucial for vehicles to guarantee location privacy. A new three-plane hierarchical architecture with software defined network technology is proposed to manage the pseudonym resources. We use two-sided matching theory to solve the pseudonym resources allocation problem among pseudonym pools in different roadside unit clouds. Numerical results show that our proposed approach optimizes the pseudonym resources utilization and also improves the privacy entropy of vehicles.

Vehicular social network (VSN) is envisioned to serve as an essential data sensing, exchanging and processing platform for the future Intelligent Transportation Systems. In this paper, we aim to address the location privacy issue in VSNs. In traditional pseudonym-based solutions, the privacy-preserving strength is mainly dependent on the number of vehicles meeting at the same occasion. We notice that an individual vehicle actually has many chances to meet several other vehicles. In most meeting occasions, there are only few vehicles appearing concurrently. Motivated by these observations, we propose a new privacy-preserving scheme, called MixGroup, which is capable of efficiently exploiting the sparse meeting opportunities for pseudonym changing. By integrating the group signature mechanism, MixGroup constructs extended pseudonym-changing regions, in which vehicles are allowed to successively exchange their pseudonyms. As a consequence, for the tracking adversary, the uncertainty of pseudonym mixture is accumulatively enlarged, and therefore location privacy preservation is considerably improved. We carry out simulations to verify the performance of MixGroup. Results indicate that MixGroup significantly outperforms the existing schemes. In addition, MixGroup is able to achieve favorable performance even in low traffic conditions.

Mobile cloud computing is a promising technology for pervasive healthcare, which guarantees real-time health monitoring and electronic medical records sharing in different environments. In this paper, we present a hierarchical mobile cloud computing framework with three layers for pervasive healthcare. The scalable and hierarchical mobile cloud framework can be used to disperse the global storage and management load. We also study the social characteristics among patients and divide the patients into different social groups for privacy protection. A secure electronic medical records sharing scheme and a real-time health information transmission scheme are proposed. The security analysis shows that our schemes not only provide secure communication but also protect privacy of the patients.