With the rapid evolution of 5G and the ongoing development of 6G technologies, the Internet of Vehicles (IoV) is expected to play a critical role in next-generation intelligent transportation systems. Applications such as autonomous driving, augmented reality, and smart mobility not only require ultra-low latency and high computational efficiency, but also demand enhanced trustworthiness and privacy assurance. To address these demands, Vehicular Edge Computing (VEC) has emerged as a foundational paradigm for 6G-IoT, enabling intelligent services by offloading tasks from vehicles to edge nodes. However, task offloading in IoV-VEC systems still faces critical challenges, including the need for responsible AI decision-making under dynamic network conditions and the protection of sensitive vehicular data. This paper proposes FedVTO, a privacy-preserving federated vehicle task offloading framework that integrates Federated Learning (FL) and Deep Reinforcement Learning (DRL) to optimize task offloading decisions and resource allocation strategies in VEC networks. By incorporating information entropy models and dynamically adjusting weighting parameters using an entropy-based method within a three-tier architecture (vehicles, roadside units, and cloud server), FedVTO minimizes latency, energy consumption, and privacy leakage. Experimental results show that FedVTO significantly improves task offloading efficiency and mitigates privacy risks compared to traditional methods in dynamic VEC environments.

With the development of Federated Learning (FL) in IoT Edge-Cloud Computing environments, mobile terminals are able to cooperate without the leakage on raw data. However, factors including the terminals' high mobility and the network fluctuations make the cooperator selection during FL training extremely complex. Under the distributed cooperation, traditional FL strategies show certain limitations and cannot always select the available nodes when training, leading to the difficulties in energy and latency optimization. In this paper, we propose a Hierarchical Reinforcement Learning (HRL)-based federated knowledge distillation (HRL-FedKD) framework in which both high-level and low-level controllers utilize the Double Deep Q-Network (DDQN) algorithm. The high-level controller selects the nodes participating in FL training, while the low-level controller determines the number of local training epochs for each node. After training, the global model will be compressed into a lightweight model by knowledge distillation (KD) in deployment while preserving the personalization of local models. The experiments were conducted using Chest X-Ray and Brain Tumor MRI datasets to validate the proposed FL strategy. The results demonstrate that the HRL-FedKD framework can effectively optimize latency and energy consumption in complex state spaces.

Federated learning (FL) is an emerging distributed machine learning paradigm that has privacy-preserving properties, but still poses privacy leakage risks in traditional centralized FL (CFL) caused by the frequent transmission of model parameters during training. Due to the resource differences among nodes, the training process is constrained by the slowest node, while frequent data transmissions result in significant communication overhead, leading to the reduced overall efficiency. What is more, resource-rich nodes cannot fully utilize their potentials, and large models cannot be deployed on resource-constrained end devices. Therefore, selecting participating nodes and their local training strategies efficiently is a key issue in FL. To address the aforementioned issues, this article proposes an edge-cooperative decentralized lightweight FL framework (Dec-LWFL), which introduces a multiagent reinforcement learning (MARL) method, and designs a scoring voting mechanism for selecting participating FL nodes, determining their local training strategies, and allocating the model aggregation tasks. During agent interactions, Gaussian noise is added to the state information to safeguard the privacy of edge nodes and users, and Rényi differential privacy (RDP) is utilized to quantify the effectiveness of the privacy protection mechanism. To adapt to the resource-constrained IoT environment, Huffman coding is employed during FL training phase to compress the transmitted models and reduce the communication overhead; then, knowledge distillation is selected during the deployment phase to achieve the goal of lightweight deployment. Experimental results demonstrate that Dec-LWFL can effectively balance the privacy and performance. The framework can significantly optimize the training latency and energy consumption, while satisfying the requirements for lightweight deployment.

As a rapid increase in Internet of Things (IoT) devices, vehicle fog/edge computing (VFC/VEC) has seen swift development. Consequently, these devices often opt to purchase computing resources from the edge–cloud service providers (ECSPs) to expand their capabilities. However, due to limited edge server resources, they may face risks of overload or breakdowns. Meanwhile, there are often large amounts of underutilized idle resources near roads (such as parked vehicles), which can provide additional computing and communication capabilities to the system. Inspired by this, we propose a scheme that utilizes idle vehicles to assist in computation. To coordinate the interests of various participating entities and incentivize resource sharing, we construct a multistage multileader multifollower (MSMLMF) Stackelberg game model that encompasses the collaboration and competition among users, ECSPs, vehicle operators (VOPs), and idle vehicles. Participants aim to maximize their utility while considering the potential actions of others. Additionally, considering the information asymmetry between VOP and vehicles, we introduce individual rationality (IR) and incentive compatibility (IC) constraints from the contract theory to analyze and ensure the effectiveness of contracts. Next, we employ backward induction to gradually simplify the game model into convex optimization problems and theoretically prove the existence and uniqueness of Nash equilibrium (NE) points. Finally, through simulation experiments verify that our proposed model and scheme outperform other baselines in overall social welfare.

With the continuous rolling-out of wireless edge cloud networks, Federated Learning (FL) has emerged as a promising solution for decentralized model training without exposing raw data. However, conventional centralized FL faces several limitations in resource-constrained mobile environments, including limited privacy-preserving capabilities and substantial communication overhead, which can lead to privacy leakage. Moreover, in non-independent and identically distributed (Non IID) data environments, FL faces the critical challenge of “client drift”, which leads to performance degradation. To address these challenges, this paper proposes TWHFL, a two-stage hierarchical knowledge distillation framework for Non-IID federated learning, designed to enhance terminal privacy protection and improve model personalization under heterogeneous data distributions. Specifically, in the cloud-edge collaboration stage, edge servers generate pseudo “hard samples” for all sub-MEC centers by optimizing noise inputs guided by feature distribution statistics (e.g., batch normalization running means and variances). To alleviate label distribution skew, both the label proportions and the volume of pseudo data are dynamically adapted based on the real-time operational state of each sub-MEC center. In the edge-terminal collaboration stage, each sub-MEC center conducts localized training using both real and synthetic data without external communication, thereby significantly reducing the risk of privacy leakage. Furthermore, a joint optimization problem is formulated to determine optimal configurations of pruning rates, CPU frequencies, up-link power, and bandwidth allocation, while jointly considering constraints on convergence rate, energy consumption, and latency. Experimental results show that the proposed TWHFL framework can effectively balance privacy protection and model performance in Non-IID settings.

The application of federated learning (FL) has been widely extended to medical domains, including medical image analysis and health monitoring. With the increasing computation power demand on edge devices, split federated learning has emerged as a promising FL architecture. In this work, a home healthcare monitoring scenario is explored. Unlike existing split federated learning studies that primarily focus on model-level optimization, this study considers a system-level optimization involving latency, packet error rate, and federated training time. Specifically, a k-means algorithm is presented to select inference nodes, participating training clients, and aggregation servers referring to network conditions and data quality. Furthermore, a reinforcement learning method is utilized to allocate the computation and bandwidth resources during inference, training, and aggregation, thereby further improving the quality of service (QoS) and training efficiency. Simulation results demonstrate that the proposed architecture can achieve the target accuracy while offering the enhanced QoS and reduced the FL training time.

Modern IoT industry cannot operate well without task scheduling, while the merging of edge computing and blockchain can empower more secure task scheduling models in distributed IoT environments. Due to various desirable properties (self-verifying, self-executing, immutability, reliability, confidentiality, etc.) provided by blockchain, the tasks generated from IoT devices can be safely scheduled. However, merely incorporating a blockchain framework into an IoT edge computing environment cannot guarantee the most desirable rewards for task participants. So in this article, we propose to use a Nash bargaining method in blockchain smart contract designing to strive the rewards for task participants and stimulate their proactivity while extending the above properties. The proposed blockchain-based Nash bargaining architecture can be applied in many distributed IoT scenarios, such as smart logistics, health data exchange, etc. For a practical implementation, a configurable blockchain architecture is developed consisting of both regular and constrained IoT devices. We additionally implement mutual authentication protocol and proof of authority to maintain the privacy and security for scheduling. Further, we experimentally study the feasibility of such architecture built in static and mobile IoT devices. Evaluations demonstrate that, the proposed architecture can well support a task scheduling process with tamper resistance, which is suitable for IoT edge computing with high-level security and creditability.

Vehicle Edge Computing (VEC), as an emerging computing paradigm, aims to achieve the high efficiencies and quality of service by distributing computation tasks to vehicles and cloud-edge servers. The resource pricing problem focuses on how to reasonably price the resources of VEC to encourage their allocation and utilization. However, VEC server overloading may lead to performance degradation, especially in urban congested areas. Meanwhile, idle resources near VEC roads, such as parked vehicles and RSUs, are underutilized and can provide additional computation and communication resources to the system. Inspired by this, this paper introduces a model to assist vehicle edge computing by attracting Idle Vehicles (IVs) to share resources. We use a two-stage Stackelberg game model to address the resource pricing and task offloading problem, analyzing the interaction between requesting vehicles and cloud-edge servers. Through a backward induction method, we transform the problem into a convex optimization problem and theoretically prove the existence of a unique Nash equilibrium. In the first stage, optimal offloading ratio strategy is solved using convex optimization theory. In the second stage, the original problem is decomposed into 2N sub-problems and solved using the Lagrangian dual method and Karush-Kuhn-Tucker (KKT) conditions for optimal resource pricing. Additionally, a price incentive mechanism and a task-vehicle stable matching game model are employed to recruit idle vehicles around the roads to spontaneously participate in the task offloading process. Finally, simulation results reveal our solution effectively reduces offloading costs, latency, energy use, and enhances task completion compared to others.

Abstract Deep learning (DL) techniques have grown in leaps and bounds in both academia and industry over the past few years. Despite the growth of DL projects, there has been little study on how DL projects evolve, whether maintainers in this domain encounter a dramatic increase in workload and whether or not existing maintainers can guarantee the sustained development of projects. To address this gap, we perform an empirical study to investigate the sustainability of DL projects, understand maintainers' workloads and workloads growth in DL projects, and compare them with traditional open‐source software (OSS) projects. In this regard, we first investigate how DL projects grow, then, understand maintainers' workload in DL projects, and explore the workload growth of maintainers as DL projects evolve. After that, we mine the relationships between maintainers' activities and the sustainability of DL projects. Eventually, we compare it with traditional OSS projects. Our study unveils that although DL projects show increasing trends in most activities, maintainers' workloads present a decreasing trend. Meanwhile, the proportion of workload maintainers conducted in DL projects is significantly lower than in traditional OSS projects. Moreover, there are positive and moderate correlations between the sustainability of DL projects and the number of maintainers' releases, pushes, and merged pull requests. Our findings shed lights that help understand maintainers' workload and growth trends in DL and traditional OSS projects and also highlight actionable directions for organizations, maintainers, and researchers.

Applications deployed on edge servers improve users’ experience, when compared to deployments on cloud servers. Existing works usually assume that a central scheduler helps in making decisions, but they are often inefficient, inaccurate, or time-consuming. In this paper, we present a proactive application deployment system, which consists of three modules (i.e., incentive, profit, and latency). Based on the architecture of a fully distributed edge network, our system includes SELL, a Spontaneous Edge depLoyment aLgorithm in the incentive module. SELL lets edge servers compete with each other in a two-stage Stackelberg game to win deployment rights, and the winners get paid for their deployment efforts. The other two modules help recursively adjust service prices and deployment intentions in view of their own profits. Simulations on the proactive edge application deployment system demonstrate that SELL can help an application provider find appropriate edge servers to deploy applications while maximizing the profits for both parties in a low latency.

Edge co-operations around us are playing an increasingly crucial role in both personal and business activities, because they can bring us higher-quality services. However, more networks take part in an edge co-operation, more privacy protections the co-operation need to be supported to stimulate edge networks' participation. Edge co-operation has great potential in providing a high-performance, low-latency, and high-bandwidth service environment but requires strong incentives to stimulate more networks to participate in. To tackle this challenge, we design a novel privacy-preserving incentive mechanism (PIM) for edge co-operation at a fully distributed edge. The proposed mechanism allows the Internet Service Provider (ISP) to select suitable edge networks for service provision under a budget constraint while guaranteeing differential privacy, approximate truthfulness, computational efficiency, individual rationality. Through several simulations, we evaluate the performance and validate the properties of our mechanism.

Mobile Edge Computing (MEC) has already developed into a key component of the future mobile broadband network due to its low latency. In MEC, mobile devices can access data-intensive applications deployed at edge, which are facilitated by service and computing resources available on edge servers. However, it is difficult to handle such issues while data transmission, user mobility and load balancing conditions change constantly among mobile devices, edge servers and the cloud. In this paper, we propose an approach for formulating Data-intensive Application Edge Deployment Policy (DAEDP) that maximizes the latency reduction for mobile devices while minimizing the monetary cost for Application Service Providers (ASPs). The deployment problem is modelled as a Markov decision process, and a deep reinforcement learning strategy is proposed to formulate the optimal policy with maximization of the long-term discount reward. Extensive experiments are conducted to evaluate DAEDP. The results show that DAEDP outperforms four baseline approaches.