The Internet of Electric Vehicles (IoEV) has emerged as a key component of future networks. However, some computation‐intensive vehicular applications cannot be executed locally owing to IoEV infrastructure limitations and computing resource bottlenecks. In this study, we propose a task offloading and resource management scheme based on Parked Electric Vehicle (PEV)‐assisted distributed edge intelligence (DEI), making use of underutilized PEV resources to handle offloaded tasks. In the proposed scheme, distributional reinforcement learning, the normalized average bargaining solution (NABS), and V2G charging scheduling are jointly combined to dynamically control availability prediction, resource sharing, and scheduling. The proposed scheme maximizes hybrid optimization benefits through PEV and edge server cooperation. Simulation results confirm performance improvements of 10%, 10%, and 15% in normalized service payoff, system throughput, and task failure rate, respectively, compared with existing benchmark protocols. Open issues and research directions for PEV‐DEI systems are also discussed.
The rapid growth of Internet of Vehicles (IoV) applications has imposed strict requirements on low-latency and energy-efficient computing services. This letter investigates a multi-Uncrewed Aerial Vehicle (UAV)-assisted IoV system, where multiple Mobile Edge Computing (MEC)-enabled UAVs (MUs) collaboratively provide computing services for vehicular terminals (VTs). To improve service capability, we propose an energy-efficient task offloading and load balancing scheme that jointly considers vehicle mobility, task offloading and migration, and computing resource allocation to formulate an optimization problem. To solve this problem, a collective learning (CL)-enabled multi-agent reinforcement learning (CL-MARL) algorithm is proposed, where each agent learns optimal policies through centralized training and collective cooperative learning. Simulation results demonstrate that the proposed scheme outperforms benchmark strategies in terms of energy efficiency, task completion rate, and load balancing.
Yongbin Wang, Peng Lin, Yan Liu et al.· IEEE Wireless Communications...· 0 citations
A framework based on GTGO to jointly offload, schedule and allocate resources to different tasks and augment it with an integrated explainable AI (XAI) module is presented, indicating that the suggested framework is an effective, efficient, and transparent resource management solution in intelligent vehicular edge computing systems.
Aditi Moudgil, S. Rani, Fazlullah Khan· PLoS ONE· 0 citations
The rapid growth of electric vehicles (EVs) creates challenges for grid stability, peak demand management, and renewable energy integration. Conventional cloud-centric charging coordination systems rely on continuous communication and suffer from latency that limits real-time responsiveness. This study introduces a novel distributed edge-intelligent EV charging coordination framework that integrates behavioral prediction, grid-aware scheduling, renewable-aware optimization, and localized AI inference within a communication-efficient IoT architecture. Lightweight models (CNN+LSTM, XGBoost, and Random Forest) are deployed on Jetson Orin Nano and Raspberry Pi 5 devices to enable low-latency decision-making with reduced reliance on the cloud. The framework is validated using a large-scale U.S. Department of Energy dataset. Experimental results demonstrate 27.6% improvement in station utilization, 24.5% reduction in peak grid load, and 29.8% decrease in user charging costs, with predictive performance reaching R² = 0.92. The findings provide a scalable and communication-efficient reference design for data-driven EV charging coordination in smart grid systems.
Uncoordinated charging of large-scale electric vehicles exacerbates peak-valley differences and voltage exceedance risks in the power grid, while existing scheduling methods still have limitations in distributed decision-making, dynamic pricing, and multiobjective balancing. These problems become more significant in charging station clusters where power-electronic converters, communication links, and complex electromagnetic operating environments jointly affect grid interaction stability. In this paper, a collaborative optimization framework based on multi-agent reinforcement learning is proposed for orderly charging at electric vehicle charging stations and coordinated interaction with the power grid. First, each charging station is modeled as an autonomous agent, and distributed environment modeling is realized based on local observation information and Markov decision processes. Second, a proximal policy optimization algorithm is used to generate a dynamic service fee multiplier in a continuous action space, which is combined with a demand elasticity module to form an adaptive pricing mechanism. Finally, a composite reward system integrating grid stability, operational revenue, and user satisfaction is developed, and multi-agent convergence training is achieved through parameter sharing and generalized advantage estimation. The results confirm the overall benefits of joint optimization in load shaping, economic performance, and robustness, providing a technical reference for intelligent charging coordination under grid interaction and electromagnetic compatibility constraints.
Y. X. Wang· Advanced Electromagnetics· 0 citations
: The demand for computer resources for internet of vehicles services like autonomous driving, real-time navigation, and in-vehicle entertainment has grown rapidly due to the widespread deployment of intelligent transportation systems and the ongoing advancement of information and communication technologies. Therefore, a novel task offloading optimization allocation model for internet of vehicles edge computing is proposed. The model is based on mobile edge computing architecture. Through clustering algorithm, it intelligently clusters all nodes in the static parked vehicles edge computing architecture. Moreover, the PSO algorithm is coded and optimized, which improves the efficiency and resource utilization of internet of vehicles task offloading. The experimental results indicated that the model was able to realize obvious inter-cluster separation under 2 min, 10 min, 50 min, and 100 min time nodes. The vehicles inside the clusters were also more closely distributed, resulting in good internal consistency and external separation. When the number of tasks was increased to 60, the corresponding total system cost of the research model was only 198. When the task computation volume was 120 GHZ, the total system cost of the research model was only 214. In addition, the research model still maintained a high offloading success rate of 97.5%, 94.6%, and 92.8 in low-density, medium-density, and high-density environments. In summary, the research model not only can effectively improve the vehicle task processing efficiency and reduce the system overhead, but also shows strong adaptability and robustness, which has good prospects for practical applications.