Hybrid Cloud-Edge-Vehicle Collaborative Task Offloading in VEC Based on Reinforcement Learning and Game Theory
Open Access
- 24 December 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of Vehicular Technology
- Vol. 7, 290-305
Abstract
With the rapid advancement of autonomous driving technologies, Vehicle-to-Everything (V2X) networks are recognized as pivotal in enhancing the efficiency and safety of intelligent transportation systems. However, the highly dynamic and mobile nature of V2X environments poses considerable challenges for task offloading, particularly in achieving low delay, high energy efficiency and task success rate maximization. To address these issues, this study introduces the Dynamic Task Offloading Framework (DTOF) and the Hybrid Integrated Offloading Algorithm (HIOA). The DTOF incorporates dynamic task segmentation with cross-layer resource allocation, thereby improving adaptability under high mobility conditions, with vehicle speeds ranging from 20 to 120km/h. The HIOA integrates deep reinforcement learning (DRL) with game-theoretic methods to achieve near-optimal multi-objective optimization, encompassing delay minimization and energy efficiency improvement across vehicle densities of 30 to 80 vehicles/km2. Specifically designed to satisfy the delay requirement for Level 4 and beyond autonomous driving, the HIOA ensures both low delay and energy efficiency. Hybrid simulations combining SUMO traffic modeling and a 5G New Radio (NR) channel model demonstrate that the HIOA achieves superior performance compared to existing approaches. Under typical operating conditions, it reduces service access delay by 25%,lowers energy consumption by 18% and elevates task success rate by 30%. Moreover, the HIOA maintains robust performance under peak traffic scenarios (80 vehicles/km2) and amid infrastructure impairments (30% RSU failure rate). This work substantially augments the efficiency and adaptability of V2X, establishing a solid groundwork for further development of autonomous driving technologies. Future research will investigate federated learning for cross-domain collaboration and refine the integration of game-theoretic and DRL mechanisms to further reduce computational complexity.Keywords
Funding Information
- Natural Science Foundation of Hunan Province (2025JJ80309)
- Hunan Provincial Social Science Appraisal Committee (XSP25YBC539)
This publication has 28 references indexed in Scilit:
- Deep meta reinforcement learning for efficient task offloading in edge computing environmentsCluster Computing, 2025
- Cost optimization strategy for dependent task offloading in vehicular edge computingApplied Soft Computing, 2025
- A deep Q-network-based edge service offloading in cloud–edge–terminal environmentThe Journal of Supercomputing, 2025
- Vehicle Edge Computing Task Offloading Strategy Based on Multi-Agent Deep Reinforcement LearningJournal of Grid Computing, 2025
- Meta learning-based deep reinforcement learning algorithm for task offloading in dynamic vehicular networkEngineering Applications of Artificial Intelligence, 2025
- A hybrid PSO and GA algorithm with rescheduling for task offloading in device–edge–cloud collaborative computingCluster Computing, 2024
- Novel multi-dimensional task offloading techniques for vehicular edge computing networksInternational Journal of System Assurance Engineering and Management, 2024
- A Digital Twin-based multi-objective optimized task offloading and scheduling scheme for vehicular edge networksFuture Generation Computer Systems, 2024
- Delay-sensitive task offloading and efficient resource allocation in intelligent edge–cloud environments: A discretized differential evolution-based approachApplied Soft Computing, 2024
- Decision tree‐based task offloading in vehicle edge computingConcurrency and Computation: Practice and Experience, 2024