Incentive-driven and SAC-based Resource Allocation and Offloading Strategy in Vehicular Edge Computing Networks

Vehicular edge computing (VEC) networks can provide low-latency services for vehicles. However, it is a great challenge for edge nodes to satisfy the computing tasks of all vehicles during vehicle peak hours. This paper studies the joint optimization problem of offloading strategy and resource allocation in a VEC network composed of road side units (RSUs) with computing resources, vehicle users and vehicle workers. In order to alleviate the computing pressure of the RSU, we use contract theory to encourage vehicle workers to execute computing tasks. At the same time, we propose a novel algorithm based on Soft Actor-Critic (SAC) to solve the system cost minimization problem considering vehicle users' satisfaction, RSUs' cost and vehicle workers' reward. Finally, we conduct extensive simulations in different scenarios, the simulation results show that our proposed algorithm has higher performance in reducing system cost compared with other benchmark methods.