Diffusion-Based Multi-Agent Reinforcement Learning for Semantic Vehicular Edge Computing

Vehicular edge computing (VEC) is critical for the safe and efficient driving of intelligent vehicles, by which they can offload computation-intensive tasks (such as driving environment perception) to edge servers to overcome the limitations of onboard computational resources and cooperate with others. One of the major challenges faced by VEC is that the offloaded intelligent driving tasks generally generate large amounts of data, which can easily stretch and congest the vehicle communication channels. To address the above challenges, we first propose a novel semantic VEC (SVEC) architecture, which can extract the semantic information of tasks and offload them to edge servers, thereby achieving reliable and efficient offloaded task communication and computation adaptively. Considering the scarce channel resources of vehicles and the intelligent tasks with different priorities and modalities, we define a novel user utility model for SVEC and transform the problem of maximizing user utility into a joint optimization problem of semantic feature extraction, task offloading and resource allocation. Furthermore, to cope with the complexity of the solution space of the optimization problem, we propose a diffusion-based multi-agent reinforcement learning algorithm, which improves the ability of agents to explore the solution space through the diffusion process, thereby achieving optimal decisions for semantic feature extraction, task offloading and resource allocation. Simulation results show that the proposed scheme improves the overall performance of SVEC while reducing offload latency and average system cost.