Credit Value Based Autonomous Vehicles Joint Task Offloading Optimization

To address the issue of selfish behavior demonstrated by autonomous vehicles in vehicle-infrastructure cooperation, where vehicles having spare computing resources are disinclined to share them, we propose a vehicle selection-assisted computing scheme based on a credit value incentive mechanism. This scheme is aimed at resolving the reluctance of autonomous vehicles to supply their spare computing resources while also facilitating low-performance vehicles to participate effectively in task computing. Additionally, considering the optimization problem of delay and energy consumption during offloading and computing tasks for autonomous vehicles, we formulate a mathematical problem that integrates weighted sums of delay and energy consumption. To handle this problem, we propose a double populations adaptive particle swarm optimization algorithm (DPAPSO) based on the traditional particle swarm optimization algorithm (PSO). The DPAPSO forms two populations of particles in accordance with our model and utilizes different updating strategies for each population. Experimental results show that the proposed DPAPSO outperforms the traditional particle swarm optimization algorithm in terms of optimization effects within this model. Furthermore, it presents superior performance and stability compared to both the simulated annealing algorithm (SA) and the genetic algorithm (GA).