Delay and Battery Degradation Optimization based on PPO for Task Offloading in RSU-assisted IoV
Wei Zhao, Runhu Zhong, Cheng Wu, Xinwei Xu · 2023
In the context of Internet of Vehicles, Roadside Units (RSUs) play a crucial role in reducing the task delay through their strong computing capabilities. Nevertheless, extended usage of RSUs accelerates the battery degradation and impacts their service capacity. By offloading tasks to the cloud and vehicles, the degradation rate of the RSU battery is reduced at the expense of high task delay. Therefore, the problem of balancing task offloading delay and RSU battery degradation is a challenge. To address this issue, in this paper, we propose a joint optimization model that considers both task offloading delay and RSU battery degradation. RSUs actively perceive information from environment through their sensors. Tasks are processed either through local computation on RSUs, offloading computation to vehicles, or offloading computation to the cloud. By computing the Depth of Discharge (DOD) of the battery, we establish a battery degradation cost model to assess the degree of battery degradation. Due to the complexity of the environment, the optimization problem of jointly considering task offloading delay and RSU battery degradation is a nonconvex problem that is difficult to solve. Thus, this paper proposes transforms the problem into a Markov decision process and applies the Proximal Policy Optimization (PPO) algorithm to strike a balance between task offloading delay and RSU battery degradation. Experimental results have demonstrated the effectiveness of our proposal.