DRL-driven zero-RIS assisted energy-efficient task offloading in vehicular edge computing networks

Abstract

The increasing complexity of modern automotive applications presents difficulties when running them on the on-board units (OBUs) of vehicles. While 5G/6G vehicular edge computing networks (VECNs) offer potential solutions through computation task offloading, ensuring prompt, energy-efficient access to these networks remains a significant challenge. To overcome these challenges, reconfigurable intelligent surfaces (RIS) can play an important role in 6G vehicular networks. With RIS, networks can provide better connectivity, increased data rate and energy efficient access, and communication channel security. In this paper, we utilize zero-energy RIS (ze-RIS) to aid vehicular computation offloading while maximizing the energy and time savings while meeting the task and environmental constraints. A joint power and offloading mechanism controlling DRL-driven RIS-assisted energy efficient task offloading (DREEO) scheme is proposed. DREEO utilizes a hybrid approach that combines binary and partial offloading mechanisms, complemented by an intelligent communication link switching mechanism. This strategy helps in saving both energy and time effectively. An efficiency factor, serving as both a performance indicator and a reward function, is introduced for the DRL agent, considering both saved energy and time. Through extensive evaluations, DREEO scheme shown an increase in task success rate from 2.13% to 7.36% and has improved the efficiency factor from 21.97 to 51.27. Furthermore, compared to other evaluated schemes, the DREEO scheme consistently outperforms them in terms of reward and the TFPS ratio, the DRL properties.