Reconfigurable Intelligent Surface Aided Vehicular Edge Computing: Joint Phase-shift Optimization and Multi-User Power Allocation

TL;DR

This paper proposes a novel deep reinforcement learning framework for optimizing reconfigurable intelligent surface phase-shifts and power allocation in vehicular edge computing, significantly enhancing communication and computational efficiency.

Contribution

It introduces a joint optimization scheme using DRL algorithms for RIS phase-shift and power control in VEC systems, addressing channel variability and task randomness.

Findings

Outperforms traditional DDPG, TD3, and stochastic schemes in simulations.

Enhances communication reliability and computational efficiency in RIS-assisted VEC.

Demonstrates the effectiveness of DRL-based joint optimization in dynamic vehicular environments.

Abstract

Vehicular edge computing (VEC) is an emerging technology with significant potential in the field of internet of vehicles (IoV), enabling vehicles to perform intensive computational tasks locally or offload them to nearby edge devices. However, the quality of communication links may be severely deteriorated due to obstacles such as buildings, impeding the offloading process. To address this challenge, we introduce the use of Reconfigurable Intelligent Surfaces (RIS), which provide alternative communication pathways to assist vehicular communication. By dynamically adjusting the phase-shift of the RIS, the performance of VEC systems can be substantially improved. In this work, we consider a RIS-assisted VEC system, and design an optimal scheme for local execution power, offloading power, and RIS phase-shift, where random task arrivals and channel variations are taken into account. To address the scheme, we propose an innovative deep reinforcement learning (DRL) framework that combines the Deep Deterministic Policy Gradient (DDPG) algorithm for optimizing RIS phase-shift coefficients and the Multi-Agent Deep Deterministic Policy Gradient (MADDPG) algorithm for optimizing the power allocation of vehicle user (VU). Simulation results show that our proposed scheme outperforms the traditional centralized DDPG, Twin Delayed Deep Deterministic Policy Gradient (TD3) and some typical stochastic schemes.