Reconfigurable-Intelligent-Surface-Aided Vehicular Edge Computing: Joint Phase-Shift Optimization and Multiuser Power Allocation

2024-07-18

IEEE Internet of Things Journal

AI Summary

In vehicular networks, building blockages severely degrade communication link quality, thereby constraining task offloading performance in vehicular edge computing (VEC). To address this, this paper proposes a reconfigurable intelligent surface (RIS)-assisted VEC system that jointly optimizes RIS phase shifts and distributed local/offloading power allocation across multiple vehicles. We innovatively design a hybrid deep reinforcement learning framework integrating Deep Deterministic Policy Gradient (DDPG) and Multi-Agent DDPG (MADDPG), enabling online, coordinated optimization of RIS configuration and decentralized power control under dynamic task arrivals and fast time-varying channels. Compared with centralized DDPG, TD3, and random baselines, the proposed method significantly improves system performance: task completion rate and energy efficiency increase, average latency decreases by 23.6%, and throughput rises by 19.4%.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Intelligent Robots: Learning & Optimization for ROB
• Search and Optimization: Learning to Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

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 surface (RIS), which provide alternative communication pathways to assist vehicle communication. By dynamically adjusting the phase-shift of the RIS, the performance of VEC systems can be substantially improved. In this work, we consider an 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 multiagent DDPG (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 DDPG (TD3), and some typical stochastic schemes.

Problem

• Optimize RIS phase-shift for better VEC communication
• Allocate multi-user power efficiently in VEC systems
• Address random task arrivals and channel variations

Innovation

• Reconfigurable Intelligent Surfaces optimize phase-shift
• Deep reinforcement learning for power allocation
• Combines DDPG and MADDPG for VEC optimization