Joint Channel Estimation and Reinforcement-Learning-Based Resource Allocation of Intelligent-Reflecting-Surface-Aided Multicell Mobile Edge Computing

Due to the massive computing demands of the Internet of Things, mobile edge computing (MEC) has been extensively investigated as a means of providing computation-intensive and latency-sensitive services at the network edge. With increasing density of base stations (BSs), users are simultaneously served by multiple BSs, leading to the multicell MEC environment. Intelligent reflecting surface (IRS) provides a promising solution for constructing the virtual Line-of-Sight (LoS) links between cell-edge users (CEUs) and BSs. In this article, we investigate the joint channel estimation and resource allocation in the IRS-aided multicell MEC system. Instead of assuming the perfect channel state information (CSI), we propose a three-phase channel estimation method to obtain the CSI. Our purpose is to minimize the total joint energy and latency cost (JELC) in terms of both task-execution latency and energy consumption in the IRS-aided multicell MEC problem by jointly optimizing the task offloading volume, precoding matrix, and IRS phase shifts. We propose a quadratically constrained program (QCP)-assisted proximal policy optimization (PPO) reinforcement learning algorithm with two modules (i.e., QCP optimizer and PPO agent) execute iteratively. The QCP optimizer is utilized to compute the offloading decision variables, and the PPO agent is adapted to determine the optimal channel precoding matrix and the phase shifts of IRS. Numerical results validate that our QCP-assisted PPO algorithm executes more rapidly than benchmarks. Moreover, the proposed QCP-assisted PPO algorithm delivers the best performance compared to benchmarks. Furthermore, the multicell IRS-aided MEC framework yields additional performance gains compared to those without IRS.

I. Introduction

The proliferation of complex and computation-intensive mobile applications due to the rapid growth of the Internet of Things (IoT) presents significant challenges for the limited resources of IoT mobile devices (MDs) [1]. In response to the aforementioned challenge, mobile edge computing (MEC) has emerged as a novel network architecture that leverages abundant computing and storage resources in close proximity to MDs [2]. With the increasing density of base stations (BSs) in 5G networks, reaching up to 50 BSs per square kilometer [3], mobile users may frequently move across different cells. As a result, a multicell environment arises, where users may be simultaneously covered by multiple BSs. However, edge servers in this environment have limited storage and computational capacities compared to cloud centers, which means that they can only support a subset of services and may struggle to handle peak demand. To mitigate this issue, users can send service requests to any nearby BS for processing. In such scenarios, neighboring MEC servers can collaboratively serve users at the cell edge when some servers’ resources become insufficient.