An efficient computation offloading and resource allocation algorithm in RIS empowered MEC

Abstract

Mobile edge computing (MEC) enables mobile devices (MDs) to offload computation-intensive tasks to edge servers to support a variety of latency-sensitive emerging applications (such as the Internet of Vehicles, real-time video analytics, etc.). However, the time-varying communication link environment of signal occlusion and interference between MDs and edge servers often leads to disappointing offloading benefits. Reconfigurable intelligent surface (RIS) is recognized as a promising technology in sixth-generation communication networks, with great potential to intelligently adjust the phase shift and amplitude of reflective elements to enhance wireless network capabilities. This paper proposes a novel computation offloading algorithm for RIS empowered MEC networks. Specifically, we comprehensively consider the optimization problems of delay, energy consumption, and operator cost in the process of computation offloading, and model it as a Markov decision process. To overcome the continuous action space challenge, we propose a computation offloading algorithm based on Deep Deterministic Policy Gradient (DDPG) to jointly optimize the phase shift and amplitude of RIS, offloading decision, and MEC resource allocation strategy. Finally, compared with various other benchmark algorithms, our proposed algorithm has a significant performance improvement over non-RIS learning algorithms and other classical algorithms, and maintains the optimal performance.