Deep Reinforcement Learning Enabled Joint Deployment and Beamforming in STAR-RIS Assisted Networks

Abstract: In the new generation of wireless communication systems, reconfigurable intelligent surfaces (RIS) and simultaneously transmitting and reflecting reconfigurable intelligent surfaces (STAR-RIS) have become competitive network components to achieve intelligent and reconfigurable network environments. However, existing work has not fully studied the deployment freedom of STAR-RIS, which limits further improvements in network communication performance. Therefore, this paper proposes a solution based on a deep reinforcement learning algorithm to dynamically deploy STAR-RIS and hybrid beamforming to improve the total communication rate of users in mobile wireless networks. The paper constructs a STAR-RIS assisted multi-user multiple-input single-output (MU-MISO) mobile wireless network and jointly optimizes the dynamic deployment strategy of STAR-RIS and the hybrid beamforming strategy to maximize the long-term total communication rate of users. To solve this problem, the paper uses the Proximal Policy Optimization (PPO) algorithm to optimize the deployment of STAR-RIS and the joint beamforming strategy of STAR-RIS and the base station. The trained policy can maximize the downlink transmission rate of the system and meet the real-time decision-making needs of the system. Numerical simulation results show that compared with the traditional scheme without using STAR-RIS and fixed STAR-RIS deployment, the PPO method proposed in this paper can effectively improve the total communication rate of wireless network users in the service area.