Energy-Efficient Design for a NOMA Assisted STAR-RIS Network With Deep Reinforcement Learning

Abstract

Simultaneous transmitting and reflecting reconfigurable intelligent surfaces (STAR-RISs) have been considered promising auxiliary devices to enhance the performance of the wireless network, where users located at different sides of the surfaces can be simultaneously served by the transmitting or reflecting signals. In this article, an energy efficiency (EE) optimization problem for non-orthogonal multiple access (NOMA) assisted STAR-RIS downlink network is investigated. Due to the fractional form of the objective function, it is challenging to solve the EE optimization problem using traditional convex optimization solutions. This article proposes a deep deterministic policy gradient (DDPG)-based algorithm to maximize the EE by jointly optimizing the transmission beamforming vectors at the base station and the coefficients matrices at the STAR-RIS. Simulation results demonstrate that the proposed algorithm can effectively maximize the system EE considering the time-varying channels.