Research on Energy Efficiency Optimization of IRS-NOMA Wireless Communication System Based on Deep Reinforcement Learning

In this study, the design of an energy-efficient IRS-NOMA wireless communication system based on Non-Orthogonal Multiple Access (NOMA) and Simultaneous Transmitting and Reflecting Reconfigurable Intelligent Surface (STAR-RIS) technologies is investigated. The study uses the Deep Deterministic Policy Gradient (DDPG) algorithm, a deep reinforcement learning approach, to jointly optimize the transmit beamforming vectors at the base station and the coefficient matrix at the STAR-RIS for maximizing Energy Efficiency (EE). This approach addresses the optimization challenges inherent in traditional methods.