Maximizing DRL-based Energy Efficiency in IRS-NOMA using a DDPG Algorithm for the Next Generation of Wireless Communications

Combining Intelligent Reflecting Surfaces (IRSs) with Non-Orthogonal Multiple Access (NOMA) effectively enhances communication. This study introduces a NOMA-assisted Downlink Transmission (DT) system, emphasizing Energy Efficiency (EE) optimization. EE, crucial in Wireless Communications (WCs), measures data transmission relative to energy consumption. This study focuses on a Deep Deterministic Policy Gradient (DDPG) algorithm that intelligently adjusts IRS phase-shift matrices and access point beamforming in NOMA DT. Beamforming directs signals to users for optimal strength and quality, while phase shift control enhances signal coverage and quality. Strategic IRS placement improves user signal transmissions. The simulation results demonstrate significantly improved EE compared to other algorithms, such as Deep Q Network (DQN) and Proximal Policy Optimization (PPO), showcasing the effectiveness of the combined IRS and NOMA approach in enhancing communication systems' EE.