STAR Ri

Simultaneously transmitting and reflecting reconfigurable intelligent surfaces (STAR-RISs) are emerging as a key technology to enhance wireless communication coverage and capacity, particularly in challenging indoor or multi-hop scenarios. Current research focuses on optimizing STAR-RIS deployment, beamforming strategies (both active and passive), and resource allocation using techniques like deep reinforcement learning (various algorithms including DDPG, PPO, and multi-agent approaches) to maximize energy efficiency, sum throughput, and network utility, often in conjunction with non-orthogonal multiple access (NOMA). These advancements hold significant promise for improving the performance and efficiency of future wireless networks, particularly in dense urban environments and indoor settings.