SCMA for STAR-RIS-Assisted UAV Networks: A DRL Approach for Energy Efficiency Maximization

This letter proposes a simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS)-aided downlink (DL) sparse code multiple access (SCMA) uncrewed aerial vehicle (UAV) network, where a UAV serves as an aerial base station to provide wireless communications. The objective is to maximize the total energy efficiency (EE) of the system. To achieve this, we introduce a deep reinforcement learning (DRL) framework to jointly optimize the SCMA mapping matrix (MM), power allocation (PA), UAV trajectory, and the phase shifts of the STAR-RIS. The DRL agent is trained using the proximal policy optimization (PPO) algorithm. Simulation results demonstrate the superior performance of the proposed framework over both power-domain non-orthogonal multiple access (PD-NOMA) and conventional RIS counterparts.