Energy efficiency performance in RIS-based integrated satellite–aerial–terrestrial relay networks with deep reinforcement learning

Abstract

Integrated satellite–aerial–terrestrial relay networks (ISATRNs) play a vital role in next-gen networks, particularly those with high-altitude platforms (HAP). This study introduces a new model for hybrid optical/RF-based HAP-enabled ISATRNs, incorporating reconfigurable intelligent surfaces (RIS) on unmanned aerial vehicles (UAVs) to optimize access in dense urban areas. Non-orthogonal multiple access is employed for improved spectrum efficiency. The objective is to jointly optimize UAV trajectory, RIS phase shift, and active transmit beamforming while considering energy consumption. A deep reinforcement learning approach using LSTM-DDQN framework is proposed. Numerical results show the effectiveness of our algorithm over traditional DDQN, with higher single-step exploration reward and evaluation metrics.