Abstract
Providing satisfactory quality of service (QoS) in high-speed railway (HSR) network is being strangled by external interference as well as jamming. To address this issue, we study the reconfigurable intelligent surface (RIS)-aided HSR network, where one RIS is deployed nearby the onboard mobile relay (MR) to suppress the interference as well as jamming in HSR system. Aiming at enhancing the HSR network capacity against the interference, we formulate an optimization problem for designing the phase shifts at the RIS. Since the HSR environment is time-varying and complicated, the optimization problem is challenging to settle. Inspired by the recent advances of deep reinforcement learning (DRL), we propose a deep deterministic policy gradient (DDPG)-based scheme to settle the problem through designing the action space, the state space as well as the reward function. Simulation results present that 1) deploying the RIS nearby the onboard MR is strongly facilitative of suppressing the interference; 2) the proposed DDPG scheme can achieve better capacity than the baseline schemes, and be gradually close to the upper boundary with the number of RIS elements increasing.