Achievable Rate Maximization for RIS-UAV Assisted Vehicular Communication Network

The Reconfigurable Intelligent Surface (RIS) is a promising paradigm in the 6G era and plays a crucial role in various wireless networks when integrated with the unmanned aerial vehicles (UAV). This article studies the RIS-assisted with UAV (RIS-UAV) in vehicular communication network, where RIS-UAV plays the role of a mobile passive relay to reflect the incident signal transmitted by the base station (BS). In the case of predicting the positions of the vehicle by UAV, the joint optimization scheme of UAV’s trail and RIS’s phase shift matrix is performed to maximize the achievable communication rate. Moreover, a deep reinforcement learning (DRL) algorithm is employed to tackle the optimization problem. The simulation results suggest that the utilized approach outperforms similar studies in maximizing the achievable communication rate.