LSTM-based RIS Phase Shift Control for V2X Communication Systems

Abstract

With the rapid development of intelligent transportation systems (ITS), a growing number of vehicular applications have emerged to provide an entirely new experience for our daily life. To provide low-latency and high reliable services for these applications, there has been growing interest in reconfigurable intelligent surface (RIS)-aided vehicle-to-everything (V2X) systems. In this paper, we propose an entirely different deep learning (DL)-based phase shift control scheme for fast time-varying V2X channel. The proposed scheme, henceforth referred to as LSTM-based phase shift control for V2X (L-PSCV), learns temporal variation of channels from past pilot sequence and then uses them to find out the optimal phase shift for instantaneous channel. From the numerical experiments on the V2X system, we demonstrate that the proposed L-PSCV scheme outperforms the conventional schemes in terms of sum-rate.