Active Beam Tracking with Reconfigurable Intelligent Surface

This paper studies a beam tracking problem in a reconfigurable intelligent surface (RIS)-assisted communication system, in which a single antenna access point (AP) tracks a single-antenna mobile user equipment (UE) through actively reconfiguring the RIS. To maintain beam alignment over time, the mobile UE periodically sends a sequence of pilots to the AP in the uplink, and the AP updates the RIS reflection coefficients for both the subsequent downlink data transmission and uplink pilot reception stages in a sequential fashion. This is an active sensing problem which is analytically intractable. This paper proposes a deep learning framework to solve this problem. We use a neural network architecture based on long short-term memory (LSTM) in which the LSTM cell automatically summarizes the time-varying channel information based on periodically received pilots into a state vector, and the state vector is mapped to the RIS reflection coefficients for subsequent downlink data transmission and uplink pilot reception using two additional deep neural networks (DNNs). Simulation results show that this proposed active sensing approach is able to maintain beam alignment much more efficiently than traditional data-driven methods based only on channel statistics.

1. INTRODUCTION

Reconfigurable intelligent surface (RIS) is a promising technology for integrated sensing and communications due to its ability to reflect incoming signals toward desired directions [1], [2], [3]. The RIS can enhance communication by establishing focused beams between the access point (AP) and the user equipment (UE), but this focusing capability depends crucially on channel sensing. In time-division duplex (TDD) systems with channel reciprocity, channel state information (CSI) acquisition for RIS-assisted systems can be done using uplink pilots [4], [5]. However, in high-mobility scenarios where CSI needs to be obtained more frequently, the existing schemes can lead to significant pilot overhead since they estimate CSI from scratch in each channel sensing phase without exploiting the temporal channel correlation due to UE mobility.