Active Sensing for Multiuser Beam Tracking with Reconfigurable Intelligent Surface

TL;DR

A deep learning framework utilizing a recurrent neural network (RNN) to automatically summarize the time-varying CSI obtained from the periodically received pilots into state vectors, which are mapped to the AP beamformers and RIS reflection coefficients for subsequent downlink data transmissions.

Abstract

This paper studies a beam tracking problem in which an access point (AP), in collaboration with a reconfigurable intelligent surface (RIS), dynamically adjusts its downlink beamformers and the reflection pattern at the RIS in order to maintain reliable communications with multiple mobile user equipments (UEs). Specifically, the mobile UEs send uplink pilots to the AP periodically during the channel sensing intervals, the AP then adaptively configures the beamformers and the RIS reflection coefficients for subsequent data transmission based on the received pilots. This is an active sensing problem, because channel sensing involves configuring the RIS coefficients during the pilot stage and the optimal sensing strategy should exploit the trajectory of channel state information (CSI) from previously received pilots. Analytical solution to such an active sensing problem is very challenging. In this paper, we propose a deep learning framework utilizing a recurrent neural network (RNN) to automatically summarize the time-varying CSI obtained from the periodically received pilots into state vectors. These state vectors are then mapped to the AP beamformers and RIS reflection coefficients for subsequent downlink data transmissions, as well as the RIS reflection coefficients for the next round of uplink channel sensing. The mappings from the state vectors to the downlink beamformers and the RIS reflection coefficients for both channel sensing and downlink data transmission are performed using graph neural networks (GNNs) to account for the interference among the UEs. Simulations demonstrate significant and interpretable performance improvement of the proposed approach over the existing data-driven methods with nonadaptive channel sensing schemes.

Figures (15)

• Figure 1: RIS assisted multiuser mobile communication system.
• Figure 2: Frame structure of the proposed transmission protocol.
• Figure 3: Overall graph neural network architecture with an initialization layer, $D$ updating layers, and a final normalization layer.
• Figure 4: Active sensing unit for multiuser beam tracking with RIS.
• Figure 5: Proposed active sensing framework for multiuser beam tracking with RIS. During the training phase, we concatenate $U$ active sensing units corresponding to $U$ transmission frames. Once trained and deployed, we reuse the active sensing units for a potentially infinite number of transmission frames.