Liquid State Machine-Empowered Reflection Tracking in RIS-Aided THz Communications

TL;DR

This paper introduces a deep learning framework using liquid state machines and ensemble techniques to accurately track RIS reflection coefficients in THz communications, significantly enhancing spectral efficiency.

Contribution

It proposes a novel two-step deep learning approach with LSMs and ensemble learning for RIS reflection coefficient prediction in THz systems.

Findings

Xavier initialization reduces LSM prediction variance by up to 26%.

Spectral efficiency improves by up to 46% with the proposed method.

Ensemble learning reduces prediction variance by 66% and increases spectral efficiency by 54%.

Abstract

Passive beamforming in reconfigurable intelligent surfaces (RISs) enables a feasible and efficient way of communication when the RIS reflection coefficients are precisely adjusted. In this paper, we present a framework to track the RIS reflection coefficients with the aid of deep learning from a time-series prediction perspective in a terahertz (THz) communication system. The proposed framework achieves a two-step enhancement over the similar learning-driven counterparts. Specifically, in the first step, we train a liquid state machine (LSM) to track the historical RIS reflection coefficients at prior time steps (known as a time-series sequence) and predict their upcoming time steps. We also fine-tune the trained LSM through Xavier initialization technique to decrease the prediction variance, thus resulting in a higher prediction accuracy. In the second step, we use ensemble learning technique which leverages on the prediction power of multiple LSMs to minimize the prediction variance and improve the precision of the first step. It is numerically demonstrated that, in the first step, employing the Xavier initialization technique to fine-tune the LSM results in at most 26% lower LSM prediction variance and as much as 46% achievable spectral efficiency (SE) improvement over the existing counterparts, when an RIS of size 11x11 is deployed. In the second step, under the same computational complexity of training a single LSM, the ensemble learning with multiple LSMs degrades the prediction variance of a single LSM up to 66% and improves the system achievable SE at most 54%.