Reinforcement Learning for Optimized Beam Training in Multi-Hop Terahertz Communications

TL;DR

This paper introduces a reinforcement learning-based hierarchical beam training scheme for multi-hop terahertz communications, significantly reducing training overhead and boosting spectral efficiency in high-frequency wireless links.

Contribution

It proposes a dynamic, joint optimization of beam training levels using a multi-armed bandit approach, improving over fixed-level schemes in multi-hop THz networks.

Findings

Achieves up to 75% spectral efficiency gain.

Demonstrates fast convergence in random channel conditions.

Effectively reduces training time overhead.

Abstract

Communication at terahertz (THz) frequency bands is a promising solution for achieving extremely high data rates in next-generation wireless networks. While the THz communication is conventionally envisioned for short-range wireless applications due to the high atmospheric absorption at THz frequencies, multi-hop directional transmissions can be enabled to extend the communication range. However, to realize multi-hop THz communications, conventional beam training schemes, such as exhaustive search or hierarchical methods with a fixed number of training levels, can lead to a very large time overhead. To address this challenge, in this paper, a novel hierarchical beam training scheme with dynamic training levels is proposed to optimize the performance of multi-hop THz links. In fact, an optimization problem is formulated to maximize the overall spectral efficiency of the multi-hop THz link by dynamically and jointly selecting the number of beam training levels across all the constituent single-hop links. To solve this problem in presence of unknown channel state information, noise, and path loss, a new reinforcement learning solution based on the multi-armed bandit (MAB) is developed. Simulation results show the fast convergence of the proposed scheme in presence of random channels and noise. The results also show that the proposed scheme can yield up to 75% performance gain, in terms of spectral efficiency, compared to the conventional hierarchical beam training with a fixed number of training levels.