Graph Neural Network Based Hybrid Beamforming Design in Wideband Terahertz MIMO-OFDM Systems

TL;DR

This paper introduces a graph neural network-based hybrid beamforming method for wideband Terahertz MIMO-OFDM systems, effectively reducing complexity and maintaining high spectral efficiency despite beam squint effects.

Contribution

It proposes a novel GNN-based hybrid beamforming design tailored for wideband systems, improving efficiency and robustness over traditional methods.

Findings

Achieves near digital beamforming spectral efficiency

Reduces computational and memory requirements significantly

Maintains high performance under increasing bandwidth and frequency

Abstract

6G wireless technology is projected to adopt higher and wider frequency bands, enabled by highly directional beamforming. However, the vast bandwidths available also make the impact of beam squint in massive multiple input and multiple output (MIMO) systems non-negligible. Traditional approaches such as adding a true-time-delay line (TTD) on each antenna are costly due to the massive antenna arrays required. This paper puts forth a signal processing alternative, specifically adapted to the multicarrier structure of OFDM systems, through an innovative application of Graph Neural Networks (GNNs) to optimize hybrid beamforming. By integrating two types of graph nodes to represent the analog and the digital beamforming matrices efficiently, our approach not only reduces the computational and memory burdens but also achieves high spectral efficiency performance, approaching that of all digital beamforming. The GNN runtime and memory requirement are at a fraction of the processing time and resource consumption of traditional signal processing methods, hence enabling real-time adaptation of hybrid beamforming. Furthermore, the proposed GNN exhibits strong resiliency to beam squinting, achieving almost constant spectral efficiency even as the system bandwidth increases at higher carrier frequencies.