Transformer-Based Hybrid Beamforming with Reconfigurable Pixel Antenna for HAPS Communications

TL;DR

This paper introduces a Transformer-based hybrid beamforming framework with reconfigurable pixel antennas for HAPS communications, achieving high spectral efficiency with reduced computational complexity.

Contribution

It presents a novel pattern reconfigurable hybrid beamforming network utilizing Transformers and residual learning for efficient HAPS MIMO systems.

Findings

Approaches the spectral efficiency of greedy benchmarks.

Reduces computational complexity significantly.

Effective in reconfigurable pixel antenna systems.

Abstract

This paper proposes a Transformer-based hybrid beamforming framework for reconfigurable pixel antenna (RPA)-equipped massive multiple-input multiple-output (MIMO) in high-altitude platform station (HAPS) communications. The proposed pattern reconfigurable hybrid beamforming network (PR-HBFNet) comprises two key components: 1) a pattern reconfigurable network that leverages a Transformer encoder to determine the radiation pattern for each antenna element, and 2) a hybrid beamforming network that employs model-driven residual learning to compute analog and digital precoders over SVD-based initializations. Simulation results demonstrate that the proposed PR-HBFNet closely approaches the spectral efficiency of a greedy benchmark while significantly reducing computational complexity.