Deep Learning-Based Tri-Hybrid Multi-User MIMO Precoding: The Blessing of EM-Reconfigurable Antennas

2026-09-30

AI Summary

This study addresses the challenge of jointly designing electromagnetic, analog, and digital precoding in wideband multi-user MIMO systems by proposing Tri-PNet, an unsupervised Conformer-based triple-hybrid precoding network. To the best of our knowledge, this work is the first to unify the optimization of all three precoding stages for spectral efficiency maximization. Tri-PNet integrates the local modeling capabilities of convolutions with the global dependency capture of Transformers, further incorporating cross-attention mechanisms and SVD/ZF prior-guided strategies. Experimental results demonstrate that Tri-PNet significantly outperforms conventional methods, closely approaching the greedy search upper bound while maintaining low computational complexity. Moreover, the proposed architecture exhibits strong robustness against imperfect channel state information, highlighting its practical viability for next-generation wireless communications.

Abstract

Electromagnetic (EM)-reconfigurable antennas provide multiple candidate radiation patterns per element, thereby introducing an additional EM-domain degree of freedom. Integrating radiation-pattern reconfigurability, realized as EM-domain precoding, with conventional hybrid analog-digital precoding yields tri-hybrid multiple-input multiple-output (MIMO) precoding, which can substantially improve the spectral efficiency of wideband multi-user MIMO orthogonal frequency-division multiplexing (OFDM) systems. However, the joint design of EM, analog, and digital precoding remains challenging. To address this challenge, we propose a tri-hybrid precoding network (Tri-PNet) based on Conformer, an emerging neural architecture that combines the local modeling strength of convolutional neural networks with the global dependency modeling of Transformers. Furthermore, two representative radiation-pattern modes, i.e., the non-regular mode and the 3rd Generation Partnership Project (3GPP) Technical Report (TR) 38.901 mode, are investigated. Tri-PNet is trained in an unsupervised manner to jointly learn EM, analog, and digital precoding by maximizing the average sum spectral efficiency. Its radiation-pattern selection network (RPSNet) employs a Conformer encoder to capture both local and global frequency-domain correlations, whereas its hybrid analog-digital precoding network (HPNet) combines cross-attention and dual-path processing with singular-value-decomposition (SVD) and zero-forcing (ZF) priors. Simulation results under both radiation-pattern modes demonstrate that Tri-PNet outperforms random EM precoding and conventional hybrid MIMO without EM precoding, approaches the greedy EM precoding search scheme with substantially lower online complexity, and remains robust to imperfect channel state information (CSI).

Problem

• Tri-hybrid precoding
• Multi-user MIMO
• EM-reconfigurable antennas
• Spectral efficiency
• Joint design

Innovation

• Tri-hybrid precoding
• EM-reconfigurable antennas
• Conformer
• Unsupervised learning
• MIMO-OFDM