Model-based learning for joint channel estimationand hybrid MIMO precoding

2025-05-07

AI Summary

To address hardware impairments-induced channel estimation errors and the computational intractability of jointly optimizing digital/analog hybrid precoding in massive MIMO systems, this paper proposes an end-to-end model-driven deep learning architecture. The method innovatively embeds unfolded matching pursuit—designed for robust channel estimation—and unfolded projected gradient ascent—for constrained hybrid precoding optimization—into a lightweight, interpretable neural network with minimal learnable parameters. By deeply integrating hardware impairment models and structural priors of hybrid MIMO channels, the architecture directly maps pilot signals to near-optimal hybrid precoders. Evaluated on realistic synthetic channels, the approach significantly outperforms conventional schemes in spectral efficiency and robustness, reduces computational overhead, and demonstrates strong resilience to calibration errors and phase noise.

Technology Category

• Machine Learning: Hardware-aware ML
• Search and Optimization: Learning to Search
• Natural Language Processing: Learning & Optimization for NLP

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Hybrid precoding is a key ingredient of cost-effective massive multiple-input multiple-output transceivers. However, setting jointly digital and analog precoders to optimally serve multiple users is a difficult optimization problem. Moreover, it relies heavily on precise knowledge of the channels, which is difficult to obtain, especially when considering realistic systems comprising hardware impairments. In this paper, a joint channel estimation and hybrid precoding method is proposed, which consists in an end-to-end architecture taking received pilots as inputs and outputting precoders. The resulting neural network is fully model-based, making it lightweight and interpretable with very few learnable parameters. The channel estimation step is performed using the unfolded matching pursuit algorithm, accounting for imperfect knowledge of the antenna system, while the precoding step is done via unfolded projected gradient ascent. The great potential of the proposed method is empirically demonstrated on realistic synthetic channels.

Problem

• Jointly optimizing digital and analog precoders for multi-user MIMO systems
• Overcoming channel estimation challenges with hardware impairments
• Developing lightweight model-based neural networks for hybrid precoding

Innovation

• Model-based neural network for hybrid precoding
• Unfolded matching pursuit for channel estimation
• Unfolded projected gradient ascent for precoding