A Low-Complexity Plug-and-Play Deep Learning Model for Generalizable Massive MIMO Precoding

TL;DR

This paper introduces PaPP, a versatile deep learning-based precoding framework for massive MIMO systems that is robust, energy-efficient, and adaptable across different deployment scenarios without retraining from scratch.

Contribution

The paper presents a plug-and-play deep learning precoder that can be trained once and reused across various sites and conditions, incorporating meta-learning for domain generalization.

Findings

Outperforms conventional and DL baselines after minimal fine-tuning

Reduces computation energy by over 21 times

Maintains performance under channel estimation errors

Abstract

Massive multiple-input multiple-output (mMIMO) downlink precoding offers high spectral efficiency but remains challenging to deploy in practice because near-optimal algorithms such as the weighted minimum mean squared error (WMMSE) are computationally expensive, and sensitive to SNR and channel-estimation quality, while existing deep learning (DL)-based solutions often lack robustness and require retraining for each deployment site. This paper proposes a plug-and-play precoder (PaPP), a DL framework with a backbone that can be trained for either fully digital (FDP) or hybrid beamforming (HBF) precoding and reused across sites, transmit-power levels, and with varying amounts of channel estimation error, avoiding the need to train a new model from scratch at each deployment. PaPP combines a high-capacity teacher and a compact student with a self-supervised loss that balances teacher imitation and normalized sum-rate, trained using meta-learning domain-generalization and transmit-power-aware input normalization. Numerical results on ray-tracing data from three unseen sites show that the PaPP FDP and HBF models both outperform conventional and deep learning baselines, after fine-tuning with a small set of local unlabeled samples. Across both architectures, PaPP achieves more than 21$\times$ reduction in modeled computation energy and maintains good performance under channel-estimation errors, making it a practical solution for energy-efficient mMIMO precoding.