A Low-Complexity Plug-and-Play Deep Learning Model for Massive MIMO Precoding Across Sites
This addresses complexity and generalization challenges in wireless communication for massive MIMO systems, though it is incremental as it builds on existing deep learning and meta-learning approaches.
The paper tackles the high computational complexity of existing massive MIMO precoding methods by proposing a deep learning-based model that uses meta-learning and a teacher-student architecture for generalization across sites. It achieves at least a 73x reduction in complexity while outperforming WMMSE in sum-rate performance across all tested sites and SNR conditions.
Massive multiple-input multiple-output (mMIMO) technology has transformed wireless communication by enhancing spectral efficiency and network capacity. This paper proposes a novel deep learning-based mMIMO precoder to tackle the complexity challenges of existing approaches, such as weighted minimum mean square error (WMMSE), while leveraging meta-learning domain generalization and a teacher-student architecture to improve generalization across diverse communication environments. When deployed to a previously unseen site, the proposed model achieves excellent sum-rate performance while maintaining low computational complexity by avoiding matrix inversions and by using a simpler neural network structure. The model is trained and tested on a custom ray-tracing dataset composed of several base station locations. The experimental results indicate that our method effectively balances computational efficiency with high sum-rate performance while showcasing strong generalization performance in unseen environments. Furthermore, with fine-tuning, the proposed model outperforms WMMSE across all tested sites and SNR conditions while reducing complexity by at least 73$\times$.