Robust Hybrid Precoding for Millimeter Wave MU-MISO System Via Meta-Learning

TL;DR

This paper introduces a gradient-guided meta-learning framework for hybrid precoding in millimeter wave MU-MISO systems, achieving faster convergence and higher spectral efficiency without training data.

Contribution

It proposes a novel GGML-based hybrid precoding method that is training-free, plug-and-play, and effective even with imperfect channel information.

Findings

Significantly improves spectral efficiency.

Speeds up convergence by 8 times.

Outperforms fully digital WMMSE precoding.

Abstract

Thanks to the low cost and power consumption, hybrid analog-digital architectures are considered as a promising energy-efficient solution for massive multiple-input multiple-output (MIMO) systems. The key idea is to connect one RF chain to multiple antennas through low-cost phase shifters. However, due to the non-convex objective function and constraints, we propose a gradient-guided meta-learning (GGML) based alternating optimization framework to solve this challenging problem. The GGML based hybrid precoding framework is \textit{free-of-training} and \textit{plug-and-play}. Specifically, GGML feeds the raw gradient information into a neural network, leveraging gradient descent to alternately optimize sub-problems from a local perspective, while a lightweight neural network embedded within the meta-learning framework is updated from a global perspective. We also extend the proposed framework to include precoding with imperfect channel state information. Simulation results demonstrate that GGML can significantly enhance spectral efficiency, and speed up the convergence by 8 times faster compared to traditional approaches. Moreover, GGML could even outperform fully digital weighted minimum mean square error (WMMSE) precoding with the same number of antennas.