Learning-Based Massive Beamforming

TL;DR

This paper introduces convolutional neural networks for efficient massive beamforming in multi-user MIMO systems, addressing high-dimensionality and dynamic objectives with improved speed and throughput.

Contribution

It proposes a novel CMBNN architecture that leverages WMMSE structure for supervised and unsupervised learning in massive beamforming, overcoming traditional convergence issues.

Findings

CMBNN significantly reduces computation time.

CMBNN achieves higher system throughput.

The method effectively handles high-dimensional beamforming problems.

Abstract

Developing resource allocation algorithms with strong real-time and high efficiency has been an imperative topic in wireless networks. Conventional optimization-based iterative resource allocation algorithms often suffer from slow convergence, especially for massive multiple-input-multiple-output (MIMO) beamforming problems. This paper studies learning-based efficient massive beamforming methods for multi-user MIMO networks. The considered massive beamforming problem is challenging in two aspects. First, the beamforming matrix to be learned is quite high-dimensional in case with a massive number of antennas. Second, the objective is often time-varying and the solution space is not fixed due to some communication requirements. All these challenges make learning representation for massive beamforming an extremely difficult task. In this paper, by exploiting the structure of the most popular WMMSE beamforming solution, we propose convolutional massive beamforming neural networks (CMBNN) using both supervised and unsupervised learning schemes with particular design of network structure and input/output. Numerical results demonstrate the efficacy of the proposed CMBNN in terms of running time and system throughput.