Learning Energy-Efficient Hardware Configurations for Massive MIMO Beamforming

TL;DR

This paper introduces an unsupervised deep learning approach to optimize energy efficiency in massive MIMO beamforming systems, effectively balancing spectral efficiency and energy consumption even with imperfect channel information.

Contribution

It develops a novel energy model and deep neural network framework for designing transmitter configurations in fully digital and hybrid beamforming systems, considering practical imperfect CSI.

Findings

Outperforms conventional methods in energy efficiency.

Robust to noise and trained with imperfect CSI.

Less complex and more adaptable to different user scenarios.

Abstract

Hybrid beamforming (HBF) and antenna selection are promising techniques for improving the energy efficiency~(EE) of massive multiple-input multiple-output~(mMIMO) systems. However, the transmitter architecture may contain several parameters that need to be optimized, such as the power allocated to the antennas and the connections between the antennas and the radio frequency chains. Therefore, finding the optimal transmitter architecture requires solving a non-convex mixed integer problem in a large search space. In this paper, we consider the problem of maximizing the EE of fully digital precoder~(FDP) and hybrid beamforming~(HBF) transmitters. First, we propose an energy model for different beamforming structures. Then, based on the proposed energy model, we develop an unsupervised deep learning method to maximize the EE by designing the transmitter configuration for FDP and HBF. The proposed deep neural networks can provide different trade-offs between spectral efficiency and energy consumption while adapting to different numbers of active users. Finally, to ensure that the proposed method can be implemented in practice, we investigate the ability of the model to be trained exclusively using imperfect channel state information~(CSI), both for the input to the deep learning model and for the calculation of the loss function. Simulation results show that the proposed solutions can outperform conventional methods in terms of EE while being trained with imperfect CSI. Furthermore, we show that the proposed solutions are less complex and more robust to noise than conventional methods.