Deep learning for location based beamforming with NLOS channels

TL;DR

This paper introduces a neural network-based location to precoder mapping for Massive MIMO systems, reducing CSI acquisition overhead and effectively handling both LOS and NLOS channels.

Contribution

It proposes a novel deep learning approach using random Fourier features for location-based beamforming in NLOS channels, improving over previous methods.

Findings

Achieves promising results on synthetic channels

Handles both LOS and NLOS scenarios effectively

Reduces pilot symbol overhead in CSI acquisition

Abstract

Massive MIMO systems are highly efficient but critically rely on accurate channel state information (CSI) at the base station in order to determine appropriate precoders. CSI acquisition requires sending pilot symbols which induce an important overhead. In this paper, a method whose objective is to determine an appropriate precoder from the knowledge of the user's location only is proposed. Such a way to determine precoders is known as location based beamforming. It allows to reduce or even eliminate the need for pilot symbols, depending on how the location is obtained. the proposed method learns a direct mapping from location to precoder in a supervised way. It involves a neural network with a specific structure based on random Fourier features allowing to learn functions containing high spatial frequencies. It is assessed empirically and yields promising results on realistic synthetic channels. As opposed to previously proposed methods, it allows to handle both line-of-sight (LOS) and non-line-of-sight (NLOS) channels.