Deep Learning based Fast and Accurate Beamforming for Millimeter-Wave Systems

TL;DR

This paper introduces BeamShaper, a deep learning framework that enables real-time, accurate beamforming in millimeter-wave systems, surpassing traditional LUT methods in speed, flexibility, and noise resilience.

Contribution

The paper presents a novel DNN-based beamforming method that generates array coefficients for any 3D direction in real-time, improving over fixed-beam LUTs.

Findings

BeamShaper achieves higher cosine-similarity and better angle accuracy than LUTs.

The approach is more resilient to quantization noise in digital phase-shifters.

Real-time beam steering is feasible with the proposed neural network model.

Abstract

The widespread proliferation of mmW devices has led to a surge of interest in antenna arrays. This interest in arrays is due to their ability to steer beams in desired directions, for the purpose of increasing signal-power and/or decreasing interference levels. To enable beamforming, array coefficients are typically stored in look-up tables (LUTs) for subsequent referencing. While LUTs enable fast sweep times, their limited memory size restricts the number of beams the array can produce. Consequently, a receiver is likely to be offset from the main beam, thus decreasing received power, and resulting in sub-optimal performance. In this letter, we present BeamShaper, a deep neural network (DNN) framework, which enables fast and accurate beamsteering in any desirable 3-D direction. Unlike traditional finite-memory LUTs which support a fixed set of beams, BeamShaper utilizes a trained NN model to generate the array coefficients for arbitrary directions in \textit{real-time}. Our simulations show that BeamShaper outperforms contemporary LUT based solutions in terms of cosine-similarity and central angle in time scales that are slightly higher than LUT based solutions. Additionally, we show that our DNN based approach has the added advantage of being more resilient to the effects of quantization noise generated while using digital phase-shifters.