Deep Learning Based Predictive Beamforming Design

TL;DR

This paper introduces a deep learning framework that predicts transmit beamforming directly from historical channel data, reducing estimation overhead and enhancing spectrum efficiency in high-mobility vehicular scenarios.

Contribution

It proposes a joint learning approach with attention-enhanced LSTM to improve beamforming prediction accuracy without current channel information.

Findings

Significant spectrum efficiency gains over traditional methods.

Effective channel prediction using attention-based LSTM.

Validated with autoregressive and 3GPP channel models.

Abstract

This paper investigates deep learning techniques to predict transmit beamforming based on only historical channel data without current channel information in the multiuser multiple-input-single-output downlink. This will significantly reduce the channel estimation overhead and improve the spectrum efficiency especially in high-mobility vehicular communications. Specifically, we propose a joint learning framework that incorporates channel prediction and power optimization, and produces prediction for transmit beamforming directly. In addition, we propose to use the attention mechanism in the Long Short-Term Memory Recurrent Neural Networks to improve the accuracy of channel prediction. Simulation results using both a simple autoregressive process model and the more realistic 3GPP spatial channel model verify that our proposed predictive beamforming scheme can significantly improve the effective spectrum efficiency compared to traditional channel estimation and the method that separately predicts channel and then optimizes beamforming.