Deep learning-based beam alignment in mmWave vehicular networks

TL;DR

This paper introduces a deep learning approach to design structured compressed sensing matrices tailored for mmWave vehicular channels, enabling more efficient beam alignment with fewer measurements compared to traditional methods.

Contribution

The authors develop an end-to-end deep learning method to create CS matrices that exploit channel sparsity and spatial structure, improving beam alignment in vehicular networks.

Findings

Deep learning-designed CS matrices outperform random phase shift-based designs.

The approach reduces the number of measurements needed for effective beam alignment.

Simulation results show improved beam alignment accuracy in vehicular channels.

Abstract

Millimeter wave channels exhibit structure that allows beam alignment with fewer channel measurements than exhaustive beam search. From a compressed sensing (CS) perspective, the received channel measurements are usually obtained by multiplying a CS matrix with a sparse representation of the channel matrix. Due to the constraints imposed by analog processing, designing CS matrices that efficiently exploit the channel structure is, however, challenging. In this paper, we propose an end-to-end deep learning technique to design a structured CS matrix that is well suited to the underlying channel distribution, leveraging both sparsity and the particular spatial structure that appears in vehicular channels. The channel measurements acquired with the designed CS matrix are then used to predict the best beam for link configuration. Simulation results for vehicular communication channels indicate that our deep learning-based approach achieves better beam alignment than standard CS techniques that use the random phase shift-based design.