Federated mmWave Beam Selection Utilizing LIDAR Data

TL;DR

This paper introduces a federated learning approach using LIDAR data and neural networks to improve beam selection in vehicle-to-infrastructure mmWave communication, reducing overhead and complexity.

Contribution

It presents a novel federated LIDAR-based beam selection method with a reduced-complexity CNN architecture for V2I mmWave systems, outperforming previous approaches.

Findings

Significant performance improvement over previous methods.

Reduced computational complexity of the CNN classifier.

Effective collaboration of vehicles in federated learning for beam selection.

Abstract

Efficient link configuration in millimeter wave (mmWave) communication systems is a crucial yet challenging task due to the overhead imposed by beam selection. For vehicle-to-infrastructure (V2I) networks, side information from LIDAR sensors mounted on the vehicles has been leveraged to reduce the beam search overhead. In this letter, we propose a federated LIDAR aided beam selection method for V2I mmWave communication systems. In the proposed scheme, connected vehicles collaborate to train a shared neural network (NN) on their locally available LIDAR data during normal operation of the system. We also propose a reduced-complexity convolutional NN (CNN) classifier architecture and LIDAR preprocessing, which significantly outperforms previous works in terms of both the performance and the complexity.