Federated mmWave Beam Selection Utilizing LIDAR Data

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 vehicles has been leveraged reduce search overhead. In this letter, we propose federated aided selection method for V2I mmWave systems. proposed scheme, connected collaborate train shared neural network (NN) their locally available data during normal operation of system. We also reduced-complexity convolutional NN (CNN) classifier architecture and preprocessing, which significantly outperforms previous works terms both performance complexity.