Skip navigation

mmWave Beam Selection in Analog Beamforming Using Personalized Federated Learning

Using analog beamforming in mmWave frequency bands, we can focus the energy towards a receiver to achieve high throughput. We propose a personalized Federated Learning (FL) method to address the challenge of quickly finding the best downlink beam configuration in the face of non-IID data.

With the method, we learn a mapping between uplink Sub-6GHz channel estimates and the best downlink beam in heterogeneous scenarios with non-IID characteristics. We also devise FEDLION, a FL implementation of the Lion optimization algorithm. Our approach reduces the signaling overhead and provides superior performance, up to 33.6 % higher accuracy than a single FL model and 6 % higher than a local model.


Martin Isaksson, Filippo Vannella, David Sandberg, Rickard Cöster

To be published in IEEE Future Networks World Forum 2023

©2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse.