Federated Learning for Channel Estimation in Conventional and RIS-Assisted Massive MIMO

TL;DR

This paper introduces a federated learning framework for channel estimation in massive MIMO systems, significantly reducing communication overhead while maintaining high accuracy, applicable to both conventional and RIS-assisted scenarios.

Contribution

It proposes a novel federated learning approach for channel estimation that reduces data transmission overhead compared to centralized methods in massive MIMO systems.

Findings

FL reduces communication overhead by approximately 16 times compared to CL.

The proposed CNN-based FL scheme achieves comparable performance to centralized learning.

Lower estimation error than existing ML-based channel estimation schemes.

Abstract

Machine learning (ML) has attracted a great research interest for physical layer design problems, such as channel estimation, thanks to its low complexity and robustness. Channel estimation via ML requires model training on a dataset, which usually includes the received pilot signals as input and channel data as output. In previous works, model training is mostly done via centralized learning (CL), where the whole training dataset is collected from the users at the base station (BS). This approach introduces huge communication overhead for data collection. In this paper, to address this challenge, we propose a federated learning (FL) framework for channel estimation. We design a convolutional neural network (CNN) trained on the local datasets of the users without sending them to the BS. We develop FL-based channel estimation schemes for both conventional and RIS (intelligent reflecting surface) assisted massive MIMO (multiple-input multiple-output) systems, where a single CNN is trained for two different datasets for both scenarios. We evaluate the performance for noisy and quantized model transmission and show that the proposed approach provides approximately 16 times lower overhead than CL, while maintaining satisfactory performance close to CL. Furthermore, the proposed architecture exhibits lower estimation error than the state-of-the-art ML-based schemes.