Federated Learning for Hybrid Beamforming in mm-Wave Massive MIMO
Yükleniyor...
Dosyalar
Tarih
2020
Yazarlar
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Ieee-Inst Electrical Electronics Engineers Inc
Erişim Hakkı
info:eu-repo/semantics/openAccess
Özet
Machine learning for hybrid beamforming has been extensively studied by using centralized machine learning (CML) techniques, which require the training of a global model with a large dataset collected from the users. However, the transmission of the whole dataset between the users and the base station (BS) is computationally prohibitive due to limited communication bandwidth and privacy concerns. In this work, we introduce a federated learning (FL) based framework for hybrid beamforming, where the model training is performed at the BS by collecting only the gradients from the users. We design a convolutional neural network, in which the input is the channel data, yielding the analog beamformers at the output. Via numerical simulations, FL is demonstrated to be more tolerant to the imperfections and corruptions in the channel data as well as having less transmission overhead than CML.
Açıklama
Anahtar Kelimeler
Training, Array signal processing, Artificial neural networks, Radio frequency, MIMO communication, Computational modeling, Unmanned aerial vehicles, Deep learning, federated learning, hybrid beamforming, massive MIMO, Design
Kaynak
Ieee Communications Letters
WoS Q Değeri
Q2
Scopus Q Değeri
Q1
Cilt
24
Sayı
12
