Physical Status Representation in Multiple Administrative Optical Networks by Federated Unsupervised Learning

We present our data-collection and deep neural network (DNN)-training scheme for extracting the optical status from signals received by digital coherent optical receivers in fiber-optic networks. The DNN is trained with unlabeled datasets across multiple administrative network domains by combining f...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEICE Transactions on Communications 2023/11/01, Vol.E106.B(11), pp.1084-1092
Hauptverfasser:	TANIMURA, Takahito, HIRAI, Riu, KIKUCHI, Nobuhiko
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial neural networks Datasets federated learning Fiber optics Machine learning monitoring Optical communication optical networks Optical receivers Quadrature phase shift keying Signal to noise ratio Unsupervised learning
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!