Convolutional neural networks with multiple layers per span for nonlinearity mitigation in long-haul WDM transmission systems

Oleg Sidelnikov, Alexey Redyuk, Stylianos Sygletos, Mikhail Fedoruk, Sergei Turitsyn

Research output: Chapter in Book/Published conference outputConference publication

Abstract

Overcoming fiber nonlinearity is one of the most challenging tasks in optical fiber links and it is a major limiting factor for extending their capacity. Digital backward propagation (DBP) method can be used to mitigate nonlinear transmission impairments [1] , but its complexity prevents any real-time implementation in these systems. On the other hand, it has been recently shown that deep neural networks can provide a good approximation of DBP at lower computational cost [2] . In this work, we continue the investigation of the proposed deep convolutional neural network (DCNN) [3] for long-haul WDM transmission systems. We study the effect of the number of neural network layers on the efficiency of nonlinear distortion compensation.
Original languageEnglish
Title of host publicationThe European Conference on Lasers and Electro-Optics, CLEO/Europe 2021
PublisherThe Optical Society
Number of pages1
ISBN (Electronic)9781557528209
DOIs
Publication statusPublished - 30 Sep 2021
Event2021 European Conference on Lasers and Electro-Optics, CLEO/Europe 2021 - Virtual, Online, Germany
Duration: 21 Jun 202125 Jun 2021

Publication series

NameOptics InfoBase Conference Papers

Conference

Conference2021 European Conference on Lasers and Electro-Optics, CLEO/Europe 2021
Country/TerritoryGermany
CityVirtual, Online
Period21/06/2125/06/21

Bibliographical note

Funding Information:
The work was supported by the Russian Science Foundation (Grant No. 17-72-30006).

Fingerprint

Dive into the research topics of 'Convolutional neural networks with multiple layers per span for nonlinearity mitigation in long-haul WDM transmission systems'. Together they form a unique fingerprint.

Cite this