Sparse Identification for Nonlinear Optical communication systems

Mariia Sorokina; Stylianos Sygletos; Sergei Turitsyn

doi:10.1109/ICTON.2017.8024969

Sparse Identification for Nonlinear Optical communication systems

Mariia Sorokina^*, Stylianos Sygletos, Sergei Turitsyn

^*Corresponding author for this work

Research output: Chapter in Book/Published conference output › Conference publication

Abstract

We have developed a low complexity machine learning based nonlinear impairment equalization scheme and demonstrated its successful performance in SDM transmission links achieving compensation of both inter- and intra- channel Kerr-based nonlinear effects. The method operates in one sample per symbol and in one computational step. It is adaptive, i.e. it does not require a knowledge of system parameters, and it is scalable to different power levels and modulation formats. The method can be straightforwardly expanded to multi-channel systems and to any other type of nonlinear impairment.

Original language	English
Title of host publication	ICTON 2017 - 19th International Conference on Transparent Optical Networks
Publisher	IEEE
ISBN (Electronic)	9781538608586
DOIs	https://doi.org/10.1109/ICTON.2017.8024969
Publication status	Published - 4 Sept 2017
Event	19th International Conference on Transparent Optical Networks, ICTON 2017 - Girona, Catalonia, Spain Duration: 2 Jul 2017 → 6 Jul 2017

Conference

Conference	19th International Conference on Transparent Optical Networks, ICTON 2017
Country/Territory	Spain
City	Girona, Catalonia
Period	2/07/17 → 6/07/17

Bibliographical note

© Copyright 2017 IEEE - All rights reserved

Funding: EPSRC project UNLOC EP/J017582/1 and EU-FP7 INSPACE project under grant agreement N.619732

Keywords

fiber optic communications
machine learning
nonlinear analysis
spatial division multiplexing

Access to Document

10.1109/ICTON.2017.8024969

Sparse Identification for Nonlinear Optical Communication Systems
© Copyright 2017 IEEE - All rights reserved
Accepted author manuscript, 499 KB

Cite this

@inproceedings{e7c918e3292c484eb0b424328644154e,

title = "Sparse Identification for Nonlinear Optical communication systems",

abstract = "We have developed a low complexity machine learning based nonlinear impairment equalization scheme and demonstrated its successful performance in SDM transmission links achieving compensation of both inter- and intra- channel Kerr-based nonlinear effects. The method operates in one sample per symbol and in one computational step. It is adaptive, i.e. it does not require a knowledge of system parameters, and it is scalable to different power levels and modulation formats. The method can be straightforwardly expanded to multi-channel systems and to any other type of nonlinear impairment.",

keywords = "fiber optic communications, machine learning, nonlinear analysis, spatial division multiplexing",

author = "Mariia Sorokina and Stylianos Sygletos and Sergei Turitsyn",

note = "{\textcopyright} Copyright 2017 IEEE - All rights reserved Funding: EPSRC project UNLOC EP/J017582/1 and EU-FP7 INSPACE project under grant agreement N.619732; 19th International Conference on Transparent Optical Networks, ICTON 2017 ; Conference date: 02-07-2017 Through 06-07-2017",

year = "2017",

month = sep,

day = "4",

doi = "10.1109/ICTON.2017.8024969",

language = "English",

booktitle = "ICTON 2017 - 19th International Conference on Transparent Optical Networks",

publisher = "IEEE",

address = "United States",

}

TY - GEN

T1 - Sparse Identification for Nonlinear Optical communication systems

AU - Sorokina, Mariia

AU - Sygletos, Stylianos

AU - Turitsyn, Sergei

PY - 2017/9/4

Y1 - 2017/9/4

N2 - We have developed a low complexity machine learning based nonlinear impairment equalization scheme and demonstrated its successful performance in SDM transmission links achieving compensation of both inter- and intra- channel Kerr-based nonlinear effects. The method operates in one sample per symbol and in one computational step. It is adaptive, i.e. it does not require a knowledge of system parameters, and it is scalable to different power levels and modulation formats. The method can be straightforwardly expanded to multi-channel systems and to any other type of nonlinear impairment.

AB - We have developed a low complexity machine learning based nonlinear impairment equalization scheme and demonstrated its successful performance in SDM transmission links achieving compensation of both inter- and intra- channel Kerr-based nonlinear effects. The method operates in one sample per symbol and in one computational step. It is adaptive, i.e. it does not require a knowledge of system parameters, and it is scalable to different power levels and modulation formats. The method can be straightforwardly expanded to multi-channel systems and to any other type of nonlinear impairment.

KW - fiber optic communications

KW - machine learning

KW - nonlinear analysis

KW - spatial division multiplexing

UR - http://www.scopus.com/inward/record.url?scp=85030994991&partnerID=8YFLogxK

U2 - 10.1109/ICTON.2017.8024969

DO - 10.1109/ICTON.2017.8024969

M3 - Conference publication

AN - SCOPUS:85030994991

BT - ICTON 2017 - 19th International Conference on Transparent Optical Networks

PB - IEEE

T2 - 19th International Conference on Transparent Optical Networks, ICTON 2017

Y2 - 2 July 2017 through 6 July 2017

ER -

Sparse Identification for Nonlinear Optical communication systems

Abstract

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this