Numerical analysis of artificial neural network and volterra-based nonlinear equalizers for coherent optical OFDM

Elias Giacoumidis, Jinlong Wei, Mutsam A. Jarajreh, Son T. Le, Paul A. Haigh, Jan Bohata, Andreas Perentos, Sofien Mhatli, Mohammad Ghanbarisabagh, Ivan Aldaya, Nick J. Doran

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

One major drawback of coherent optical orthogonal frequency-division multiplexing (CO-OFDM) that hitherto remains unsolved is its vulnerability to nonlinear fiber effects due to its high peak-to-average power ratio. Several digital signal processing techniques have been investigated for the compensation of fiber nonlinearities, e.g., digital back-propagation, nonlinear pre- and post-compensation and nonlinear equalizers (NLEs) based on the inverse Volterra-series transfer function (IVSTF). Alternatively, nonlinearities can be mitigated using nonlinear decision classifiers such as artificial neural networks (ANNs) based on a multilayer perceptron. In this paper, ANN-NLE is presented for a 16QAM CO-OFDM system. The capability of the proposed approach to compensate the fiber nonlinearities is numerically demonstrated for up to 100-Gb/s and over 1000km and compared to the benchmark IVSTF-NLE. Results show that in terms of Q-factor, for 100-Gb/s at 1000km of transmission, ANN-NLE outperforms linear equalization and IVSTF-NLE by 3.2dB and 1dB, respectively.

Original languageEnglish
Title of host publicationPIERS 2015 Prague
Subtitle of host publicationProgress in Electromagnetics Research Symposium, proceedings
Place of PublicationCambridge, MA (US)
PublisherElectromagnetics Academy
Pages2473-2477
Number of pages5
ISBN (Print)978-1-934142-30-1
Publication statusPublished - 2015
EventProgress in Electromagnetics Research Symposium - Prague, Czech Republic
Duration: 6 Jul 20156 Jul 2015

Publication series

NamePIERS proceedings
PublisherElectromagnetics Academy
ISSN (Print)1559-9450
ISSN (Electronic)1931-7360

Symposium

SymposiumProgress in Electromagnetics Research Symposium
Abbreviated titlePIERS 2015 Prague
CountryCzech Republic
CityPrague
Period6/07/156/07/15

Fingerprint

Equalizers
Orthogonal frequency division multiplexing
Numerical analysis
Neural networks
Transfer functions
Fibers
Multilayer neural networks
Digital signal processing
Backpropagation
Classifiers
Compensation and Redress

Bibliographical note

Funding: EU 7FP (FP/2007-2013) under grant 318137 (DISCUS).

Cite this

Giacoumidis, E., Wei, J., Jarajreh, M. A., Le, S. T., Haigh, P. A., Bohata, J., ... Doran, N. J. (2015). Numerical analysis of artificial neural network and volterra-based nonlinear equalizers for coherent optical OFDM. In PIERS 2015 Prague: Progress in Electromagnetics Research Symposium, proceedings (pp. 2473-2477). (PIERS proceedings). Cambridge, MA (US): Electromagnetics Academy.
Giacoumidis, Elias ; Wei, Jinlong ; Jarajreh, Mutsam A. ; Le, Son T. ; Haigh, Paul A. ; Bohata, Jan ; Perentos, Andreas ; Mhatli, Sofien ; Ghanbarisabagh, Mohammad ; Aldaya, Ivan ; Doran, Nick J. / Numerical analysis of artificial neural network and volterra-based nonlinear equalizers for coherent optical OFDM. PIERS 2015 Prague: Progress in Electromagnetics Research Symposium, proceedings. Cambridge, MA (US) : Electromagnetics Academy, 2015. pp. 2473-2477 (PIERS proceedings).
@inproceedings{31b26257858e483194e0dad4fc93b2fd,
title = "Numerical analysis of artificial neural network and volterra-based nonlinear equalizers for coherent optical OFDM",
abstract = "One major drawback of coherent optical orthogonal frequency-division multiplexing (CO-OFDM) that hitherto remains unsolved is its vulnerability to nonlinear fiber effects due to its high peak-to-average power ratio. Several digital signal processing techniques have been investigated for the compensation of fiber nonlinearities, e.g., digital back-propagation, nonlinear pre- and post-compensation and nonlinear equalizers (NLEs) based on the inverse Volterra-series transfer function (IVSTF). Alternatively, nonlinearities can be mitigated using nonlinear decision classifiers such as artificial neural networks (ANNs) based on a multilayer perceptron. In this paper, ANN-NLE is presented for a 16QAM CO-OFDM system. The capability of the proposed approach to compensate the fiber nonlinearities is numerically demonstrated for up to 100-Gb/s and over 1000km and compared to the benchmark IVSTF-NLE. Results show that in terms of Q-factor, for 100-Gb/s at 1000km of transmission, ANN-NLE outperforms linear equalization and IVSTF-NLE by 3.2dB and 1dB, respectively.",
author = "Elias Giacoumidis and Jinlong Wei and Jarajreh, {Mutsam A.} and Le, {Son T.} and Haigh, {Paul A.} and Jan Bohata and Andreas Perentos and Sofien Mhatli and Mohammad Ghanbarisabagh and Ivan Aldaya and Doran, {Nick J.}",
note = "Funding: EU 7FP (FP/2007-2013) under grant 318137 (DISCUS).",
year = "2015",
language = "English",
isbn = "978-1-934142-30-1",
series = "PIERS proceedings",
publisher = "Electromagnetics Academy",
pages = "2473--2477",
booktitle = "PIERS 2015 Prague",

}

Giacoumidis, E, Wei, J, Jarajreh, MA, Le, ST, Haigh, PA, Bohata, J, Perentos, A, Mhatli, S, Ghanbarisabagh, M, Aldaya, I & Doran, NJ 2015, Numerical analysis of artificial neural network and volterra-based nonlinear equalizers for coherent optical OFDM. in PIERS 2015 Prague: Progress in Electromagnetics Research Symposium, proceedings. PIERS proceedings, Electromagnetics Academy, Cambridge, MA (US), pp. 2473-2477, Progress in Electromagnetics Research Symposium, Prague, Czech Republic, 6/07/15.

Numerical analysis of artificial neural network and volterra-based nonlinear equalizers for coherent optical OFDM. / Giacoumidis, Elias; Wei, Jinlong; Jarajreh, Mutsam A.; Le, Son T.; Haigh, Paul A.; Bohata, Jan; Perentos, Andreas; Mhatli, Sofien; Ghanbarisabagh, Mohammad; Aldaya, Ivan; Doran, Nick J.

PIERS 2015 Prague: Progress in Electromagnetics Research Symposium, proceedings. Cambridge, MA (US) : Electromagnetics Academy, 2015. p. 2473-2477 (PIERS proceedings).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Numerical analysis of artificial neural network and volterra-based nonlinear equalizers for coherent optical OFDM

AU - Giacoumidis, Elias

AU - Wei, Jinlong

AU - Jarajreh, Mutsam A.

AU - Le, Son T.

AU - Haigh, Paul A.

AU - Bohata, Jan

AU - Perentos, Andreas

AU - Mhatli, Sofien

AU - Ghanbarisabagh, Mohammad

AU - Aldaya, Ivan

AU - Doran, Nick J.

N1 - Funding: EU 7FP (FP/2007-2013) under grant 318137 (DISCUS).

PY - 2015

Y1 - 2015

N2 - One major drawback of coherent optical orthogonal frequency-division multiplexing (CO-OFDM) that hitherto remains unsolved is its vulnerability to nonlinear fiber effects due to its high peak-to-average power ratio. Several digital signal processing techniques have been investigated for the compensation of fiber nonlinearities, e.g., digital back-propagation, nonlinear pre- and post-compensation and nonlinear equalizers (NLEs) based on the inverse Volterra-series transfer function (IVSTF). Alternatively, nonlinearities can be mitigated using nonlinear decision classifiers such as artificial neural networks (ANNs) based on a multilayer perceptron. In this paper, ANN-NLE is presented for a 16QAM CO-OFDM system. The capability of the proposed approach to compensate the fiber nonlinearities is numerically demonstrated for up to 100-Gb/s and over 1000km and compared to the benchmark IVSTF-NLE. Results show that in terms of Q-factor, for 100-Gb/s at 1000km of transmission, ANN-NLE outperforms linear equalization and IVSTF-NLE by 3.2dB and 1dB, respectively.

AB - One major drawback of coherent optical orthogonal frequency-division multiplexing (CO-OFDM) that hitherto remains unsolved is its vulnerability to nonlinear fiber effects due to its high peak-to-average power ratio. Several digital signal processing techniques have been investigated for the compensation of fiber nonlinearities, e.g., digital back-propagation, nonlinear pre- and post-compensation and nonlinear equalizers (NLEs) based on the inverse Volterra-series transfer function (IVSTF). Alternatively, nonlinearities can be mitigated using nonlinear decision classifiers such as artificial neural networks (ANNs) based on a multilayer perceptron. In this paper, ANN-NLE is presented for a 16QAM CO-OFDM system. The capability of the proposed approach to compensate the fiber nonlinearities is numerically demonstrated for up to 100-Gb/s and over 1000km and compared to the benchmark IVSTF-NLE. Results show that in terms of Q-factor, for 100-Gb/s at 1000km of transmission, ANN-NLE outperforms linear equalization and IVSTF-NLE by 3.2dB and 1dB, respectively.

UR - http://www.scopus.com/inward/record.url?scp=84947232228&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84947232228

SN - 978-1-934142-30-1

T3 - PIERS proceedings

SP - 2473

EP - 2477

BT - PIERS 2015 Prague

PB - Electromagnetics Academy

CY - Cambridge, MA (US)

ER -

Giacoumidis E, Wei J, Jarajreh MA, Le ST, Haigh PA, Bohata J et al. Numerical analysis of artificial neural network and volterra-based nonlinear equalizers for coherent optical OFDM. In PIERS 2015 Prague: Progress in Electromagnetics Research Symposium, proceedings. Cambridge, MA (US): Electromagnetics Academy. 2015. p. 2473-2477. (PIERS proceedings).