Towards FPGA Implementation of Neural Network-Based Nonlinearity Mitigation Equalizers in Coherent Optical Transmission Systems

Pedro J. Freire; Michael Anderson; Bernhard Spinnler; Thomas Bex; Jaroslaw E. Prilepsky; Tobias A. Eriksson; Nelson Costa; Wolfgang Schairer; Michaela Blott; Antonio Napoli; Sergei K. Turitsyn

Towards FPGA Implementation of Neural Network-Based Nonlinearity Mitigation Equalizers in Coherent Optical Transmission Systems

Pedro J. Freire^*, Michael Anderson, Bernhard Spinnler, Thomas Bex, Jaroslaw E. Prilepsky, Tobias A. Eriksson, Nelson Costa, Wolfgang Schairer, Michaela Blott, Antonio Napoli, Sergei K. Turitsyn

^*Corresponding author for this work

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

Abstract

For the first time, recurrent and feedforward neural network-based equalizers for nonlinearity compensation are implemented in an FPGA, with a level of complexity comparable to that of a dispersion equalizer. We demonstrate that the NN-based equalizers can outperform a 1-step-per-span DBP.

Original language	English
Title of host publication	2022 European Conference on Optical Communication, ECOC 2022
Publisher	IEEE
Number of pages	4
ISBN (Electronic)	9781957171159
Publication status	Published - 20 Dec 2022
Event	2022 European Conference on Optical Communication, ECOC 2022 - Basel, Switzerland Duration: 18 Sept 2022 → 22 Sept 2022

Publication series

Name	2022 European Conference on Optical Communication, ECOC 2022

Conference

Conference	2022 European Conference on Optical Communication, ECOC 2022
Country/Territory	Switzerland
City	Basel
Period	18/09/22 → 22/09/22

Bibliographical note

Funding Information:
Acknowledgements: This work has been supported by the EU H2020 Marie Skodowska-Curie Action project REAL-NET (No. 813144) and EPSRC project TRANSNET.

Publisher Copyright:
© 2022 Optica.

Keywords

optical fibers
equalizers
Europe
artificicial neural networks
optical fiber networks
fiber nonlinear optics
complexity theory

Cite this

Freire, P. J., Anderson, M., Spinnler, B., Bex, T., Prilepsky, J. E., Eriksson, T. A., Costa, N., Schairer, W., Blott, M., Napoli, A., & Turitsyn, S. K. (2022). Towards FPGA Implementation of Neural Network-Based Nonlinearity Mitigation Equalizers in Coherent Optical Transmission Systems. In 2022 European Conference on Optical Communication, ECOC 2022 (2022 European Conference on Optical Communication, ECOC 2022). IEEE.

@inproceedings{aaeef00d44a94dccbc0b36b738b302ce,

title = "Towards FPGA Implementation of Neural Network-Based Nonlinearity Mitigation Equalizers in Coherent Optical Transmission Systems",

abstract = "For the first time, recurrent and feedforward neural network-based equalizers for nonlinearity compensation are implemented in an FPGA, with a level of complexity comparable to that of a dispersion equalizer. We demonstrate that the NN-based equalizers can outperform a 1-step-per-span DBP.",

keywords = "optical fibers, equalizers, Europe, artificicial neural networks, optical fiber networks, fiber nonlinear optics, complexity theory",

author = "Freire, {Pedro J.} and Michael Anderson and Bernhard Spinnler and Thomas Bex and Prilepsky, {Jaroslaw E.} and Eriksson, {Tobias A.} and Nelson Costa and Wolfgang Schairer and Michaela Blott and Antonio Napoli and Turitsyn, {Sergei K.}",

note = "Funding Information: Acknowledgements: This work has been supported by the EU H2020 Marie Skodowska-Curie Action project REAL-NET (No. 813144) and EPSRC project TRANSNET. Publisher Copyright: {\textcopyright} 2022 Optica.; 2022 European Conference on Optical Communication, ECOC 2022 ; Conference date: 18-09-2022 Through 22-09-2022",

year = "2022",

month = dec,

day = "20",

language = "English",

series = "2022 European Conference on Optical Communication, ECOC 2022",

publisher = "IEEE",

booktitle = "2022 European Conference on Optical Communication, ECOC 2022",

address = "United States",

}

Freire, PJ, Anderson, M, Spinnler, B, Bex, T, Prilepsky, JE, Eriksson, TA, Costa, N, Schairer, W, Blott, M, Napoli, A & Turitsyn, SK 2022, Towards FPGA Implementation of Neural Network-Based Nonlinearity Mitigation Equalizers in Coherent Optical Transmission Systems. in 2022 European Conference on Optical Communication, ECOC 2022. 2022 European Conference on Optical Communication, ECOC 2022, IEEE, 2022 European Conference on Optical Communication, ECOC 2022, Basel, Switzerland, 18/09/22.

Towards FPGA Implementation of Neural Network-Based Nonlinearity Mitigation Equalizers in Coherent Optical Transmission Systems. / Freire, Pedro J.; Anderson, Michael; Spinnler, Bernhard et al.
2022 European Conference on Optical Communication, ECOC 2022. IEEE, 2022. (2022 European Conference on Optical Communication, ECOC 2022).

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

TY - GEN

T1 - Towards FPGA Implementation of Neural Network-Based Nonlinearity Mitigation Equalizers in Coherent Optical Transmission Systems

AU - Freire, Pedro J.

AU - Anderson, Michael

AU - Spinnler, Bernhard

AU - Bex, Thomas

AU - Prilepsky, Jaroslaw E.

AU - Eriksson, Tobias A.

AU - Costa, Nelson

AU - Schairer, Wolfgang

AU - Blott, Michaela

AU - Napoli, Antonio

AU - Turitsyn, Sergei K.

N1 - Funding Information: Acknowledgements: This work has been supported by the EU H2020 Marie Skodowska-Curie Action project REAL-NET (No. 813144) and EPSRC project TRANSNET. Publisher Copyright: © 2022 Optica.

PY - 2022/12/20

Y1 - 2022/12/20

N2 - For the first time, recurrent and feedforward neural network-based equalizers for nonlinearity compensation are implemented in an FPGA, with a level of complexity comparable to that of a dispersion equalizer. We demonstrate that the NN-based equalizers can outperform a 1-step-per-span DBP.

AB - For the first time, recurrent and feedforward neural network-based equalizers for nonlinearity compensation are implemented in an FPGA, with a level of complexity comparable to that of a dispersion equalizer. We demonstrate that the NN-based equalizers can outperform a 1-step-per-span DBP.

KW - optical fibers

KW - equalizers

KW - Europe

KW - artificicial neural networks

KW - optical fiber networks

KW - fiber nonlinear optics

KW - complexity theory

UR - http://www.scopus.com/inward/record.url?scp=85146400459&partnerID=8YFLogxK

UR - https://ieeexplore.ieee.org/abstract/document/9979383

M3 - Conference publication

AN - SCOPUS:85146400459

T3 - 2022 European Conference on Optical Communication, ECOC 2022

BT - 2022 European Conference on Optical Communication, ECOC 2022

PB - IEEE

T2 - 2022 European Conference on Optical Communication, ECOC 2022

Y2 - 18 September 2022 through 22 September 2022

ER -

Towards FPGA Implementation of Neural Network-Based Nonlinearity Mitigation Equalizers in Coherent Optical Transmission Systems

Abstract

Publication series

Conference

Bibliographical note

Keywords

Other files and links

Fingerprint

Cite this