A machine learning-based detection technique for optical fiber nonlinearity mitigation

Abdelkerim Amari; Xiang  Lin; Octavia A. Dobre; Ramachandran Venkatesan; Alex  Alvarado

doi:10.1109/LPT.2019.2902973

A machine learning-based detection technique for optical fiber nonlinearity mitigation

Abdelkerim Amari (Corresponding author)
, Xiang Lin
, Octavia A. Dobre
, Ramachandran Venkatesan
, Alex Alvarado

Research output: Contribution to journal › Article › Academic › peer-review

48 Citations (SciVal)

157 Downloads (Pure)

Abstract

We investigate the performance of a machine learning classi?cation technique, called the Parzen window, to mitigate the ?ber nonlinearity in the context of dispersion managed and dispersion unmanaged systems. The technique is applied for detection at the receiver side, and deals with the non-Gaussian nonlinear effects by designing improved decision boundaries. We also propose a two-stage mitigation technique using digital back propagation and Parzen window for dispersion unmanaged systems. In this case, digital back propagation compensates for the deterministic nonlinearity and the Parzen window deals with the stochastic nonlinear signal-noise interactions, which are not taken into account by digital back propagation. A performance improvement up to 0.4 dB in terms of Q factor is observed.

Original language	English
Article number	8660506
Pages (from-to)	627-630
Number of pages	4
Journal	IEEE Photonics Technology Letters
Volume	31
Issue number	8
DOIs	https://doi.org/10.1109/LPT.2019.2902973
Publication status	Published - 15 Apr 2019

Funding

Manuscript received October 29, 2018; revised January 4, 2019; accepted February 25, 2019. Date of publication March 5, 2019; date of current version April 2, 2019. This work was supported in part by the Atlantic Canada Opportunities Agency, in part by the Research Development Corporation Canada, and in part by the Netherlands Organisation for Scientific Research through the VIDI ICONIC under Project 15685. (Corresponding author: Abdelkerim Amari.) A. Amari was with the Faculty of Engineering and Applied Science, Memorial University, St. John’s, NL A1C 5S7, Canada. He is now with the Information and Communication Theory Lab, Signal Processing Systems Group, Department of Electrical Engineering, Eindhoven University of Technology, 5612 AZ Eindhoven, The Netherlands (e-mail: [email protected]).

Keywords

Digital back propagation
fiber nonlinearity mitigation
machine learning
optical communication systems
Parzen window

Access to Document

10.1109/LPT.2019.2902973

PTL_Amari_2018_VF_2Final author version , 415 KB

Cite this

@article{acd058a667924def9a4637e2a53f1a2e,

title = "A machine learning-based detection technique for optical fiber nonlinearity mitigation",

abstract = "We investigate the performance of a machine learning classi?cation technique, called the Parzen window, to mitigate the ?ber nonlinearity in the context of dispersion managed and dispersion unmanaged systems. The technique is applied for detection at the receiver side, and deals with the non-Gaussian nonlinear effects by designing improved decision boundaries. We also propose a two-stage mitigation technique using digital back propagation and Parzen window for dispersion unmanaged systems. In this case, digital back propagation compensates for the deterministic nonlinearity and the Parzen window deals with the stochastic nonlinear signal-noise interactions, which are not taken into account by digital back propagation. A performance improvement up to 0.4 dB in terms of Q factor is observed.",

keywords = "Digital back propagation, fiber nonlinearity mitigation, machine learning, optical communication systems, Parzen window",

author = "Abdelkerim Amari and Xiang Lin and Dobre, \{Octavia A.\} and Ramachandran Venkatesan and Alex Alvarado",

year = "2019",

month = apr,

day = "15",

doi = "10.1109/LPT.2019.2902973",

language = "English",

volume = "31",

pages = "627--630",

journal = "IEEE Photonics Technology Letters",

issn = "1041-1135",

publisher = "Institute of Electrical and Electronics Engineers",

number = "8",

}

TY - JOUR

T1 - A machine learning-based detection technique for optical fiber nonlinearity mitigation

AU - Amari, Abdelkerim

AU - Lin, Xiang

AU - Dobre, Octavia A.

AU - Venkatesan, Ramachandran

AU - Alvarado, Alex

PY - 2019/4/15

Y1 - 2019/4/15

N2 - We investigate the performance of a machine learning classi?cation technique, called the Parzen window, to mitigate the ?ber nonlinearity in the context of dispersion managed and dispersion unmanaged systems. The technique is applied for detection at the receiver side, and deals with the non-Gaussian nonlinear effects by designing improved decision boundaries. We also propose a two-stage mitigation technique using digital back propagation and Parzen window for dispersion unmanaged systems. In this case, digital back propagation compensates for the deterministic nonlinearity and the Parzen window deals with the stochastic nonlinear signal-noise interactions, which are not taken into account by digital back propagation. A performance improvement up to 0.4 dB in terms of Q factor is observed.

AB - We investigate the performance of a machine learning classi?cation technique, called the Parzen window, to mitigate the ?ber nonlinearity in the context of dispersion managed and dispersion unmanaged systems. The technique is applied for detection at the receiver side, and deals with the non-Gaussian nonlinear effects by designing improved decision boundaries. We also propose a two-stage mitigation technique using digital back propagation and Parzen window for dispersion unmanaged systems. In this case, digital back propagation compensates for the deterministic nonlinearity and the Parzen window deals with the stochastic nonlinear signal-noise interactions, which are not taken into account by digital back propagation. A performance improvement up to 0.4 dB in terms of Q factor is observed.

KW - Digital back propagation

KW - fiber nonlinearity mitigation

KW - machine learning

KW - optical communication systems

KW - Parzen window

UR - https://www.scopus.com/pages/publications/85064128451

U2 - 10.1109/LPT.2019.2902973

DO - 10.1109/LPT.2019.2902973

M3 - Article

AN - SCOPUS:85064128451

SN - 1041-1135

VL - 31

SP - 627

EP - 630

JO - IEEE Photonics Technology Letters

JF - IEEE Photonics Technology Letters

IS - 8

M1 - 8660506

ER -

A machine learning-based detection technique for optical fiber nonlinearity mitigation

Abstract

Funding

Keywords

Access to Document

Other files and links

Fingerprint

ICONIC: Increasing the Capacity of Optical Nonlinear Interfering Channels

Cite this

A machine learning-based detection technique for optical fiber nonlinearity mitigation

Abstract

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Projects

ICONIC: Increasing the Capacity of Optical Nonlinear Interfering Channels

Cite this