Compensation of nonlinear distortion in coherent optical OFDM systems using a MIMO deep neural network-based equalizer

Ivan Aldaya; Elias Giacoumidis; Athanasios Tsokanos; Mutsam Jarajreh; Yannuo Wen; Jinlong Wei; Gabriel Campuzano; Marcelo L.F. Abbade; Liam P. Barry

doi:10.1364/OL.403778

Compensation of nonlinear distortion in coherent optical OFDM systems using a MIMO deep neural network-based equalizer

Ivan Aldaya, Elias Giacoumidis, Athanasios Tsokanos, Mutsam Jarajreh, Yannuo Wen, Jinlong Wei, Gabriel Campuzano, Marcelo L.F. Abbade, Liam P. Barry

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

4 Citations (Scopus)

Abstract

A novel nonlinear equalizer based on a multiple-input multiple-output (MIMO) deep neural network (DNN) is proposed and experimentally demonstrated for compensation of inter-subcarrier nonlinearities in a 40 Gb/s coherent optical orthogonal frequency division multiplexing system. Experimental results reveal that MIMO-DNN can extend the power margin by 4 dB at 2000 km of standard single-mode fiber transmission when compared to linear compensation or conventional single-input single-output DNN. It is also found that MIMO-DNN outperforms digital back propagation by increasing up to 1 dB the effective Q-factor and reducing by a factor of three the computational cost.

Original language	English
Pages (from-to)	5820-5823
Number of pages	4
Journal	Optics Letters
Volume	45
Issue number	20
DOIs	https://doi.org/10.1364/OL.403778
Publication status	Published - 15 Oct 2020

Access to Document

10.1364/OL.403778

Cite this

@article{132198c1e3104ad1a7d58d61b0099a22,

title = "Compensation of nonlinear distortion in coherent optical OFDM systems using a MIMO deep neural network-based equalizer",

abstract = "A novel nonlinear equalizer based on a multiple-input multiple-output (MIMO) deep neural network (DNN) is proposed and experimentally demonstrated for compensation of inter-subcarrier nonlinearities in a 40 Gb/s coherent optical orthogonal frequency division multiplexing system. Experimental results reveal that MIMO-DNN can extend the power margin by 4 dB at 2000 km of standard single-mode fiber transmission when compared to linear compensation or conventional single-input single-output DNN. It is also found that MIMO-DNN outperforms digital back propagation by increasing up to 1 dB the effective Q-factor and reducing by a factor of three the computational cost. ",

author = "Ivan Aldaya and Elias Giacoumidis and Athanasios Tsokanos and Mutsam Jarajreh and Yannuo Wen and Jinlong Wei and Gabriel Campuzano and Abbade, {Marcelo L.F.} and Barry, {Liam P.}",

note = "Funding Information: Funding. Funda{\c c}{\~a}o de Amparo {\`a} Pesquisa do Estado de S{\~a}o Paulo (2018/25339-4); Science Foundation Ireland (12/RC/2276, 13/RC/2077, 15/US-C2C/I3132); Conselho Nacional de Desenvolvimento Cient{\'i}fico e Tecnol{\'o}gico (311035/2018-3, 432303/2018-9). Publisher Copyright: {\textcopyright} 2020 Optical Society of America.",

year = "2020",

month = oct,

day = "15",

doi = "10.1364/OL.403778",

language = "English",

volume = "45",

pages = "5820--5823",

journal = "Optics Letters",

issn = "0146-9592",

publisher = "The Optical Society",

number = "20",

}

TY - JOUR

T1 - Compensation of nonlinear distortion in coherent optical OFDM systems using a MIMO deep neural network-based equalizer

AU - Aldaya, Ivan

AU - Giacoumidis, Elias

AU - Tsokanos, Athanasios

AU - Jarajreh, Mutsam

AU - Wen, Yannuo

AU - Wei, Jinlong

AU - Campuzano, Gabriel

AU - Abbade, Marcelo L.F.

AU - Barry, Liam P.

N1 - Funding Information: Funding. Fundação de Amparo à Pesquisa do Estado de São Paulo (2018/25339-4); Science Foundation Ireland (12/RC/2276, 13/RC/2077, 15/US-C2C/I3132); Conselho Nacional de Desenvolvimento Científico e Tecnológico (311035/2018-3, 432303/2018-9). Publisher Copyright: © 2020 Optical Society of America.

PY - 2020/10/15

Y1 - 2020/10/15

N2 - A novel nonlinear equalizer based on a multiple-input multiple-output (MIMO) deep neural network (DNN) is proposed and experimentally demonstrated for compensation of inter-subcarrier nonlinearities in a 40 Gb/s coherent optical orthogonal frequency division multiplexing system. Experimental results reveal that MIMO-DNN can extend the power margin by 4 dB at 2000 km of standard single-mode fiber transmission when compared to linear compensation or conventional single-input single-output DNN. It is also found that MIMO-DNN outperforms digital back propagation by increasing up to 1 dB the effective Q-factor and reducing by a factor of three the computational cost.

AB - A novel nonlinear equalizer based on a multiple-input multiple-output (MIMO) deep neural network (DNN) is proposed and experimentally demonstrated for compensation of inter-subcarrier nonlinearities in a 40 Gb/s coherent optical orthogonal frequency division multiplexing system. Experimental results reveal that MIMO-DNN can extend the power margin by 4 dB at 2000 km of standard single-mode fiber transmission when compared to linear compensation or conventional single-input single-output DNN. It is also found that MIMO-DNN outperforms digital back propagation by increasing up to 1 dB the effective Q-factor and reducing by a factor of three the computational cost.

UR - http://www.scopus.com/inward/record.url?scp=85093493084&partnerID=8YFLogxK

U2 - 10.1364/OL.403778

DO - 10.1364/OL.403778

M3 - Article

C2 - 33057293

AN - SCOPUS:85093493084

SN - 0146-9592

VL - 45

SP - 5820

EP - 5823

JO - Optics Letters

JF - Optics Letters

IS - 20

ER -

Compensation of nonlinear distortion in coherent optical OFDM systems using a MIMO deep neural network-based equalizer

Abstract

Access to Document

Other files and links

Fingerprint

Cite this