Unsupervised Support Vector Machines for Nonlinear Blind Equalization in CO-OFDM

Elias  Giacoumidis; Athanasios Tsokanos; M.  Ghanbarisabagh; S.  Mhatli; L. P.  Barry

doi:10.1109/LPT.2018.2832617

Unsupervised Support Vector Machines for Nonlinear Blind Equalization in CO-OFDM

Elias Giacoumidis, Athanasios Tsokanos, M. Ghanbarisabagh, S. Mhatli, L. P. Barry

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

6 Citations (Scopus)

24 Downloads (Pure)

Abstract

A novel blind nonlinear equalization (BNLE) technique based on the iterative re-weighted least square is experimentally demonstrated for single- and multi-channel coherent optical orthogonal frequency-division multiplexing. The adopted BNLE combines, for the first time, a support vector machine-learning cost function with the classical Sato or Godard error functions and maximum likelihood recursive least-squares. At optimum launched optical power, BNLE reduces the fiber nonlinearity penalty by ~1 (16-QAM single-channel at 2000 km) and ~1.7 dB (QPSK multi-channel at 3200 km) compared to a Volterra-based NLE. The proposed BNLE is more effective for multi-channel configuration: 1) it outperforms the “gold-standard” digital-back propagation and 2) for a high number of subcarriers the performance is better due to its capability of tackling inter-subcarrier four-wave mixing.

Original language	English
Pages (from-to)	1091 - 1094
Number of pages	4
Journal	IEEE Photonics Technology Letters
Volume	30
Issue number	12
Early online date	4 May 2018
DOIs	https://doi.org/10.1109/LPT.2018.2832617
Publication status	Published - 15 Jun 2018

Keywords

Optical OFDM
fiber nonlinearity compensation
machine learning
optical fiber communication

Access to Document

10.1109/LPT.2018.2832617

BlindNLE_PTL_2018 (002)Accepted author manuscript, 2.51 MB

Cite this

@article{62b2916756a9487e8309b64c876f2608,

title = "Unsupervised Support Vector Machines for Nonlinear Blind Equalization in CO-OFDM",

abstract = "A novel blind nonlinear equalization (BNLE) technique based on the iterative re-weighted least square is experimentally demonstrated for single- and multi-channel coherent optical orthogonal frequency-division multiplexing. The adopted BNLE combines, for the first time, a support vector machine-learning cost function with the classical Sato or Godard error functions and maximum likelihood recursive least-squares. At optimum launched optical power, BNLE reduces the fiber nonlinearity penalty by ~1 (16-QAM single-channel at 2000 km) and ~1.7 dB (QPSK multi-channel at 3200 km) compared to a Volterra-based NLE. The proposed BNLE is more effective for multi-channel configuration: 1) it outperforms the “gold-standard” digital-back propagation and 2) for a high number of subcarriers the performance is better due to its capability of tackling inter-subcarrier four-wave mixing.",

keywords = "Optical OFDM, fiber nonlinearity compensation, machine learning, optical fiber communication",

author = "Elias Giacoumidis and Athanasios Tsokanos and M. Ghanbarisabagh and S. Mhatli and Barry, {L. P.}",

note = "This document is the Accepted Manuscript of the following article: E. Giacoumidis, et al, 'Unsupervised Support Vector Machines for Nonlinear Blind Equalization in CO-OFDM', Vol. 30 (12): 1091-1094, June 2018. Under embargo until 4 May 2020. The final, published version is available online at doi: https://doi.org/10.1109/LPT.2018.2832617 {\textcopyright} 2018 IEEE",

year = "2018",

month = jun,

day = "15",

doi = "10.1109/LPT.2018.2832617",

language = "English",

volume = "30",

pages = "1091 -- 1094 ",

journal = "IEEE Photonics Technology Letters ",

issn = "1041-1135",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

number = "12",

}

TY - JOUR

T1 - Unsupervised Support Vector Machines for Nonlinear Blind Equalization in CO-OFDM

AU - Giacoumidis, Elias

AU - Tsokanos, Athanasios

AU - Ghanbarisabagh, M.

AU - Mhatli, S.

AU - Barry, L. P.

N1 - This document is the Accepted Manuscript of the following article: E. Giacoumidis, et al, 'Unsupervised Support Vector Machines for Nonlinear Blind Equalization in CO-OFDM', Vol. 30 (12): 1091-1094, June 2018. Under embargo until 4 May 2020. The final, published version is available online at doi: https://doi.org/10.1109/LPT.2018.2832617 © 2018 IEEE

PY - 2018/6/15

Y1 - 2018/6/15

N2 - A novel blind nonlinear equalization (BNLE) technique based on the iterative re-weighted least square is experimentally demonstrated for single- and multi-channel coherent optical orthogonal frequency-division multiplexing. The adopted BNLE combines, for the first time, a support vector machine-learning cost function with the classical Sato or Godard error functions and maximum likelihood recursive least-squares. At optimum launched optical power, BNLE reduces the fiber nonlinearity penalty by ~1 (16-QAM single-channel at 2000 km) and ~1.7 dB (QPSK multi-channel at 3200 km) compared to a Volterra-based NLE. The proposed BNLE is more effective for multi-channel configuration: 1) it outperforms the “gold-standard” digital-back propagation and 2) for a high number of subcarriers the performance is better due to its capability of tackling inter-subcarrier four-wave mixing.

AB - A novel blind nonlinear equalization (BNLE) technique based on the iterative re-weighted least square is experimentally demonstrated for single- and multi-channel coherent optical orthogonal frequency-division multiplexing. The adopted BNLE combines, for the first time, a support vector machine-learning cost function with the classical Sato or Godard error functions and maximum likelihood recursive least-squares. At optimum launched optical power, BNLE reduces the fiber nonlinearity penalty by ~1 (16-QAM single-channel at 2000 km) and ~1.7 dB (QPSK multi-channel at 3200 km) compared to a Volterra-based NLE. The proposed BNLE is more effective for multi-channel configuration: 1) it outperforms the “gold-standard” digital-back propagation and 2) for a high number of subcarriers the performance is better due to its capability of tackling inter-subcarrier four-wave mixing.

KW - Optical OFDM

KW - fiber nonlinearity compensation

KW - machine learning

KW - optical fiber communication

UR - http://www.scopus.com/inward/record.url?scp=85046469780&partnerID=8YFLogxK

U2 - 10.1109/LPT.2018.2832617

DO - 10.1109/LPT.2018.2832617

M3 - Article

SN - 1041-1135

VL - 30

SP - 1091

EP - 1094

JO - IEEE Photonics Technology Letters

JF - IEEE Photonics Technology Letters

IS - 12

ER -

Unsupervised Support Vector Machines for Nonlinear Blind Equalization in CO-OFDM

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this