Fibre impairment compensation using artificial neural network equalizer for high-capacity coherent optical OFDM signals

M.A. Jarajreh; S. Rajbhandari; E. Giacoumidis; N.J. Doran; Z. Ghassemlooy

doi:10.1109/CSNDSP.2014.6923996

Fibre impairment compensation using artificial neural network equalizer for high-capacity coherent optical OFDM signals

M.A. Jarajreh, S. Rajbhandari, E. Giacoumidis, N.J. Doran, Z. Ghassemlooy

Aston Institute of Photonic Technologies (AiPT)

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

7 Citations (Scopus)

Abstract

We propose an artificial neural network (ANN) equalizer for transmission performance enhancement of coherent optical OFDM (C-OOFDM) signals. The ANN equalizer showed more efficiency in combating both chromatic dispersion (CD) and single-mode fibre (SMF)-induced non-linearities compared to the least mean square (LMS). The equalizer can offer a 1.5 dB improvement in optical signal-to-noise ratio (OSNR) compared to LMS algorithm for 40 Gbit/s C-OOFDM signals when considering only CD. It is also revealed that ANN can double the transmission distance up to 320 km of SMF compared to the case of LMS, providing a nonlinearity tolerance improvement of ∼0.7 dB OSNR.

Original language	English
Title of host publication	2014 9th international symposium on Communication Systems, Networks and Digital Signl Processing, CSNDSP 2014
Publisher	IEEE
Pages	1112-1117
Number of pages	6
ISBN (Print)	978-1-4799-2581-0
DOIs	https://doi.org/10.1109/CSNDSP.2014.6923996
Publication status	Published - 31 Dec 2014
Event	9th IEEE/IET international symposium on Communication Systems, Networks and Digital Signl Processing - Manchester Metropolitan University, Manchester, United Kingdom Duration: 23 Jul 2014 → 25 Jul 2014

Symposium

Symposium	9th IEEE/IET international symposium on Communication Systems, Networks and Digital Signl Processing
Abbreviated title	CSNDSP 2014
Country/Territory	United Kingdom
City	Manchester
Period	23/07/14 → 25/07/14

Bibliographical note

Funding: EU FP7 project DISCUS (Grant Agreement 318137).

Keywords

artificial neural networks
coherent optical OFDM
functional link
nonlinear channel equalization
optical fibre communication

Access to Document

10.1109/CSNDSP.2014.6923996

Cite this

Jarajreh, M. A., Rajbhandari, S., Giacoumidis, E., Doran, N. J., & Ghassemlooy, Z. (2014). Fibre impairment compensation using artificial neural network equalizer for high-capacity coherent optical OFDM signals. In 2014 9th international symposium on Communication Systems, Networks and Digital Signl Processing, CSNDSP 2014 (pp. 1112-1117). IEEE. https://doi.org/10.1109/CSNDSP.2014.6923996

@inproceedings{a3ff6fbdb54b44f8a46c07c07e09b050,

title = "Fibre impairment compensation using artificial neural network equalizer for high-capacity coherent optical OFDM signals",

abstract = "We propose an artificial neural network (ANN) equalizer for transmission performance enhancement of coherent optical OFDM (C-OOFDM) signals. The ANN equalizer showed more efficiency in combating both chromatic dispersion (CD) and single-mode fibre (SMF)-induced non-linearities compared to the least mean square (LMS). The equalizer can offer a 1.5 dB improvement in optical signal-to-noise ratio (OSNR) compared to LMS algorithm for 40 Gbit/s C-OOFDM signals when considering only CD. It is also revealed that ANN can double the transmission distance up to 320 km of SMF compared to the case of LMS, providing a nonlinearity tolerance improvement of ∼0.7 dB OSNR.",

keywords = "artificial neural networks, coherent optical OFDM, functional link, nonlinear channel equalization, optical fibre communication",

author = "M.A. Jarajreh and S. Rajbhandari and E. Giacoumidis and N.J. Doran and Z. Ghassemlooy",

note = "Funding: EU FP7 project DISCUS (Grant Agreement 318137).; 9th IEEE/IET international symposium on Communication Systems, Networks and Digital Signl Processing, CSNDSP 2014 ; Conference date: 23-07-2014 Through 25-07-2014",

year = "2014",

month = dec,

day = "31",

doi = "10.1109/CSNDSP.2014.6923996",

language = "English",

isbn = "978-1-4799-2581-0",

pages = "1112--1117",

booktitle = "2014 9th international symposium on Communication Systems, Networks and Digital Signl Processing, CSNDSP 2014",

publisher = "IEEE",

address = "United States",

}

Jarajreh, MA, Rajbhandari, S, Giacoumidis, E, Doran, NJ & Ghassemlooy, Z 2014, Fibre impairment compensation using artificial neural network equalizer for high-capacity coherent optical OFDM signals. in 2014 9th international symposium on Communication Systems, Networks and Digital Signl Processing, CSNDSP 2014. IEEE, pp. 1112-1117, 9th IEEE/IET international symposium on Communication Systems, Networks and Digital Signl Processing, Manchester, United Kingdom, 23/07/14. https://doi.org/10.1109/CSNDSP.2014.6923996

Fibre impairment compensation using artificial neural network equalizer for high-capacity coherent optical OFDM signals. / Jarajreh, M.A.; Rajbhandari, S.; Giacoumidis, E. et al.
2014 9th international symposium on Communication Systems, Networks and Digital Signl Processing, CSNDSP 2014. IEEE, 2014. p. 1112-1117.

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

TY - GEN

T1 - Fibre impairment compensation using artificial neural network equalizer for high-capacity coherent optical OFDM signals

AU - Jarajreh, M.A.

AU - Rajbhandari, S.

AU - Giacoumidis, E.

AU - Doran, N.J.

AU - Ghassemlooy, Z.

N1 - Funding: EU FP7 project DISCUS (Grant Agreement 318137).

PY - 2014/12/31

Y1 - 2014/12/31

N2 - We propose an artificial neural network (ANN) equalizer for transmission performance enhancement of coherent optical OFDM (C-OOFDM) signals. The ANN equalizer showed more efficiency in combating both chromatic dispersion (CD) and single-mode fibre (SMF)-induced non-linearities compared to the least mean square (LMS). The equalizer can offer a 1.5 dB improvement in optical signal-to-noise ratio (OSNR) compared to LMS algorithm for 40 Gbit/s C-OOFDM signals when considering only CD. It is also revealed that ANN can double the transmission distance up to 320 km of SMF compared to the case of LMS, providing a nonlinearity tolerance improvement of ∼0.7 dB OSNR.

AB - We propose an artificial neural network (ANN) equalizer for transmission performance enhancement of coherent optical OFDM (C-OOFDM) signals. The ANN equalizer showed more efficiency in combating both chromatic dispersion (CD) and single-mode fibre (SMF)-induced non-linearities compared to the least mean square (LMS). The equalizer can offer a 1.5 dB improvement in optical signal-to-noise ratio (OSNR) compared to LMS algorithm for 40 Gbit/s C-OOFDM signals when considering only CD. It is also revealed that ANN can double the transmission distance up to 320 km of SMF compared to the case of LMS, providing a nonlinearity tolerance improvement of ∼0.7 dB OSNR.

KW - artificial neural networks

KW - coherent optical OFDM

KW - functional link

KW - nonlinear channel equalization

KW - optical fibre communication

UR - http://www.scopus.com/inward/record.url?scp=84910615934&partnerID=8YFLogxK

UR - http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6923996

U2 - 10.1109/CSNDSP.2014.6923996

DO - 10.1109/CSNDSP.2014.6923996

M3 - Conference publication

AN - SCOPUS:84910615934

SN - 978-1-4799-2581-0

SP - 1112

EP - 1117

BT - 2014 9th international symposium on Communication Systems, Networks and Digital Signl Processing, CSNDSP 2014

PB - IEEE

T2 - 9th IEEE/IET international symposium on Communication Systems, Networks and Digital Signl Processing

Y2 - 23 July 2014 through 25 July 2014

ER -

Fibre impairment compensation using artificial neural network equalizer for high-capacity coherent optical OFDM signals

Abstract

Symposium

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

A 10 Mb/s visible light communication system using a low bandwidth polymer light-emitting diode

Adaptive time synchronization and frequency offset estimation for CO-OFDM

Dual-polarization multi-band OFDM signals for next generation core networks

Cite this