Comparison of optical performance monitoring techniques using artificial neural networks

Vítor Ribeiro, Mário Lima, António Teixeira

Research output: Contribution to journalArticle

Abstract

In this paper, we make an overview of three techniques that have used artificial neural networks (ANNs) to model impairments in optical fiber. A comparison between a linear partial least squares regression algorithm and ANN is also shown. We demonstrate that nonlinear modeling is required for multi-impairment monitoring in optical fiber when using Parametric Asynchronous Eye Diagram (PAED). Results demonstrating the accuracy of PAED are also shown. A comparison between PAED and Synchronous Eye Diagrams is also demonstrated, for NRZ, RZ and QPSK modulated signals. We show that PAED can provide comprehensible diagrams for QPSK modulated signals, under a certain range of chromatic dispersion.
Original languageEnglish
Pages (from-to)583–589
JournalNeural Computing and Applications
Volume23
Issue number3-4
DOIs
Publication statusPublished - 14 Apr 2013

Fingerprint

Quadrature phase shift keying
Optical fibers
Neural networks
Chromatic dispersion
Monitoring

Cite this

@article{fcbaddb75bb14cbf8c301f59a70a2787,
title = "Comparison of optical performance monitoring techniques using artificial neural networks",
abstract = "In this paper, we make an overview of three techniques that have used artificial neural networks (ANNs) to model impairments in optical fiber. A comparison between a linear partial least squares regression algorithm and ANN is also shown. We demonstrate that nonlinear modeling is required for multi-impairment monitoring in optical fiber when using Parametric Asynchronous Eye Diagram (PAED). Results demonstrating the accuracy of PAED are also shown. A comparison between PAED and Synchronous Eye Diagrams is also demonstrated, for NRZ, RZ and QPSK modulated signals. We show that PAED can provide comprehensible diagrams for QPSK modulated signals, under a certain range of chromatic dispersion.",
author = "V{\'i}tor Ribeiro and M{\'a}rio Lima and Ant{\'o}nio Teixeira",
year = "2013",
month = "4",
day = "14",
doi = "10.1007/s00521-013-1405-z",
language = "English",
volume = "23",
pages = "583–589",
journal = "Neural Computing and Applications",
issn = "0941-0643",
publisher = "Springer",
number = "3-4",

}

Comparison of optical performance monitoring techniques using artificial neural networks. / Ribeiro, Vítor; Lima, Mário; Teixeira, António.

In: Neural Computing and Applications, Vol. 23, No. 3-4, 14.04.2013, p. 583–589.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Comparison of optical performance monitoring techniques using artificial neural networks

AU - Ribeiro, Vítor

AU - Lima, Mário

AU - Teixeira, António

PY - 2013/4/14

Y1 - 2013/4/14

N2 - In this paper, we make an overview of three techniques that have used artificial neural networks (ANNs) to model impairments in optical fiber. A comparison between a linear partial least squares regression algorithm and ANN is also shown. We demonstrate that nonlinear modeling is required for multi-impairment monitoring in optical fiber when using Parametric Asynchronous Eye Diagram (PAED). Results demonstrating the accuracy of PAED are also shown. A comparison between PAED and Synchronous Eye Diagrams is also demonstrated, for NRZ, RZ and QPSK modulated signals. We show that PAED can provide comprehensible diagrams for QPSK modulated signals, under a certain range of chromatic dispersion.

AB - In this paper, we make an overview of three techniques that have used artificial neural networks (ANNs) to model impairments in optical fiber. A comparison between a linear partial least squares regression algorithm and ANN is also shown. We demonstrate that nonlinear modeling is required for multi-impairment monitoring in optical fiber when using Parametric Asynchronous Eye Diagram (PAED). Results demonstrating the accuracy of PAED are also shown. A comparison between PAED and Synchronous Eye Diagrams is also demonstrated, for NRZ, RZ and QPSK modulated signals. We show that PAED can provide comprehensible diagrams for QPSK modulated signals, under a certain range of chromatic dispersion.

UR - https://link.springer.com/article/10.1007/s00521-013-1405-z

U2 - 10.1007/s00521-013-1405-z

DO - 10.1007/s00521-013-1405-z

M3 - Article

VL - 23

SP - 583

EP - 589

JO - Neural Computing and Applications

JF - Neural Computing and Applications

SN - 0941-0643

IS - 3-4

ER -