Applying Artificial Neural Networks for Fault Prediction in Optical Network Links

  • C. H. R. Gonçalves
  • M. Oliveira
  • R. M. C. Andrade
  • M. F. Castro
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3124)


The IP+GMPLS over DWDM model has been considered a trend for the evolution of optical networks. However, a challenge that has been investigated in this model is how to achieve fast rerouting in case of DWDM failure. Artificial Neural Networks (ANNs) can be used to generate proactive intelligent agents, which are able to detect failure trends in optical network links early and to approximate optical link protection mode from 1:n to 1+1. The main goal of this paper is to present an environment called RENATA2 and its process on how to develop ANNs that can give to the intelligent agents a proactive behavior able to predict failure in optical links.


Mean Square Error Intelligent Agent Fault Prediction Perturbation Generator Optical Link 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Banerjee, A., et al.: Generalized Multiprotocol Label Switching: An Overview of Routing and Management Enhancements. IEEE Comm. Mag. 39(1), 145–150 (2001)CrossRefGoogle Scholar
  2. 2.
    Franklin, M.F.: Redes Neurais na Estimativa da Capacidade Requerida em Comutadores ATM. Master’s Thesis, Universidade Federal do Ceará, Fortaleza (April 1999)Google Scholar
  3. 3.
    Nascimento, A.S.: Desenvolvendo Agentes Inteligentes para a Gerência Pró-Ativa de Redes ATM. Master’s Thesis, Universidade Federal do Ceará, Fortaleza (1999) Google Scholar
  4. 4.
    Soto, C.P.: Redes Neurais Temporais para o tratamento de Sistemas Variantes no Tempo. Master’s Thesis, PUC/RJ, Rio de Janeiro (1999) Google Scholar
  5. 5.
    Doverspike, R., Yates, J.: Challenges for MPLS in Optical Network Restoration. IEEE Communications Magazine 39(2), 89–96 (2001)CrossRefGoogle Scholar
  6. 6.
    Kartalopoulos, S.V.: Fault Detectability in DWDM – Toward Higher Signal Quality & System Reliability. IEEE Press, New York (2001)Google Scholar
  7. 7.
    Mas, C., Thiran, P.: An Efficient Algorithm for Locating Soft and Hard Failures in WDM Networks. IEEE JSAC 18(10), 1900–1991 (2000)Google Scholar
  8. 8.
    Wong, P.K.C., Ryan, H.M., Tindle, J.: Power System Fault Prediction Using Artificial Neural Networks. In: Proc. of International Conference on Neural Information Processing, Hong Kong (September 1996)Google Scholar
  9. 9.
    Abraham, A.: A Soft Computing Approach for Fault Prediction of Electronic Systems. In: Karim, M.A., et al. (eds.) Proc. of The Second International Conference on Computers In Industry (ICCI 2000), Bahrain, pp. 83–91. The Bahrain Society of Engineers (2000)Google Scholar
  10. 10.
    Lawrence, J.: Designing Multiprotocol Label Switching Networks. IEEE Comm. Mag. 39(7), 134–142 (2001)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • C. H. R. Gonçalves
    • 1
  • M. Oliveira
    • 1
  • R. M. C. Andrade
    • 2
  • M. F. Castro
    • 3
  1. 1.Laboratório Multiinstitucional de Redes de Computadores e Sistemas Distribuídos Centro Federal de Educação Tecnológica do Ceará (LAR/CEFET-CE)FortalezaBrasil
  2. 2.Departamento de Computação (DC/UFC)Universidade Federal do CearáFortalezaBrasil
  3. 3.Institut National des TélécommunicationsEvry CedexFrance

Personalised recommendations