Journal of Network and Systems Management

, Volume 25, Issue 3, pp 558–590 | Cite as

Model-Based Probabilistic Reasoning for Self-Diagnosis of Telecommunication Networks: Application to a GPON-FTTH Access Network

  • S. R. Tembo
  • S. Vaton
  • J. L. Courant
  • S. Gosselin
  • M. Beuvelot


Carrying out self-diagnosis of telecommunication networks requires an understanding of the phenomenon of fault propagation on these networks. This understanding makes it possible to acquire relevant knowledge in order to automatically solve the problem of reverse fault propagation. Two main types of methods can be used to understand fault propagation in order to guess or approximate as much as possible the root causes of observed alarms. Expert systems formulate laws or rules that best describe the phenomenon. Artificial intelligence methods consider that a phenomenon is understood if it can be reproduced by modeling. We propose in this paper, a generic probabilistic modeling method which facilitates fault propagation modeling on large-scale telecommunication networks. A Bayesian network (BN) model of fault propagation on gigabit-capable passive optical network-fiber to the home (GPON-FTTH) access network is designed according to the generic model. GPON-FTTH network skills are used to build structure and approximatively determine parameters of the BN model so-called expert BN model of the GPON-FTTH network. This BN model is confronted with reality by carrying out self-diagnosis of real malfunctions encountered on a commercial GPON-FTTH network. Obtained self-diagnosis results are very satisfying and we show how and why these results of the probabilistic model are more consistent with the behaviour of the GPON-FTTH network, and more reasonable on a representative sample of diagnosis cases, than a rule-based expert system. With the main goal to improve diagnostic performances of the BN model, we study and apply expectation maximization algorithm in order to automatically fine-tune parameters of the BN model from real data generated by a commercial GPON-FTTH network. We show that the new BN model with optimized parameters reasonably improves self-diagnosis previously carried out by the expert Bayesian network model of the GPON-FTTH access network.


Network management Optical network Fault management Fault propagation Model-based approach Bayesian network Statistical inference Parameters estimation Expectation maximization 


  1. 1.
    Steinder, M., Sethi, A.S.: A survey of fault localization techniques in computer networks. Sci. Comput. Program. 53, 165–194 (2004)MathSciNetCrossRefMATHGoogle Scholar
  2. 2.
    Hounkonnou, C.: Active self-diagnosis in telecommunication networks. PhD Thesis, European University of Brittany, University of Rennes 1, INRIA, ISTIC, France (2013)Google Scholar
  3. 3.
    Pau, L.F.: Survey of expert systems for fault detection, test generation and maintenance. Expert Syst. 3, 100–110 (1986)CrossRefGoogle Scholar
  4. 4.
    Scherer, W.T., White, C.C.: Knowledge-Based System Diagnosis, Supervision, and Control. Chapter 16. A Survey of Expert Systems for Equipment Maintenance and Diagnostics. Springer, New York (1989)Google Scholar
  5. 5.
    Gardner, R.D., Harle, D.A.: Alarm correlation and network fault resolution using the Kohonen self-organising map. Global Telecommunications Conference (GLOBECOM 1997), pp. 1398–1402 (1997)Google Scholar
  6. 6.
    Patton, R.J., Chen, J., Siew, T.M.: Fault diagnosis in nonlinear dynamic systems via neural networks. Int. Conf. Control 2, 1346–1351 (1994)CrossRefGoogle Scholar
  7. 7.
    Goel, A., Ramanujam, J., Sadayappan, P.: Towards a ’neural’ architecture for abductive reasoning. In: IEEE International Conference on Neural Networks, pp. 681–688. (1998)Google Scholar
  8. 8.
    Lewis, L.: A case-based reasoning approach to the resolution of faults in communication networks. In: Proceedings of the Third International Symposium on Integrated Network Management, pp. 671–682. (1993)Google Scholar
  9. 9.
    Tembo, S.R., Courant J.L., Vaton, S.: A 3-layered self-reconfigurable generic model for self-diagnosis of telecommunication networks. In: IEEE SAI International Conference on Intelligent Systems, INTELLISYS, London (2015)Google Scholar
  10. 10.
    Pearl, Judéa: Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan Kaufmann, San Mateo (1988)MATHGoogle Scholar
  11. 11.
    Naim, P., Wuillemin, P.H., Leray, P., Pourret, O., Becker, A.: Réseaux Bayésiens. EYROLLES, Paris (2008)Google Scholar
  12. 12.
    Cornuéjols, A.: Miclet, L.: Apprentissage Artificiel. Concepts et Algorithmes. EYROLLES, Paris (2013)Google Scholar
  13. 13.
    Telecommunication Standardization Sector of ITU (International Telecommunication Union). G.984.3 Recommendation. ITU-T (2008)Google Scholar
  14. 14.
    Telecommunication Standardization Sector of ITU (International Telecommunication Union). G.977.1 Recommendation. ITU-T (2003)Google Scholar
  15. 15.
    Gruschke, B.: Integrated event management: event correlation using dependency graphs. In: A.S. Sethi (ed.), Ninth International Workshop on Distributed Systems: Operations and Management, University of Delaware, Newark, DE, vol. 87, pp. 130–141, October (1998)Google Scholar
  16. 16.
    Kätker S.: A modeling framework for integrated distributed systems fault management. In: C. Popien (ed.) Proceedings of IFIP/IEEE International Conference on Distributed Platforms, Dresden, Germany, pp. 187–198 (1995)Google Scholar
  17. 17.
    Houck, K., Calo, S., Finkel, A.: Towards a practical alarm correlation system. In: Proceedings of the Fourth International Symposium on Integrated Network Management, pp. 226–237 (1995)Google Scholar
  18. 18.
    Jordaan, J.F., Paterokl, M.E.: Event correlation in heterogeneous networks using the osi management framework. In: Proceedings of the Third International Symposium on Integrated Network Management, pp. 683–695 (1993)Google Scholar
  19. 19.
    Kätker, S., Geihs, K.: A generic model for fault isolation in integrated management systems. J. Netw. Syst. Manag. 5(2), 109–130 (1997)CrossRefGoogle Scholar
  20. 20.
    Kätker, S., Paterok, M.: Fault isolation and event correlation for integrated fault management. In: Proceedings of the Fifth International Symposium on Integrated Network Management, pp. 583–596 (1997)Google Scholar
  21. 21.
    Jakobson, G., Weissman, M.: Real-time telecommunication network management: extending event correlation with temporal constraints. In: Proceedings of the Fourth International Symposium on Integrated Network Management, pp. 290–301 (1995)Google Scholar
  22. 22.
    Sanchez, J.M., Yahia, I.G.B., Crespi, N.: Self modeling based diagnosis of software defined networks. In: 1st Conference on Network Softwarization (NetSoft) (2015)Google Scholar
  23. 23.
    Liu, G., Ji, C.: Resilience of all-optical network architectures under in-band crosstalk attacks: a probabilistic graphical model approach. IEEE J. Sel. Areas Commun. 25(3), 2–17 (2007)CrossRefGoogle Scholar
  24. 24.
    Aghasaryan, Armen, Fabre, Eric, Benvenist, Albert: Fault detection and diagnosis in distributed systems: an approach by partially stochastic petri nets. J. Discret. Event Dyn. Syst.: Theory Appl. 8, 203–231 (1998)MathSciNetCrossRefMATHGoogle Scholar
  25. 25.
    Saradhi, Chava Vijaya, Subramaniam, Suresh: Physical layer impairment aware routing (pliar) in wdm optical networks: issues and challenges. IEEE Commun. Surv. Tutor. 11(4), 109–130 (2009)CrossRefGoogle Scholar
  26. 26.
    Lauritzen, S.: Graphical models. Oxford Statistical Science Series, Book 17. Clarendon Press, Oxford (1996)Google Scholar
  27. 27.
    Madsen, A.L., Jensen, F.V.: Lazy propagation: a junction tree inference algorithm based on lazy evaluation. Artif. Intell. 113, 203–245 (1999)MathSciNetCrossRefMATHGoogle Scholar
  28. 28.
    Laurizen, Stephen, Spiegelhalter, David: Local computations with probabilities on graphical structures and their application to expert systems. J. R. Stat. Soci. Ser. B 50(2), 157–224 (1988)MathSciNetMATHGoogle Scholar
  29. 29.
    Berry, A, Heggernes, P, Simonet, G.: The minimum degree heuristic and the minimal triangulation process. In: H. Bodlaender (ed.). WG’03: 29th International Workshop on Graph Theoretic Concepts in Computer Science, Elspeet (The Netherlands), Lecture Notes in Computer Science lirmm-00191916, pp. 58–70 (2003)Google Scholar
  30. 30.
    Dempster, A.P., Laird, N.M., Rubin, D.B.: Maximum likelihood from incomplete data via the EM algorithm. J. R. Stat. Soc. Ser. B 39(1), 1–38 (1977)MathSciNetMATHGoogle Scholar
  31. 31.
    Lauritzen, Stephen: The EM algorithm for graphical association models with missing data. Comput. Stat. Data Anal. 19, 191–201 (1995)CrossRefMATHGoogle Scholar
  32. 32.
    Lauritzen, Stephen, Spiegelhalter, David: Local computations with probabilities on graphical structures and their application to expert systems. J. R. Stat. Soc. Ser. B 50(2), 157–224 (1988)MathSciNetMATHGoogle Scholar
  33. 33.
    Tembo, S.R., Vaton, S., Courant, J.L., Gosselin, S.: A tutorial on the em algorithm for Bayesian networks: application to self-diagnosis of GPON-FTTH networks. In: IEEE Technically Sponsored Workshop TRAC 2016, Traffic analysis and Characterization (2016)Google Scholar

Copyright information

© Springer Science+Business Media New York 2016

Authors and Affiliations

  • S. R. Tembo
    • 1
    • 2
  • S. Vaton
    • 2
  • J. L. Courant
    • 1
  • S. Gosselin
    • 1
  • M. Beuvelot
    • 1
  1. 1.Orange LabsLannionFrance
  2. 2.Telecom BretagneBrestFrance

Personalised recommendations