An Eclectic Approach to Network Service Failure Detection Based on Multicriteria Analysis with an Example of Mixing Probabilistic Context Free Grammar Models

• Autorzy: Białoń P.
• Języki publikacji: EN

Abstrakty

EN

A method of failure detection in telecommunication networks is presented. This is a meta-method that correlates alarms raised by failure-detection modules based on various philosophies. The correlation takes into account two main characteristics of each module and the whole metamethod: the percentage of false alarms and the percentage of omitted failures. The trade-off between them is tackled with aspiration-based multicriteria analysis. The alarms are correlated using linear classification by support vector machines. An example of the profitability of correlating alarms in such way is shown. This is an example of probabilistic context free grammars (PCFGs), used to model the proper runtime paths of network services (and thus usable for detecting an improper behavior of the services). It is shown that the linearly mixing PCFGs can add context handling to the PCFG model, thus augmenting the capabilities of the model.

Słowa kluczowe

EN

failure detection; linear separation; probabilistic context free grammars; support vector machine (SVM)

• Wydawca: Instytut Łączności - Państwowy Instytut Badawczy
• Czasopismo: Journal of Telecommunications and Information Technology
• Rocznik: 2008
• Tom: nr 4
• Strony: 32--39
• Opis fizyczny: Bibliogr. 13 poz., rys.

Twórcy

autor

Białoń P.

• National Institute of Telecommunications, Szachowa st 1, 04-894 Warsaw, Poland,

Bibliografia

• [1] I. Katzela and M. Schwartz, “Schemes for fault identification in communication networks”, IEEE/ACM Trans. Netw., vol. 3, pp. 753–764, 1995.
• [2] M. Chen, A. Accardi, E. Kcman, J. Lloyd, D. Patterson, A. Fox, and E. Brewer, “Path-based failure and evolution management”, in Proc. First Symp. Netw. Syst. Des. Implem. NSDI, San Francisco, USA, 2004.
• [3] J. Granat, W. Traczyk, C. Głowiński, J. Pietrzykowski, P. Białoń, and P. Celej, “Eksploracja i analiza danych pozyskiwanych z obiektów sieci teleinformatycznej dla wspomagania zarządzania i podejmowania decyzji”. Report 06.30.001.1, National Institute of Telecommunications, Warsaw, Dec. 2001 (in Polish).
• [4] M. Thottan and J. Chuanyi, “Anomaly detection in IP networks”, IEEE Trans. Sig. Proces., vol. 51, no. 8, pp. 2191–2204, 2003.
• [5] T. Oates and P. R. Cohen, “Searching for structure in multiple streams of data”, in Proc. Int. Conf. Mach. Learn., Bari, Italy, 1996, pp. 346–354.
• [6] D. G¨urer, I. Khan, and R. Ogier, “An artificial intelligence approach to network fault management”, SRI International, 1996.
• [7] G. Jakobson and M. D. Weissman, “Alarm correlation – creating multiple network alarms improves telecommunications network surveillance and fault management”, IEEE Network, pp. 52–59, Nov. 1993.
• [8] J. Granat and A. P. Wierzbicki, “Objective classification of empirical probability distributions and the issue of event detection”, in Proc. 23rd IFIP TC 7 Conf. Syst. Modell. Optim., Cracow, Poland, 2007.
• [9] D. R. Musicant, “Data mining via mathematical programing and machine learning”. Ph.D. thesis, University of Wisconsin – Madison, 2000.
• [10] V. N. Vapnik, The Nature of Statistical Learning Theory. New York: Springer, 1995.
• [11] P. Białoń, “A linear support vector machine solver for a huge number of training examples”, Contr. Cybern. (to appear).
• [12] P. Białoń, A. P. Wierzbicki, and J. Granat, “Narzędzia monitoringu w zarządzaniu sieciami komputerowymi i bazami danych”. Report 06.30.003.7, National Institute of Telecommunications, Warsaw, Dec. 2007 (in Polish).
• [13] J. Granat and A. P. Wierzbicki, “Multicriteria analysis in telecommunication”, in Proc. 37th Ann. Hawaii Int. Conf. Syst. Sci. HICSS’04, Hawaii, USA, 2004, track 3, vol. 3.