Abstract
Self-management is essential for Beyond 3G (B3G) systems, where the existence of multiple access technologies (GSM, GPRS, UMTS, WLAN, etc.) will complicate network operation. Diagnosis, that is, fault identification, is the most difficult task in automatic fault management. This paper presents a probabilistic system for auto-diagnosis in the radio access part of wireless networks, which comprises a model and a method. The parameters of the model are thresholds for the discretization of Key Performance Indicators (KPIs) and probabilities. In this paper, some techniques are proposed for the automatic learning of those model parameters. In order to support the theoretical concepts, experimental results are examined, based on data from a live network. It has been proven that calculating parameters from network statistics, instead of being defined by diagnosis experts, highly increases the performance of the diagnosis system. In addition, the proposed techniques enhance the results obtained with continuous diagnosis models previously exposed in the literature.
Similar content being viewed by others
References
Altman, Z., Skehill, R., Barco, R., Moltsen, L., Brennan, R., Samhat, R., et al. (2006). The Celtic Gandalf framework. In Proceedings of IEEE Mediterranean Electrotechnical Conference MELECON’06, Benalmádena, Spain, May 2006, pp. 595–598.
Barco, R. (2007). Bayesian modelling of fault diagnosis in mobile communication networks. Ph.D. dissertation, University of Malaga, Spain, ISBN: 978-84-9747-486-3.
Barco, R., Nielsen, L., Guerrero, R., Hylander, G., & Patel, S. (2002). Automated troubleshooting of a mobile communication network using Bayesian networks. In IEEE International Workshop on Mobile and Wireless Communications Networks (MWCN’02), Stockholm, Sweden, Sep. 2002, pp. 606–610.
Barco, R., Wille, V., & Díez, L. (2005). System for automated diagnosis in cellular networks based on performance indicators. European Transactions Telecommunications, 16(5), 399–409.
Blake, C., & Merz, C. (1998). UCI repository of machine learning databases. Dept. Information and Computer Science, http://www.ics.uci.edu/ mlearn/MLRepository.html. Irvine, CA: University of California. [Online]. Available: http://www.ics.uci.edu/ mlearn/MLRepository.html.
Cestnik, B. (1990). Estimating probabilities: A crucial task in machine learning. In Proceedings of European Conference Artificial Intelligence (ECAI’90), Stockholm, Sweden, Aug. 1990, pp. 147–149.
Chan, P. M. L., Sheriff, R. E., Hu, Y. F., Conforto, P., & Tocci, C. (2001). Mobility management incorporating Fuzzy Logic for a heterogeneous IP environtment. IEEE Communications Magazine, December, 42–51.
Domingos, P. & Pazzani, P. (1997). On the optimality of the simple bayesian classifier under zero-one loss. Machine Learning, 29, 103–130.
Dougherty, K., Kohavi, R., & Sahami, M. (1995). Supervised and unsupervised discretization of continuous features. In Proceedings of International Conference on Machine Learning, Tahoe City, CA, July 1995, pp. 194–202.
Fayyad, U., & Irani, K. (1993). Multi-interval discretization of continuous valued attributes for classification learning. In Proceedings of International Joint Conference on Artificial Intelligence, Chambery, France, Aug. 1993, pp. 1022–1027.
Friedman, N., Geiger, D., & Goldszmidt, M. (1997). Bayesian network classifiers. Machine Learning, 29, 131–163.
Good, I. (1965). The estimation of probabilities. Cambridge, MA: M.I.T. Press.
Heckerman, D., Breese, J., & Rommelse, K. (1995). Decision-theoretic troubleshooting. Communication of the ACM, 38(3), 49–57.
Johnson, J. L. (2003). Probability and statistics for computer science. New Jersey, USA: Wiley.
Khanafer, R., Moltsen, L., Dubreil, H., Altman, Z., & Barco, R. (2006, August). A bayesian approach for automated troubleshooting for UMTS networks. In Proceedings of 17th IEEE International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC’06), Karlsruhe, Germany.
Laiho, J., Raivio, K., Lehtimäki, P., Hätönen, K., & Simula, O. (2005). Advanced analysis methods for 3G cellular networks. IEEE Transactions on Wireless Communications, 4(3), 930–942.
Lehtimäki, P., & Raivio, K. (2005, September). A SOM based approach for visualization of GSM network performance data. In Proceedings of International Symposium on Intelligent Data Analysis, Madrid, Spain.
Lehtimäki, P., & Raivio, K. (2005, June). A knowledge-based model for analyzing GSM network performance. In Proceedings of International Conference on Industrial & Engineering Applications of Artificial Intelligence & Expert Systems, Bari, Italy.
Nasri, R., Altman, Z., & Dubreil, H. (2006). Fuzzy-Q-learning-based autonomic management of macro-diversity algorithm in UMTS networks. Annals of Telecommunications, 61(9–10), 1119–1135.
Neapolitan, R. (2004). Learning bayesian networks. Upper Saddle River, NJ: Prentice Hall.
Ng, G., & Ong, K. (2000). Using a qualitative probabilistic network to explain diagnostic reasoning in an expert system for chest pain diagnosis. Computers in Cardiology, September, 569–572.
Pagallo, G. & Haussler, D. (1990). Boolean feature discovery in empirical learning. Machine learning, 5, 71–99.
Pearl, J. (1988). Probabilistic reasoning in intelligent systems: Networks of plausible inference. San Francisco, CA.: Morgan Kaufmann.
Quinlan, J. (1986). Induction of decision trees. Machine learning, 1, 81–106.
Renooij, S. & Witteman, C. (1999). Talking probabilities: Communicating probabilistic information with words and numbers. International Journal of Approximate Reasoning, 22(3), 169–194.
Rice, J. (1988). Mathematical statistics and data analysis. California, USA: Wadsworth & Brooks/Cole.
Rish, I. (2001). An empirical study of the naive bayes classifier, in Proceedings of International Joint Conference on Artificial Intelligence, Seattle, USA, Aug. 2001, pp. 41–46.
Salzberg, S. (1997). On comparing classifiers: pitfalls to avoid and a recommended approach. Data Mining and Knowledge Discovery, 1, 317–327.
Skaanning, C., Jensen, F., Kjærulff, U., & Madsen, A. (1999, March). Acquisition and transformation of likelihoods to conditional probabilities for bayesian networks. In Proceedings of AAAI Spring Symposium on AI in Equipment Maintenance Service and Support, Palo Alto, CA, pp. 34–40.
Steinder, M., & Sethi, A. (2004). Probabilistic fault localization in communication systems using belief networks. IEEE/ACM Transactions on Networking, 12(5), 809–822.
van der Gaag, L., Renooij, S., Witteman, C., Aleman, B., & Taal, B. (1999). How to elicit many probabilities. In Proceedings of Annual Conference on Uncertainty in Artificial Intelligence, Stockholm, Sweden, July 1999, pp. 647–654.
Wietgrefe, H. (2002). Investigation and practical assessment of alarm correlation methods for the use in GSM access networks. In Proceedings of IEEE/IFIP Network Operations and Management Symposium, Florence, Italy, Apr. 2002, pp. 391– 403.
Acknowledgements
This work has been partially supported by the Spanish Ministry of Science and Technology under project TIC2003-07827.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Barco, R., Wille, V., Díez, L. et al. Learning of model parameters for fault diagnosis in wireless networks. Wireless Netw 16, 255–271 (2010). https://doi.org/10.1007/s11276-008-0128-z
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11276-008-0128-z