Abstract
Fault management is critical to telecommunication networks. It consists of detecting, diagnosing, isolating and fixing network problems, a task that is time-consuming. A promising approach to improve fault management is to find patterns revealing the relationships between network alarms, to then only show the most important alarms to network operators. However, a limitation of current algorithms of this type is that they ignore the network topology. But the network topology is important to understand how alarms propagate on a network. This paper addresses this issue by modeling a real-life telecommunication network as a dynamic attributed graph and then extracting correlation patterns between network alarms called Alarm Correlation Rules. Experiments on a large telecommunication network show that interesting patterns are found that can greatly compress the number of alarms presented to network operators, which can reduce network maintenance costs.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Dusia, A., Sethi, A.S.: Recent advances in fault localization in computer networks. IEEE Commun. Surv. Tutor. 18(4), 3030–3051 (2016)
Ding, J., Kramer, B., Xu, S., Chen, H., Bai, Y.: Predictive fault management in the dynamic environment of IP networks. In: 2004 IEEE International Workshop on IP Operations and Management, pp. 233–239 (2004)
Wang, J., et al.: Efficient alarm behavior analytics for telecom networks. Inf. Sci. 402, 1–14 (2017)
Costa, R., Cachulo, N., Cortez, P.: An intelligent alarm management system for large-scale telecommunication companies. In: Lopes, L.S., Lau, N., Mariano, P., Rocha, L.M. (eds.) EPIA 2009. LNCS (LNAI), vol. 5816, pp. 386–399. Springer, Heidelberg (2009). https://doi.org/10.1007/978-3-642-04686-5_32
Klemettinen, M., Mannila, H., Toivonen, H.: Rule discovery in telecommunication alarm data. J. Netw. Syst. Manage. 7(4), 395–423 (1999)
Hatonen, K., Klemettinen, M., Mannila, H., Ronkainen, P., Toivonen, H.: TASA: telecommunication alarm sequence analyzer or how to enjoy faults in your network. In: Proceedings of NOMS 1996-IEEE Network Operations and Management Symposium, vol. 2, pp. 520–529. IEEE (1996)
Lozonavu, M., Vlachou-Konchylaki, M., Huang, V.: Relation discovery of mobile network alarms with sequential pattern mining. In: 2017 International Conference on Computing, Networking and Communications (ICNC), pp. 363–367. IEEE (2017)
Mannila, H., Toivonen, H., Verkamo, A.I.: Discovering frequent episodes in sequences. In: Proceedings of 1st International Conference on Knowledge Discovery and Data Mining (1995)
Ao, X., Shi, H., Wang, J., Zuo, L., Li, H., He, Q.: Large-scale frequent episode mining from complex event sequences with hierarchies. ACM Trans. Intell. Syst. Technol. (TIST) 10(4), 1–26 (2019)
Fournier-Viger, P., Wang, Y., Yang, P., Lin, J. C.-W., Yun, U.: TKE: mining top-K frequent episodes. In: Proceedings of 33rd International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems, pp. 832–845 (2020)
Luna, J.M., Fournier-Viger, P., Ventura, S.: Frequent itemset mining: a 25 years review. Wiley Interdisc. Rev. Data Min. Knowl. Disc. 9(6), e1329 (2019)
Pei, J., et al.: Mining sequential patterns by pattern-growth: the PrefixSpan approach. IEEE Trans. Knowl. Data Eng. 16(11), 1424–1440 (2004)
Truong, T., Duong, H., Le, B., Fournier-Viger, P.: FMaxCloHUSM: an efficient algorithm for mining frequent closed and maximal high utility sequences. Eng. Appl. Artif. Intell. 85, 1–20 (2019)
Tsang, S., Koh, Y.S., Dobbie, G.: Finding interesting rare association rules using rare pattern tree. Trans. Large-Scale Data Knowl. Centered Syst. 8, 157–173 (2013)
Liu, F., Deng, Y.: Determine the number of unknown targets in Open World based on Elbow method. IEEE Trans. Fuzzy Syst. (2020)
Kaytoue, M., Pitarch, Y., Plantevit, M., Robardet, C.: Triggering patterns of topology changes in dynamic graphs. In: IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM 2014) (2014)
Fournier-Viger, P., et al.: A survey of pattern mining in dynamic graphs. Wiley Interdisc. Rev. Data Min. Knowl. Disc. 10, e1372 (2020)
Fournier-Viger, P., Cheng, C., Cheng, Z., Lin, J.C.W., Selmaoui-Folcher, N.: Finding strongly correlated trends in dynamic attributed graphs. In: International Conference on Big Data Analytics and Knowledge Discovery, pp. 250–265 (2019)
Desmier, É., Plantevit, M., Robardet, C., Boulicaut, J.F.: Granularity of co-evolution patterns in dynamic attributed graphs. In: International Symposium on Intelligent Data Analysis, pp. 84–95 (2014)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Fournier-Viger, P., He, G., Zhou, M., Nouioua, M., Liu, J. (2021). Discovering Alarm Correlation Rules for Network Fault Management. In: Hacid, H., et al. Service-Oriented Computing – ICSOC 2020 Workshops. ICSOC 2020. Lecture Notes in Computer Science(), vol 12632. Springer, Cham. https://doi.org/10.1007/978-3-030-76352-7_24
Download citation
DOI: https://doi.org/10.1007/978-3-030-76352-7_24
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-76351-0
Online ISBN: 978-3-030-76352-7
eBook Packages: Computer ScienceComputer Science (R0)