An Efficient Communication Network SDH Alarm Association Rule Mining Algorithm

Abstract:

WINEPI algorithm is kind of data mining technology that is widely used in alarm association rules mining. Based on the classic WINEPI algorithm, we apply event window instead of time window to improve the exploration result, meanwhile we use FP-Growth algorithm framework instead of Apriori algorithm framework , thus improving efficiency. Based on the alarm time attribute we find interesting alarm association rules further. Experiments show that compared with the classic WINEPI algorithm our improved approach have advantages in reducing the mining error rate and gaining more interesting alarm association rules.

• Periodical: Advanced Materials Research (Volumes 926-930)
• Pages: 1870-1873
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.926-930.1870
• Online since: May 2014
• Authors: Hui Sheng Gao*, Ying Min Li
• Keywords: Alarm Association, Association Rules Exploration, Communication Network, WINEPI Algorithm

References

[1] Q.F. Xu, B. Xiao and J. Guo. The method of mining telecommunication alarm association rules. Journal of Beijing University of Posts and Telecommunications, 2011, 34(2): 86-89. In Chinese.

[2] H. Mannila, H. Toivonen and A. I. Verkamo. Discovery of frequent episodes in event sequences[J]. Data Mining and Knowledge Discovery 1, 1997: 259–289.

DOI: 10.1023/a:1009748302351

[3] Agrawal R. Mining association rules between sets of items in large databases [C] . Proceedings of the 1993 ACM SIG MOD Conference . Washington , D C : [ s. n. ] , 1993 : 207-216.

DOI: 10.1145/170036.170072

[4] Z.T. Li, A.F. Zhang and J. Lei. Real-time correlation of network security alerts[C]. IEEE International Conference on Digital Object Identifier, 2007: 73-80.

[5] S. Lagzian，F. Amiri and A. Enayati. Frequent item set mining-based alert correlation for extracting multi-stage attack scenarios[C]. 2012 Sixth International Symposium on Digital Object Identifier, 2012: 1010-1014.

DOI: 10.1109/istel.2012.6483134

[6] Z.H. Tian, Y.Z. Zhang and W.Z. Zhang. Adaptive alarm association based on pattern mining and clustering analysis. Journal of Computer Research and Development, 2009 , 46(8) : 1304-1315. In Chinese.

[7] J. Wu, X.M. Li. Research on distribute communication network alarm relevance based on association rule. Journal of Computer Science, 2009, 36(11): 204-207, 212. In Chinese.

[8] Y. Chen, Q.N. Lin and Z.Y. T. A quantitative analysis of association rules. Journal of communication, 2003, 24(3): 119-123. In Chinese.

[9] J.W. Han. Mining frequent patterns without candidate generation [A] . In: Proceedings of the 2000 ACMSIGMOD conference on Management of Data[C], Dallas, TX, 2000 : 1-12.

[10] ITU-T Rec G. 783. Characteristics of Synchronous Digit al Hierarchy ( SDH) Equipment Function Blocks[ S ] , (1996).

[11] Q.F. Xu, J.J. Kan and Y.C. Li. An algorithm of mining alarm association rules with temporal characteristic. Microelectronics, 2007, 24(3): 23-26. In Chinese.