一种有效的通信网络告警分析方法

doi:10.19665/j.issn1001-2400.2019.04.001

西安电子科技大学学报 ›› 2019, Vol. 46 ›› Issue (4): 1-8.doi: 10.19665/j.issn1001-2400.2019.04.001

• • 下一篇

一种有效的通信网络告警分析方法

齐小刚¹,胡秋秋¹,姚旭清²,刘立芳³

1.西安电子科技大学数学与统计学院,陕西西安 710071
2.中国移动集团公司山西有限公司,山西太原 030002
3.西安电子科技大学计算机科学与技术学院,陕西西安 710071

收稿日期:2019-03-04 出版日期:2019-08-20 发布日期:2019-08-15
作者简介:齐小刚(1973—),男,教授,博士,E-mail: xgqi@xidian.edu.cn.
基金资助:
国家自然科学基金(61877067);教育部-中国移动联合基金(MCM20170103);复杂电子系统仿真重点实验室研究基金(DXZT-JC-ZZ-2015-015);宁坡市自然科学基金(2016A610035);宁坡市自然科学基金(2017A610119)

Efficient alarm analysis approach for communication networks

QI Xiaogang¹,HU Qiuqiu¹,YAO Xuqing²,LIU Lifang³

1.School of Mathematics and Statistics, Xidian Univ., Xi’an 710071, China
2.Shanxi Co. Ltd., China Mobile Group Co. Ltd., Taiyuan 030002, China
3.School of Computer Science and Technology, Xidian Univ., Xi’an 710071, China

Received:2019-03-04 Online:2019-08-20 Published:2019-08-15

摘要/Abstract

摘要：

以往大多告警分析研究都是假设通信网络中所有告警是平等的,考虑此假设的不合理性,提出了一种加权告警分析方法。首先,根据告警对网络的影响程度,采用熵值法为不同的告警分配不同的权值,并将其转换成适合于数据挖掘的序列数据集;然后,设计了一种加权告警序列模式挖掘算法,并采用了一种新颖的剪枝策略来缩减需要挖掘的数据集大小以提高算法的效率;最后,利用该算法挖掘告警数据中的时序关系。实验结果表明,这种加权告警分析方法在剪枝效果、挖掘重要告警序列模式和执行效率方面具有很好的性能。

Abstract:

Considering the irrationality of this hypothesis that previous most alarm analysis studies were based on the premise that all alarms in the communication network are equal, a weighted alarm analysis method is proposed. First, according to the significance of the alarm in the network, the entropy method is used to assign different weight values for different alarms, and these values are transformed into a sequence dataset suitable for data mining. Then, a weighted alarm sequential pattern mining algorithm is proposed which uses an original pruning strategy to reduce the size of dataset needing to be mined to improve the efficiency of the algorithm. Finally, the algorithm is used to mine sequential relationship in alarm data. Experimental results show that this weighted alarm analysis approach has a good performance in pruning effectiveness, mining of the important alarm sequential pattern and execution efficiency.

Key words: correlation analysis, network management, entropy method, pruning strategy, weighted alarm sequence pattern mining algorithm

中图分类号:

TP301

齐小刚,胡秋秋,姚旭清,刘立芳. 一种有效的通信网络告警分析方法[J]. 西安电子科技大学学报, 2019, 46(4): 1-8.

QI Xiaogang,HU Qiuqiu,YAO Xuqing,LIU Lifang. Efficient alarm analysis approach for communication networks[J]. Journal of Xidian University, 2019, 46(4): 1-8.

图/表 8

表1

表2

表3

表4

图1

图2

图3

图4

参考文献 17

[1]	王意洁, 程力, 马行空 . 运用警报关联的威胁行为检测技术综述[J]. 国防科技大学学报, 2017,8(5):128-138.
	WANG Yijie, CHENG Li, MA Xingkong . Survey of Alert-correlation Based on Network Threat Detection Techniques[J]. Journal of National University of Defense Technology, 2017,8(5):128-138.
[2]	李龙营, 李金库, 马建峰 , 等. 采用攻击策略图的实时警报综合分析方法[J]. 西安电子科技大学学报, 2014,41(5):84-90. doi: 10.3969/j.issn.1001-2400.2014.05.015
	LI Longying, LI Jinku, MA Jianfeng , et al. Comprehensive Analysis of Real-time Alerts with Attack Strategy Graphs[J]. Journal of Xidian University, 2014,41(5):84-90. doi: 10.3969/j.issn.1001-2400.2014.05.015
[3]	WANG C H, YANG J M. Adaptive Feature-weighted Alert Correlation System Applicable in Cloud Environment [C]//Proceedings of the 2013 8th Asia Joint Conference on Information Security. Washington: IEEE Computer Society, 2013: 41-47.
[4]	RAMAKI A A, AMINI M, EBRAHIMI ATANI R . RTECA: Real Time Episode Correlation Algorithm for Multi-step Attack Scenarios Detection[J]. Computers and Security, 2015,49:206-219.
[5]	WANG Y, LI G C, XU Y K , et al. An Algorithm for Mining of Association Rules for the Information Communication Network Alarms Based on Swarm Intelligence[J]. Mathematical Problems in Engineering, 2014,2014:894205.
[6]	WANG Y, XU Y, LI G , et al. Association Rules Mining Algorithm Using Sharing Mechanism Niche Leaping Ant Colony Based on Apriori Algorithm[J]. Journal of Computational and Theoretical Nanoscience, 2015,12(10):3223-3231.
[7]	LI C, HUANG X. Research on FP-growth Algorithm for Massive Telecommunication Network Alarm Data Based on Spark [C]//Proceedings of the 2017 IEEE International Conference on Software Engineering and Service Science. Washington: IEEE Computer Society, 2017: 875-879.
[8]	AGRAWAL R, SRIKANT R. Mining Sequential Patterns [C]//Proceedings of the 1995 International Conference on Data Engineering. Piscataway: IEEE, 1995: 3-14.
[9]	WANG J, LI H, HUANG J , et al. Association Rules Mining Based Analysis of Consequential Alarm Sequences in Chemical Processes[J]. Journal of Loss Prevention in the Process Industries, 2016,41:178-185.
[10]	LIM H K, KIM Y, KIM M K . Failure Prediction Using Sequential Pattern Mining in the Wire Bonding Process[J]. IEEE Transactions on Semiconductor Manufacturing, 2017,30(3):285-292.
[11]	WANG J, HE C, LIU Y , et al. Efficient Alarm Behavior Analytics for Telecom Networks[J]. Information Sciences, 2017,402:1-14.
[12]	MIHAELA L, MARTHA V K, VINCENT H. Relation Discovery of Mobile Network Alarms with Sequential Pattern Mining [C]//Proceedings of the 2017 International Conference on Computing, Networking and Communications. Piscataway: IEEE, 2017: 363-367.
[13]	罗明, 孟传伟, 黄海量 . 基于加权频繁模式树的通信网络告警规则挖掘方法[J]. 计算机工程, 2016,42(4):190-196. doi: 10.3969/j.issn.1000-3428.2016.04.034
	LUO Ming, MENG Chuanwei, HUANG Hailiang . Alarm Rule Mining Method in Telecommunication Network Based on Weighted Frequent Pattern-tree[J]. Computer Engineering, 2016,42(4):190-196. doi: 10.3969/j.issn.1000-3428.2016.04.034
[14]	MURUGEST T, AIYER C A . Analysis and Optimization of Alarm[J]. Journal of System and Management Sciences, 2013,3(4):1-17.
[15]	汪星, 黄小瑜, 刘瑄璞 , 等. 面向工业大数据的多层增量特征提取方法[J]. 西安电子科技大学学报, 2018,45(4):112-117.
	WANG Xing, HUANG Xiaoyu, LIU Xuanpu , et al. Multi-layer Incremental Feature Extraction Method for Industrial Big Data[J]. Journal of Xidian University, 2018,45(4):112-117.
[16]	PEI J, HAN J, MORTAZAVI-ASL B , et al. Mining Sequential Patterns by Pattern-Growth: The Prefix Span Approach[J]. IEEE Transactions on Knowledge and Data Engineering, 2004,16(11):1424-1440.
[17]	GOETHALS B . Frequent Itemset Mining Implementations Repository[EB/OL]. [ 2019- 2- 20]. http://fimi.cs.helsinki.fi/.

属性	内容	属性	内容	属性	内容
告警设备类型	PTN	网元名称	53-147-XX-HW-PTN1	对设备的影响	无影响
告警标题	ETL_LOS	告警发生时间	2018-10-30 01:45:49	对业务的影响	可能全阻
告警级别	三级告警	告警清除时间	2018-10-30 01:46:16

告警标题	对设备的影响	对业务的影响	告警级别
告警a	局部故障	可能受影响	一级告警
告警b	性能下降	可能受影响	三级告警
告警c	可能受影响	无影响	四级告警
告警d	无影响	质量降低	四级告警
告警e	可能受影响	受影响	二级告警

告警序列ID	告警序列
F1	<a(bd)bcb(ade)>
F2	<(ef)(ab)(df)cb>
F3	<(ad)(bf)abf>
F4	<eg(af)bc>

数据信息	告警数量	网元名称数量	告警标题数量
原始告警数据信息	258103	8930	405
清洗后告警数据信息	72346	5748	165

一种有效的通信网络告警分析方法

Efficient alarm analysis approach for communication networks

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 8

参考文献 17

相关文章 7

Metrics

本文评价

推荐阅读 0

[1]	汪星;黄小瑜;刘瑄璞;孔宪光;牛萌. 面向工业大数据的多层增量特征提取方法[J]. 西安电子科技大学学报, 2018, 45(4): 106-111.
[2]	李红艳;杨光祥;王文龙. 一种最大吞吐量的深空通信网络路由算法[J]. J4, 2012, 39(1): 92-97.
[3]	韩庆绵. 一种新颖的全IP综合移动通信系统[J]. J4, 2011, 38(5): 40-45+114.
[4]	范淑艳;熊高云. 栅格通信网络体系结构及关键技术研究[J]. J4, 2009, 36(6): 990-995.
[5]	李彤岩;李兴明. 通信网告警相关性分析中有效的关联规则挖掘算法 [J]. J4, 2007, 34(7): 39-42.
[6]	陈彦辉;康槿;李建东. 无线移动通信网络拓扑有效性的研究 [J]. J4, 2006, 33(5): 700-702.
[7]	薄华1;马缚龙2. 基于流体神经网络的路径选择算法[J]. J4, 2004, 31(2): 177-181.