Workload-aware anomaly detection for web applications

ISCAS OpenIR

	Workload-aware anomaly detection for web applications
	Wang, Tao (1); Wei, Jun (1); Zhang, Wenbo (2); Zhong, Hua (2); Huang, Tao (1); Wang, T.(wangtao08@otcaix.iscas.ac.cn)
	2014
发表期刊	Journal of Systems and Software
ISSN	1641212
卷号	89 期号:1 页码:19-32
摘要	The failure of Web applications often affects a large population of customers, and leads to severe economic loss. Anomaly detection is essential for improving the reliability of Web applications. Current approaches model correlations among metrics, and detect anomalies when the correlations are broken. However, dynamic workloads cause the metric correlations to change over time. Moreover, modeling various metric correlations are difficult in complex Web applications. This paper addresses these problems and proposes an online anomaly detection approach for Web applications. We present an incremental clustering algorithm for training workload patterns online, and employ the local outlier factor (LOF) in the recognized workload pattern to detect anomalies. In addition, we locate the anomalous metrics with the Student's t-test method. We evaluated our approach on a testbed running the TPC-W industry-standard benchmark. The experimental results show that our approach is able to (1) capture workload fluctuations accurately, (2) detect typical faults effectively and (3) has advantages over two contemporary ones in accuracy. © 2013 Elsevier Inc.; The failure of Web applications often affects a large population of customers, and leads to severe economic loss. Anomaly detection is essential for improving the reliability of Web applications. Current approaches model correlations among metrics, and detect anomalies when the correlations are broken. However, dynamic workloads cause the metric correlations to change over time. Moreover, modeling various metric correlations are difficult in complex Web applications. This paper addresses these problems and proposes an online anomaly detection approach for Web applications. We present an incremental clustering algorithm for training workload patterns online, and employ the local outlier factor (LOF) in the recognized workload pattern to detect anomalies. In addition, we locate the anomalous metrics with the Student's t-test method. We evaluated our approach on a testbed running the TPC-W industry-standard benchmark. The experimental results show that our approach is able to (1) capture workload fluctuations accurately, (2) detect typical faults effectively and (3) has advantages over two contemporary ones in accuracy. © 2013 Elsevier Inc.
收录类别	SCI ; EI
关键词	Anomaly Detection Web Applications Local Outlier Factor
部门归属	(1) State Key Laboratory of Computer Science, Beijing 100190 PR, China; (2) Institute of Software, Chinese Academy of Sciences, Beijing 100190, PR, China; (3) University of Chinese Academy of Sciences, Beijing 100049 PR, China
语种	英语
WOS记录号	WOS:000331432600003
引用统计
内容类型	期刊论文
URI标识	http://ir.iscas.ac.cn/handle/311060/16869
专题	中国科学院软件研究所
通讯作者	Wang, T.(wangtao08@otcaix.iscas.ac.cn)
推荐引用方式 GB/T 7714	Wang, Tao ,Wei, Jun ,Zhang, Wenbo ,et al. Workload-aware anomaly detection for web applications[J]. Journal of Systems and Software,2014,89(1):19-32.
APA	Wang, Tao ,Wei, Jun ,Zhang, Wenbo ,Zhong, Hua ,Huang, Tao ,&Wang, T..(2014).Workload-aware anomaly detection for web applications.Journal of Systems and Software,89(1),19-32.
MLA	Wang, Tao ,et al."Workload-aware anomaly detection for web applications".Journal of Systems and Software 89.1(2014):19-32.