A statistical approach to detect application-level failures in internet services

Authors:
Li Wu;Lu Cheng;Xue-song Qiu;Yan Qiao
Affiliations:
Networking and Switching Technology State Key Laboratory, Beijing University of Posts and Telecommunications, Beijing;Networking and Switching Technology State Key Laboratory, Beijing University of Posts and Telecommunications, Beijing;Networking and Switching Technology State Key Laboratory, Beijing University of Posts and Telecommunications, Beijing;Networking and Switching Technology State Key Laboratory, Beijing University of Posts and Telecommunications, Beijing
Venue:
FSKD'09 Proceedings of the 6th international conference on Fuzzy systems and knowledge discovery - Volume 5
Year:
2009

Citing 3
Cited 0

Combining Visualization and Statistical Analysis to Improve Operator Confidence and Efficiency for Failure Detection and Localization

ICAC '05 Proceedings of the Second International Conference on Automatic Computing
Distributed Diagnosis of Failures in a Three Tier E-Commerce System

SRDS '07 Proceedings of the 26th IEEE International Symposium on Reliable Distributed Systems
Detecting application-level failures in component-based Internet services

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

To ensure the QoS in Internet Services, it is critical to detect the failures quickly and accurately. However, it is a difficult problem because one must extract and interpret fail patterns from large amounts of high-dimensional data. Presently, most technologies do not fit for large-scale system because of the complexity. Moreover, the detecting accuracy of them is relatively low. In this paper, we propose a general method which can deal with high-dimensional data efficiently and adapt for the updates of observed system. Furthermore, the detecting time grows slowly along with the sharp increase in the mount of data. An experiment is given afterwards to show how the method can be used and in the end a conclusion is drawn that the method can be effectively used to detect the failures in the applicationlevel of Internet services.