Automated Anomaly and Root Cause Detection in Distributed Systems

G.D.K.Kishore; Maddali Sravanthi; Kurma Siva Naga Mrudhula; J Sandeep; Kilaru Swapna

doi:https://doi.org/10.14445/22315381/IJETT-V3I1P209

Research Article | Open Access | Download PDF

Volume 3 | Issue 1 | Year 2012 | Article Id. IJETT-V3I1P209 | DOI : https://doi.org/10.14445/22315381/IJETT-V3I1P209

Automated Anomaly and Root Cause Detection in Distributed Systems

G.D.K.Kishore , Maddali Sravanthi , Kurma Siva Naga Mrudhula , J Sandeep , Kilaru Swapna

Citation :

G.D.K.Kishore , Maddali Sravanthi , Kurma Siva Naga Mrudhula , J Sandeep , Kilaru Swapna, "Automated Anomaly and Root Cause Detection in Distributed Systems," International Journal of Engineering Trends and Technology (IJETT), vol. 3, no. 1, pp. 47-52, 2012. Crossref, https://doi.org/10.14445/22315381/IJETT-V3I1P209

Abstract

It is a challenging issue to identify a defective system in a large scale network. The data collected from the distributed systems for troubleshooting is very huge and may contain noisy data, so manual checking and detecting of the abnormal node is time c onsuming and error prone. In order to solve this, we need to develop an automated system that detects the anomaly. Though the defective node is found it has to be rectified, for this we need to know the root cause of the problem. In this paper we present a n automated mechanism for node level anomaly detection in large - scale systems and the root cause for anomaly. A set of data mining techniques are used here to analyze the collected data and to identify the nodes acting differently from others. We use Indep endent Component Analysis (ICA) for feature extraction. We also present some of the mechanisms needed to know the root cause of the problem. So the results will be abnormal nodes and problem to be rectified in them. These can be validated manually.

Keywords

node level anomaly identification, large - scale systems, data mining techniques, independent component analysis.

References

[1] A. Hyva¨rinen and E. Oja, Independent Component Analysis:Algorithms and Applications,” Neural Networks, vol. 13, nos. 4/5,pp. 411-430, 2000.
[2] E. Knorr, R. Ng, and V. Tucakov, “DistanceBased Outliers: Algorithms and Applications,” The VLDB J., vol. 8, no. 3, pp. 237- 253, 2000.
[3] Roohi Shabrin S., Devi Prasad B., Prabu D., Pallavi R. S., and Revathi P.“Memory Leak Detection in Distributed System” - World Academy of Science, Engineering and Technology 16 2006. www.waset.org/journals/waset/v16/v16- 15.pdf
[4] Eric Koskinen andMaurice Herlihy Dreadlocks: Efficient Deadlock Detection www.cl.cam.ac.uk/~ejk39/papers/dreadlocksspaa08.pdf