Intelligent Automated Diagnosis of Client Device Bottlenecks in Private Clouds

Author

Widanapathirana, Chathuranga ; Li, J. ; Sekercioglu, Y.A. ; Ivanovich, Milosh ; Fitzpatrick, Paul

Author_Institution

Dept. of Electr. & Comput. Syst. Eng., Monash Univ., Melbourne, VIC, Australia

fYear

2011

fDate

5-8 Dec. 2011

Firstpage

261

Lastpage

266

Abstract

We present an automated solution for rapid diagnosis of client device problems in private cloud environments: the Intelligent Automated Client Diagnostic (IACD) system. Clients are diagnosed with the aid of Transmission Control Protocol (TCP) packet traces, by (i) observation of anomalous artifacts occurring as a result of each fault and (ii) subsequent use of the inference capabilities of soft-margin Support Vector Machine (SVM) classifiers. The IACD system features a modular design and is extendible to new faults, with detection capability unaffected by the TCP variant used at the client. Experimental evaluation of the IACD system in a controlled environment demonstrated an overall diagnostic accuracy of 98%.

Keywords

cloud computing; fault diagnosis; support vector machines; transport protocols; anomalous artifacts; client device bottlenecks; intelligent automated client diagnostic system; intelligent automated diagnosis; modular design; private cloud environments; support vector machine classifiers; transmission control protocol packet traces; Accuracy; Cloud computing; Computational fluid dynamics; Feature extraction; Servers; Training; Vectors; automated system; client diagnosis; cloud management; intelligent inference; packet traces;

fLanguage

English

Publisher

ieee

Conference_Titel

Utility and Cloud Computing (UCC), 2011 Fourth IEEE International Conference on

Conference_Location

Victoria, NSW

Print_ISBN

978-1-4577-2116-8

Type

conf

DOI

10.1109/UCC.2011.42

Filename

6123506