DocumentCode
2321046
Title
Distributed Monitoring with Collaborative Prediction
Author
Feng, Dawei ; Germain-Renaud, Cécile ; Glatard, Tristan
Author_Institution
Lab. de Rech. en Inf., Univ. Paris-Sud 11, Orsay, France
fYear
2012
fDate
13-16 May 2012
Firstpage
376
Lastpage
383
Abstract
Isolating users from the inevitable faults in large distributed systems is critical to Quality of Experience. We formulate the problem of probe selection for fault prediction based on end-to-end probing as a Collaborative Prediction (CP) problem. On an extensive experimental dataset from the EGI grid, the combination of the Maximum Margin Matrix Factorization approach to CP and Active Learning shows excellent performance, reducing the number of probes typically by 80% to 90%.
Keywords
collaborative filtering; fault diagnosis; grid computing; groupware; learning (artificial intelligence); matrix decomposition; monitoring; quality of service; EGI grid; active learning; collaborative prediction; distributed system monitoring; end-to-end probe; fault prediction; inevitable fault isolation; maximum margin matrix factorization approach; probe selection problem; quality of experience; Accuracy; Availability; Context; Monitoring; Prediction algorithms; Probes; Sparse matrices;
fLanguage
English
Publisher
ieee
Conference_Titel
Cluster, Cloud and Grid Computing (CCGrid), 2012 12th IEEE/ACM International Symposium on
Conference_Location
Ottawa, ON
Print_ISBN
978-1-4673-1395-7
Type
conf
DOI
10.1109/CCGrid.2012.36
Filename
6217444
Link To Document