Distributed Monitoring with Collaborative Prediction - Archive ouverte HAL Access content directly
Conference Papers Year : 2012

Distributed Monitoring with Collaborative Prediction

(1) , (2, 1) , (3)
1
2
3

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 Factor- ization approach to CP and Active Learning shows excellent performance, reducing the number of probes typically by 80% to 90%.
Fichier principal
Vignette du fichier
DMCP2012-02_22.pdf (966.06 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-00673148 , version 1 (22-02-2012)

Identifiers

  • HAL Id : hal-00673148 , version 1

Cite

Dawei Feng, Cecile Germain-Renaud, Tristan Glatard. Distributed Monitoring with Collaborative Prediction. 12th IEEE International Symposium on Cluster, Cloud and Grid Computing (CCGrid'12), May 2012, Ottawa, Canada. epub ahead of print. ⟨hal-00673148⟩
427 View
326 Download

Share

Gmail Facebook Twitter LinkedIn More