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%. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1109/CCGrid.2012.36 | CCGrid |
Keywords | Field | DocType |
excellent performance,extensive experimental dataset,maximum margin,fault prediction,matrix factorization approach,inevitable fault,isolating user,egi grid,collaborative prediction,active learning,availability,load balance,distributed system,matrix decomposition,groupware,learning artificial intelligence,matrix factorization,accuracy,sparse matrices,quality of service,grid computing,collaborative filtering,prediction algorithms | Grid computing,Collaborative filtering,Critical to quality,Load balancing (computing),Computer science,Collaborative software,Matrix decomposition,Quality of service,Grid,Distributed computing | Conference |
Citations | PageRank | References |
1 | 0.35 | 11 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Dawei Feng | 1 | 11 | 2.57 |
Cecile Germain-Renaud | 2 | 32 | 2.81 |
tristan glatard | 3 | 554 | 43.66 |