This paper describes a study of predicting machine availabilities and user presence in a pool of desktop computers. The study is based on historical traces collected from 32 machines, and shows that robust prediction accuracy can be achieved even in this highly volatile environment. The employed methods include a multitude of classification methods known from data mining, such as Bayesian methods and Support Vector Machines. Further contribution is a time series framework used in the study which automates correlations search and attribute selection, and allows for easy reconfiguration and efficient prediction. The results illustrate the utility of prediction techniques in highly dynamic computing environments. Potential applications for proactive management of desktop pools are discussed.
Subject
Desktop Grid,prediction
Cited by
Year 2013 : 1 citations
Javadi, Bahman and Kondo, Derrick and Iosup, Alexandru and Epema, Dick, ”The Failure Trace Archive: Enabling the comparison of failure measurements and models of distributed systems”, Journal of Parallel and Distributed Computing, 2013, Elsevier.
Year 2011 : 1 citations
Yi, S.; Andrzejak, A. & Kondo, D. Monetary cost-aware checkpointing and migration on Amazon cloud spot instances Services Computing, IEEE Transactions on, IEEE, 2011. DOI: 10.1109/TSC.2011.44
Year 2010 : 5 citations
Kondo, Derrick and Javadi, Bahman and Iosup, Alexandru and Epema, Dick, "The Failure Trace Archive: Enabling Comparative Analysis of Failures in Diverse Distributed Systems", 10th IEEE/ACM International Conference onCluster, Cloud and Grid Computing (CCGrid), 2010, DOI: 10.1109/CCGRID.2010.71.
Sangho Yi; Kondo, D.; Andrzejak, A, “Reducing Costs of Spot Instances via Checkpointing in the Amazon Elastic Compute Cloud”, 2010 IEEE 3rd International Conference on Cloud Computing (CLOUD), pp 236-243, 2010, DOI: 10.1109/CLOUD.2010.35.
Garcia, J.R, Lerida, J.L, Hernandez, P., “Scheduling Soft Real-Time Applications on NOWs”, 2010 18th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP), 2010, DOI: 10.1109/PDP.2010.62. Toktam Ghafarian-M., Hossein Deldari, "Task Execution Availability Prediction in the Enterprise Desktop Grid", Proceedings of the 9th IASTED International Conference, Parallel and Distributed Computing and Networks (PDCN 2010), 2010.
[PDF] http://profdoc.um.ac.ir/articles/a/1016838.pdf
Toktam Ghafarian-M., Hossein Deldari, "Task Execution Availability Prediction in the Enterprise Desktop Grid", Proceedings of the 9th IASTED International Conference, Parallel and Distributed Computing and Networks (PDCN 2010), 2010.
