An evaluation of availability comparison and prediction for optimized resource selection in the grid

Resources in the Grid exhibit different availability properties and patterns over time, mainly due to their administrators' policies for the Grid, and the different domains to which they belong, e.g. non-dedicated desktop Grids, on-demand systems, P2P systems etc. This diversification in availability properties makes availability-aware resource selection, for applications with different fault tolerance capabilities, a challenging problem. To address this problem, we introduce new availability metrics for resource availability comparison. We further predict resource availability considering their availability policies. We introduce a new resource availability predictor based on pattern matching through availability pattern recognition and classification for resource instance and duration availability, and compare it with other methods. Notably we are able to achieve an average accuracy of more than 80% in our predictions.