Models and Modeling Infrastructures for Global Computational Platforms
Rich Wolski, Daniel Charles Nurmi, John Brevik, Henri Casanova, Andrew A. Chien · 2005
The focus of this effort is on modeling and scheduling methodologies that will enable global computing, thus extending computational grids and high-performance distributed computing to a global level. In this vein, we present a methodology for automatically fitting parametric models to machine availability data. Specifically, these new modeling technologies will support resource characterization and scheduling techniques thereby enabling robust, predictable performance.