A Positive Preprocessing Framework for Mapping Traditional Replica Selection Algorithms

Replica selection algorithms in data grid have been proposed to improve the processing capability of data intensive jobs. However, the processing time of these algorithms is increased rapidly with the increase of grid sites and replicas in data grid. To solve this problem, a positive preprocessing framework for mapping traditional replica selection algorithms based on OLAP, named as OLAP4RS, is proposed. Its architecture, processing procedure, and mapping mechanism are discussed.