An Intelligent Replication Framework for Data Grids

Data grid systems are evolving as prominent platforms of choice for many scientific disciplines. Many of the experiments and applications of such disciplines require use of huge amounts of data located at geographically distributed locations. In this paper, we present an intelligent data and replica management framework coupled with computational job scheduling, to provide an integrated environment for efficient access to data and job scheduling. The main goal of our approach is to build a replica management service that integrates replica placement optimization mechanisms, and dynamic replication techniques, coupled with computation and job scheduling algorithms to provide better system performance in data grids. We evaluate our framework on a Data Grid model adopted from the Eu-Data grid project. Our results show promising improvement in the performance of the grid and job execution time.