A Predictive Algorithm for Replication Optimization in Data Grids

Abstract

Previous replication algorithms in grids only consider the file access times. They do not put user access patterns into consideration. In this paper, we propose a predictive algorithm for replication based on user's behaviors. The basic assumption is that if a user accesses a file, then he will access this file again. We can predict what the next file would be accessed with largest probability according to the access history. Our algorithm is modified from the context modeling algorithm proposed by Thomas M. Kroeger in 2001. We adapt his algorithm for Grid environment.