A new fuzzy based dynamic data replication algorithm in data grids

摘要

Data grid deals with data intensive applications, and provides the ability to access and manage data intensive resources across widely distributed communities. Data replication, through creating many replicas in different sites, reduces the data access time, increases reliability and fault tolerance, and also improves the performance of systems. Here, through improving the modified BHR (MBHR) method, we proposed a novel dynamic algorithm named fuzzy_rep for data replication in data grids. The algorithm uses a fuzzy interfere system for finding suitable site where the file may be required in the future with high probability. Based on file access history, the purposed algorithm predicts future needs of grid sites. The algorithm was tested using a grid simulator, OptorSim developed by European Data Grid Projects. The simulation results show that our proposed algorithm has better performance in comparison with other algorithms in terms of the job execution time and percentage of storage filled.