Abstract
This paper proposes an effective dynamic data placement strategy in MMDB cluster system that combines the dynamic reallocation and replication into a unified process. The objective of this placement strategy is to locate the data fragments at different sites so as to minimize the total data transfer cost and the response time incurred in executing a given set of queries. This strategy reallocates data with respect to changing data access pattern for each fragment in which data is maintained in current site, migrated or created new replicas on remote sites depend on accessing frequency and average response time. The simulation results show that the proposed strategy is suitable for MMDB cluster because it provides a better response time and maximize the locality of processing so we could develop parallel processing of MMDB in cluster platform.