Research On Data Replicating Management In Data Grid

Computational grid has been used to solve a wide area network distributed resource sharing, networking and interoperability issues, with the rapid development of data-intensive applications and the explosive growth of data, Data Grid emerged and become another focus of grid.Data Replica Management is one of the critical parts in Data Grids. It has been widely applied in the areas of distributed database, mobile database, Internet and other distributed environments. Replication can reduce access latency, and balance the loads for distributed applications. Excellently Replica location is also important to reduce access latency in data grids. This paper investigates on two component of replica management in data grids: replicas creation strategies and replica location mechanism.Replicas creation strategies tend to make decisions on where and when to create which data replicas. we propose our replicas creating strategy based on investigating and analyzing the related researches. The method employ the different methods between the inner domain and the inter domain. This method can also reduce access latency, improve data locality and improve the overall performance of the grid system.Replica location is also important to reduce access latency in data grids. we proposed an improved replica location mechanism--Decentralized Dynamic Replica Location method(DDRL),based on investigating and analyzing some Dynamic self-Adaptive Replica Location Method.