Data placement using Dewey Encoding in a hierarchical data grid

Nowadays, data grids can be seen as frameworks responding to the needs of large scale applications by affording so many resources. These are distributed on different geographically locations, but are organized to provide an integrated service. This paper studies replica placement in hierarchical data grid systems taking into account the following important issue: The hierarchical data grid can be presented as a tree structure. This structure will be labeled by a new labeling scheme (called Dewey Encoding) that lies at the core of query processing for many XML databases. This scheme avoids unnecessary replications and achieves good performance by balancing the load of replica servers. The good performance of the proposed algorithm is based on minimizing the Mean Job Execution time and Network utilization.