Providing a Technique Based on Tree and Super-Peer Structures for Resource Discovery in Grid Environment

Grid is a new generation of distributed networks and allows users to share files like the Internet. With regard to the specific features of Grid environments, such as high dynamicity and resource/members heterogeneity, there are some challenges dealing to it. One of the most important services in grid environments is the resource discovery. The purpose of resource discovery is to identify a list of available resources for assigning to tasks. In this paper, using the assignment of prime numbers as the weight for tree nodes, and combining the hierarchical and super-peer structure, a new algorithm is presented with multiple trees. The results of the experiments and comparison with the previous methods indicate the improvement of the proposed method in terms of the number of visited nodes during the search process and the reduction of processing load caused by the smaller number of weights in the indexing tree.

Keywords:

Grid computing , edge weight , resource discovery , bitmap , local resource