CAJ | 학술논문

Grids enable users to share and access large collections and various types of resources in wide areas, and how to locate resources in such dynamic, heterogeneous and autonomous distributed environments is a key and challenging issue. In this paper, a three-level decentralized and dynamic VEGA Infrastructure for Resource Discovery (VIRD) is proposed. In this architecture, every Border Grid Resource Name Server (BGRNS) or Grid Resource Name Server (GRNS)has its own local policies, governing information organization, management and searching. Changes in resource information are propagated dynamically among GRNS servers according to a link-statelike algorithm. A client can query its designated GRNS either recursively or iteratively. Optimizing techniques, such as shortcut, are adopted to make the dynamic framework more flexible and efficient. A simulator called SimVIRD is developed to verify the proposed architecture and algorithms.Experiment results indicate that this architecture could deliver good scalability and performance for grid resource discovery.