Active Services Resource Organization And Retrieval Technology In Grid Computing Environment

Computer network is moving into a large-scale distributed grid computing stage, having experienced the development stage of Internet and World Wide Web. Grid computing is virtualization and pooling of IT resources such as compute power, storage, network capacity, and so on into a single set of shared services and unified interfaces that can be provisioned or distributed, and then redistributed as needed. The kernel of Grid computing is cross-regional and inter-organizational resource sharing.Active service is a newly on-demand computing pattern based on the evolution of Web service. It provides users with an integrated, intelligent and personalized Web services solutions. According to users'service requirements, search, discover and dig out the components that meet requirements of users from Internet or local network, and then assemble, compile and publish the service to users.On the basis of grid resource sharing mechanism, create active services component resource repository, and then achieve active services technology. This paper introduces an active service model under the grid environment, mapping algorithm of global resources and local resources, mechanisms for grid resource discovery and resource retrieval methods of globus toolkit. In order to implement active services model under grid environment, component resource repository is the link between grid computing and active services. Grid resource discovery and retrieval methods will affect the implementation of active service technologies. In a word, the specific researches are as follows:According to several grid architectures and implementation mechanisms of active service, an active services model under the grid environment is introduced. The model can be divided into four parts:active service layer, protocol control layer, grid service interface layer and resource organization layer. Protocol control layer is critical technology in the implementation of active services under grid environment. At the same time, resource organization layer is the foundation of these two technologies.Grid resources are distributed, heterogeneous and dynamic. According to these features, mapping algorithm of WSRF-based global resources and local resources is researched to achieve global resources'efficient allocation and real-time access.Finally, grid resource organization and retrieval methods are the key aspects of this paper. Grid resource discovery mechanism is delivered into peer grid resource discovery mechanism and the hierarchical grid resource discovery mechanism. These two resource discovery mechanisms are analyzed and compared in detail. Additionally, algorithm performance is analyzed and presented by experiments. Globus Toolkit is an important software toolkit for grid computing. Resources searching methods of globus is undergone a comparative analysis by experiment too.