Abstract
In Grid environment, some potential resources to schedule a given job are not discovered because existing systems are based on syntactic resource matching. However they can partially fulfill the request by different degrees of match. This is due to semantic heterogeneity of terminologies being used to describe the same Grid resource. Moreover, efficient resource management is necessary for better resource utilization. In this paper, we propose semantic-based Grid Resource Management (S-GRM) system which utilizes semantic metadata to describe and discover both logical and physical resources. The proposed system integrates the component search into existing Grid application development environment and discovery of nodes in resource manager in a comprehensive perspective. We also developed a prototype implementation of our proposed architecture using ProActive Grid middleware. The results have shown that our proposed approach is effectively useful as precision of the system is increased and the number of ProActive nodes in resource discovery is more than in existing syntax-based system. As a result, component reusability is increased and there are more options for resource manager to select a suitable node from the available resource.