A semantic-based centralized resource discovery model for grid computing

Grid computing aggregates computing resources to execute computationally complex jobs. Identifying an appropriate resource selection mechanism for Grid jobs is a major concern because an appropriate mechanism could helps to schedule and allocate resources better. In existing real grid systems, centralized and hierarchical resource discovery models are very common, where providers publish resources with a fixed schema and users follow the same schema in order to find appropriate resources for jobs. Lack of coordination between users and providers in a highly heterogeneous Grid environment often results in user jobs failing in finding relevant resources. One of the reasons for rejection of jobs is the usage of fixed schema between user requests and provider resources. We present a semantic-based centralized resource discovery model to improve job success probability and utilization of resources. Preliminary simulations carried out using GridSim simulator show improved success probability and enhanced utilization of resources.