Abstract

In large-scale grid platforms, providing fault-tolerance for users is always a challenging task because of the uncertainty of network resources. In this paper, we present an intelligent agent based metascheduler, which is aiming at improving the faulttolerance of grid systems when running user’s application. The proposed meta-scheduler is designed as an extendable framework, which allows plugging in multiple scheduling policies for deal with different scenarios. The agent-based scheduling framework enables grid systems to deploy their local schedulers in a flexible manner. Extensive experiments are conducted to investigate the performance of the proposed meta-scheduler, and the results show that it is effective to provide enhanced dependability for grid users, especially when the system is across multiorganization.