Abstract
The Grid Computing is a new emerging computing infrastructure. It provides a new platform to share computational resources. Every participant has his own jobs to execute. How to schedule all participants’ jobs is an important problem. For each job, we have an execution workflow. In the traditional system, there is a centralized scheduler. Because of some problems, like single-node failure, and load-balancing consideration, we want to solve the scheduling problem without a central scheduler. In this paper, we take the market-oriented programming into our simulation. We create several Workflow Agents to plan feasible schedules for the work-flows according to the market prices of the resources and a Market Broker Agent to coordinate the simultaneous resources accesses. We describe our system model and compare two methods -- probability and α-method -- with the centralized scheduling algorithm FCFS