Agent based Load Balancing Model for Service based Grid Applications

Grids can integrate the distributed resources on the Web such as computing, data, storage, software and manpower to accomplish collaborative tasks. Service grid has combined Web service with the grid, and over the next decade lots of business will be completely transformed by using grid-enabled Web services to share not only applications but also computer power efficiently. However, in the business process scheduling of the service grid, many businesses will be integrated by using the grid services across Internet, thus we should balance the load in the service grid to enhance the resource's utility and increase the system's throughput. Furthermore, many of the services are not dependable for loose coupling, high distribution and so on. To deal with the load balancing and dependence in service grid environment, we propose a distributed scheduling model oriented to grid service execution mechanisms. In this model, we apply the agents to enable service-level load balancing and fault tolerance. To improve the scheduling efficiency, we also define a degree of dependability to concisely denote availability of the grid resources and the grid services. Agents are responsible for sensing the context of the grid, and serve as the scheduler for dynamic load adjustment and fault tolerance. Corresponding simulation tests are implemented and their result s indicated that this model and its supplementary mechanisms are suitable to service grid environment