A novel load balancing method in an agent-based grid

A computational grid is a widespread computing environment which provides huge computational power for large-scale distributed applications. One of the most important issues in such an environment is resource management. Load balancing which is a part of resource manager, has a considerable effect on resources´ performance. There are several factors which affect the stability of the load balancing in the grid. Among these factors, accurate criterion for estimating the workload, considering the workload transmission cost, validity of the information about other nodes and the overhead imposed by the method are more effective. In this paper we propose a novel method for load balancing which tries to satisfy these factors. The proposed method is implemented on an agent-based resource management system, called ARMS. There are several simulations which indicate that the proposed method outperforms than similar methods.