NEW MODEL OF FRAMEWORK FOR TASK SCHEDULING BASED ON MOBILE AGENTS

Compute-intensive applications and applications with high volume of data need strong processing power and considerable storage resources. To reach the required performance, multiple machines should be associated in order to handle the distributed tasks. In this paper, we propose a new framework for task distribution based on mobile agents. In the proposed model, a dispatcher agent is used to distribute parallel tasks to worker agents. Each worker agent is deployed in a node of the distributed system according to the load balancing system. The proposed framework is build using three layers which are the user task producer, the scheduling load balancing layer and the workers layer. After presenting the architecture and the structure of the proposed model, an example of application, relating to the distributed image processing, is presented to improve the performance of this framework.