Investigating of probabilistic load balancing algorithms in grid computing

Abstract

The computing grid is a distributed parallel processing system that share and choosing resources dynamically and provide need of user operation power, cost and quality. Grid management resources does as a diagnostic and assigning resources scheduling and resource monitoring in grid. Scheduling process directs tasks to suitable resources. It must take place somehow that load work distributed equally on resources to get the maximum interest out of existed resource, establishing load balancing is one the important performance factors in grid resource management efficiency. in this paper, a model in accordance with tree and probabilistic scheduling algorithms with load balancing purpose was suggested, that in this algorithm class of work, cost, deadline and herd behavior have considered. We investigate the probability of a resource success in different algorithms in accordance with complete time, execute time and cost. Probabilistic algorithms chooses the resources that have better past and leave the duties to it, in case of execution or non-execution on the resource the source will give a reward or punishment.