Local search based approach in grid scheduling using Simulated Annealing

Grid computing is a High Performance Computing environment. Load balancing is an important aspect of Grids, which provide the necessary resource management features. This decision is made by a resource management component of the Grid, namely, the Grid scheduler. While Grid users are often interested in satisfaction of their Quality of Service (QoS) requirements, these cannot be satisfactorily handled by commonly used queue-based approaches. In this paper, a local search based approach based on Simulated Annealing (SA) is proposed as a periodical optimizer to other dynamic, space shared and schedule-based scheduling policies. SA is found to be most reliable method to apply in practice. Using SA it has been proved that it is possible to converge to the best solution.