A New Resource Management and Scheduling Model in Grid Computing Based on a Hybrid Genetic Algorithm

Grid computing is one of the research hotspots in high performance computing area. Efficient scheduling of complex applications in a grid environment reveals several challenges due to its high heterogeneity, dynamic behavior, and space shared utilization. In this paper, we studied the characteristics of gird tasks, analyzed several main grid resource management models, and built a common model of grid tasks, put forward a hierarchy grid resource management and scheduling model, expounded the ideas of designing the model and described the details of it. Moreover, we proposed a hybrid genetic algorithm in its scheduling strategy, particularized the principle and the function of this algorithm as well as giving the concrete plan to put every step of the scheduling strategy into practice. Finally, the algorithm was simulated with the aid of SimGrid toolkit and it was proved an effective approach for grid scheduling.