Research on Scheduling Strategy in Parallel Applications Based on a Hybrid Genetic Algorithm

Efficient scheduling of parallel applications in a dynamic environment reveals several challenges due to its high heterogeneity, dynamic behavior, and space shared utilization. In this paper, first we compared some typical scheduling strategies and pointed out their shortcomings, and then we proposed a new scheduling strategy based on an advanced genetic algorithm, finally we simulated the strategy with the aid of SimGrid toolkit and it was proved reasonable and efficient. It is an effective approach for tasks scheduling in parallel applications.