Cost Optimization for Scientific Workflow Execution on Cloud Computing

Scientific workflow applications generally require various levels of computing power over the course of execution. The applications then often take advantage of Cloud computing due to its cost-effective, pay-as-you-go pricing model. However, the scientific workflow executions must be planned wisely in order to minimize total cost of the resource usage. In addition, lateness of completing some workflows may result in high penalty cost. In this paper, the scheduling algorithm based on GA and PSO is proposed for optimizing the workflow execution. The experiment to evaluate the scheduling efficiency is performed on the simple workflow engine developed by the authors. The result is then compared to the existing algorithms including HEFT, GA, PSO, and PSO-SA. The result shows that the proposed GAPSO algorithm has a good potential to give the minimum cost when execution time is restricted.