Cost and efficiency-based scheduling on a general framework combining between cloud computing and local thick clients

Today, the rapid growth of the large-scale applications conduces to a difficult challenge to individuals as well as the commercial organizations due to the limitation of the local computing resources. Meanwhile, the extension of the local computing platforms requires a huge investment about both finance and human power. Therefore, the use of nearly-unlimited resources and on-demand scaling of Cloud computing is considered as a potential solution to address the problems above. However, since Cloud computing is built from a pay-as-you-go model, the novel application scheduling approaches are challenged to guarantee the high efficiency of application execution and the reasonable cost for renting Cloud resources. In this paper, we present a novel framework built from the combination between the computing resources on Cloud computing and the computing components in the local systems. The key component of this framework is the Cost with Finish Time-based scheduling algorithm, which provides the balance between performance of application schedule and the mandatory cost for the use of Cloud resources. The experiments and comparison with the other scheduling approaches demonstrated the potential benefits of our proposed algorithm.