Building the federation of cloud service for big data

摘要

The demand for agile and flexible business application for big data has sparked interest in using cloud computing technology. Due to the limitation of provider's capability and the magnanimity of task quantity for big data, a single cloud provider may not offer enough service resources. However, a service federation among multiple providers can effectively solve this problem. This paper proposes the framework of cloud federation and introduces the basic processes of building service federation among multiple cloud providers. Moreover, we propose a multi-objectives task assigning model in the federation. A genetic algorithm based heuristic approach is developed as the optimization method. Eventually, some simulation experiments are conducted to illustrate the effectiveness of the model.