期刊名称：Bulletin of the Technical Committee on Data Engineering
出版年度：2012
卷号：35
期号：4
出版社：IEEE Computer Society
摘要：A hybrid cloud is a composition of two or more distinct cloud infrastructures (private, community, orpublic) that remain unique entities, but are bound together by standardized or proprietary technologythat enables data and application portability [1]. The emergence of the hybrid cloud paradigm hasallowed end-users to seamlessly integrate their in-house computing resources with public cloud servicesand construct potent, secure and economical data processing solutions. An end-user may be requiredto consider a variety of factors, which include several hybrid cloud deployment models and numerousapplication design criteria, during the development of their hybrid cloud solutions. Although a multitudeof applications could be developed through a combination of the aforementioned deployment models anddesign criteria, the common denominator among these applications is that they partition an application'sworkload over a hybrid cloud. Currently, there does not exist a framework that can model this workloadpartitioning problem such that all the previously mentioned factors are considered. Therefore, in thispaper we present our vision for the formalization of the workload partitioning problem such that anend-user's requirements of performance, data security and monetary costs are satisfied. Furthermore,to demonstrate the .exibility of our formalization, we show how existing systems such as [2] [3] can bederived from our general workload partitioning framework through an instantiation of the appropriatecriteria.
