Abstract :
Cloud platforms deploy data centers geographically distributed around the world and application providers select cloud infrastructures based on the requirements of their applications. While existing works mostly focus on the comparison on cloud services, we argue that proximity also plays a very important role when deciding in which cloud infrastructures to deploy the applications. In this paper, we design and evaluate the system, we call CSS, for automatic selection of cloud infrastructures. It not only considers the deployment cost, but also takes into account the location of cloud infrastructures, application clients and related applications, and the interaction among application components when selecting the cloud infrastructures. In order to address the scalability issue when the number of data centers and application components is large, we propose a stepwise application placement algorithm. Through experiments, we show that the algorithm is able to find a near-optimal placement policy within very short period of time.
Keywords :
client-server systems; cloud computing; computer centres; minimisation; CSS system design; CSS system evaluation; IaaS platforms; application clients; application components; application providers; automatic cloud infrastructure selection; cloud infrastructure location; cloud platforms; cloud service selection; geographically distributed data center deployment cost; near-optimal placement policy; proximity; scalability issue; stepwise application placement algorithm; Bandwidth; Cloud computing; Clustering algorithms; Peer-to-peer computing; Reliability; Scalability;