Skip to Main Content
Cloud Computing is the evolution of the Grid Computing paradigm towards service-oriented architectures. The terminology applied to this kind of processing, when describing shared resources, refers to the concept of X as a Service. Such resources are available on demand and at a significantly lower cost compared to self-delivery of individual components (in addition to the price of suitable hardware and software, it is also necessary to remember about the cost of specialized support for such resources). Current Cloud Computing solutions (e.g., Amazon EC2, Microsoft Azure) only provide access to basic computational and storage resources. They do not permit custom modifications of network topology layouts or parameters (such as security, communication separation, QoS guarantees, etc.). The possibility of influencing network topology parameters is crucial in cluster solutions. The purpose of this paper is to discuss various forms of mapping cluster topology requirements into Cloud environments to achieve higher reliability and scalability of application executed within Cloud resources.
Date of Conference: 20-25 Sept. 2010