Performance analysis of multi-institutional data sharing in the Clouds4Coordination system

Abstract

Cloud computing is used extensively in Architecture/ Engineering/ Construction projects for storing data and running simulations on building models (e.g. energy efficiency/environmental impact). With the emergence of multi-Clouds it has become possible to link such systems and create a distributed cloud environment. A multi-Cloud environment enables each organisation involved in a collaborative project to maintain its own computational infrastructure/ system (with the associated data), and not have to migrate to a single cloud environment. Such infrastructure becomes efficacious when multiple individuals and organisations work collaboratively, enabling each individual/ organisation to select a computational infrastructure that most closely matches its requirements. We describe the “Clouds-for-Coordination” system, and provide a use case to demonstrate how such a system can be used in practice. A performance analysis is carried out to demonstrate how effective such a multi-Cloud system can be, reporting “aggregated-time-to-complete” metric over a number of different scenarios.