An Optimized Computational Model for Multi-Community-Cloud Social Collaboration

Community Cloud Computing is an emerging and promising computing model for a specific community with common concerns, such as security, compliance and jurisdiction. It utilizes the spare resources of networked computers to provide the facilities so that the community gains services from the cloud. The effective collaboration among the community clouds offers a powerful computing capacity for complex tasks containing the subtasks that need data exchange. Selecting the best group of community clouds that are the most economy-efficient, communication-efficient, secured, and trusted to accomplish a complex task is very challenging. To address this problem, we first formulate a computational model for multi-community-cloud collaboration, namely
$MC^{3}$
. The proposed model is then optimized from four aspects: minimizing the sum of access cost and monetary cost, maximizing the security-level agreement and trust among the community clouds. Furthermore, an efficient and comprehensive selection algorithm is devised to extract the best group of community clouds in
$MC^{3}$
. Finally, the extensive simulation experiments and performance analysis of the proposed algorithm are conducted. The results demonstrate that the proposed algorithm outperforms the minimal set coverings based algorithm and the random algorithm. Moreover, the proposed comprehensive community clouds selection algorithm can guarantee good global performance in terms of access cost, monetary cost, security level and trust between user and community clouds.