Data Placement for Multi-Tenant Data Federation on the Cloud

Due to privacy concerns of users and law enforcement in data security privacy, it becomes more difficult share among organizations. Data federation brings new opportunities the data-related cooperation organizations by providing abstract interfaces. With development cloud computing, store on achieve elasticity scalability for processing. The existing placement approaches generally only consider one aspect, which is either execution time or monetary cost, do not partitioning hard constraints. In this paper, we propose an approach enable processing with from different consists a platform named FedCube Lyapunov-based algorithm. enables cloud. algorithm creates plan partition order multiple objectives while satisfying constraints based multi-objective cost model. model composed two objectives, i.e., reducing time. We present experimental evaluation show our proposed significantly reduces total (up 69.8\%) compared approaches.