Abstract: An efficient and secure mechanism to partition computations across public and private machines in a hybrid cloud setting was explored. Aiming at the restrictions in different levels for public cloud usage, the optimal risk-aware workload distribution problem was formalized as a mechanism for workload response time minimization. A dynamic programming approach that results in an optimal distribution of the query workload was proposed, which that searches for an optimal computation and data partitioning scheme given a query workload and public cloud usage boundaries (resource allocation cost and sensitive data disclosure). Finally, the performance of the dynamic programming approach was evaluated. Experimental results show that the proposed scheme can lead to a major performance gain by exploiting both the hybrid cloud components without violating any pre-determined public cloud usage constraints.


论文引用格式：刘 颖,甘 泉,王 宇.混合云环境中改进的工作负载分配方案.电信科学,2015024
Liu Y,Gan Q,Wang Y.Improved workload distribution scheme in hybrid cloud setting.Telecommunications Science,2015024