A Security-aware Data Placement Mechanism for Big Data Cloud Storage Systems

Public clouds have become an attractive candidate to meet the ever-growing storage demands. However, storing data in public clouds increases data retrieval time and threat level for data security. These challenges drive the need for intelligent methods that solve the data placement problem to achieve high performance while satisfying the security requirement. In this paper, we propose a novel approach for data placement in cloud storage systems addressing the above challenges. With the security constraint, we first formulate the data placement problem as a linear programming model that minimizes the total retrieval time of a data, which is divided and distributed over storage nodes. We then develop a heuristic algorithm namely Security-awarE Data placement mechanism for cLOUd storage Systems (SEDuLOUS) to solve the problem. We demonstrate the effectiveness of the proposed algorithm through comprehensive simulations. The simulation results show that the proposed algorithm significantly reduces the retrieval time by up to 20% for the random-network-topology systems and 19% for the Internet2-topology system compared to baseline methods, which consider only the security requirement.