Home > Published Issues > 2015 > Volume 10, No. 12, Dec. 2015 >

SELDAC: Software-Defined Storage based Efficient Load Distribution and Auto Scaling in Cloud Data Centers

Renuga Kanaga and Khin Mi Mi Aung
Data Center Technology Division, A*STAR Data Storage Institute, Singapore

Abstract—Cloud computing allows the users to access the shared pool of configurable resources such as compute, network and storage on-demand basis from the cloud Data Centers. Cloud storage provides the storage resources to the cloud users over the network. The massive growth of cloud data due to the applications such as video streaming, big data processing, social networking, banking and scientific applications fueled the storage demand. An increase in storage demand resulted in the expansion of the cloud storage with additional storage nodes. The expansion of the cloud storage necessitates the migration of data across the storage nodes to keep them balanced. Efficient management and migration of tera bytes or peta bytes of such cloud data depends not only on the storage availability but also on the networking cost which is proportional to the distance and the bandwidth requirement. In this scenario, software defined environment opens up the new opportunities to orchestrate the network and storage resources control strategies to provide an effective solution. In this paper, we present the software-defined orchestration framework for efficient load distribution and auto scaling mechanism and shows that it improves the overall efficiency in terms of latency and retrieval cost. We demonstrate the effectiveness and the efficiency of the proposed mechanism using simulations.

Index Terms—Software-defined storage, software-defined networking, load distribution, orchestration, cloud data center

Cite: Renuga Kanaga and Khin Mi Mi Aung, “SELDAC: Software-Defined Storage based Efficient Load Distribution and Auto Scaling in Cloud Data Centers," Journal of Communications, vol. 10, no. 12, pp.1020-1026, 2015. Doi: 10.12720/jcm.10.12.1020-1026