A novel power-conscious scheduling algorithm for data-intensive precedence-constrained applications in cloud environments
Peng Xiao, Ning Han · International Journal of High Performance Computing and Networking · 2014
With the development of cloud computing, energy-efficient management and control have become a major concern in the virtualisation data centres. Although many energy-conserving policies and technologies have been proposed, most of them are categorised as device/system-oriented, which mainly concentrate on low-level energy consumption optimisation. In this paper, we propose a novel application-oriented heuristic algorithm, which has the effect of saving the data-accessing energy consumption for data-intensive workflows in virtualised cloud platforms. In the proposed algorithm, a novel heuristic metric called minimal data-accessing energy path is introduced with the aim of reducing the energy consumption of intensive data-accessing. Extensive experiments are conducted to examine the effectiveness and performance of the proposed scheduling algorithm. The experimental results show that the proposed heuristic scheduling can significantly reduce the energy consumption of storing/retrieving intermediate data generated during the execution of data-intensive workflow.