Energy aware list-based scheduling for parallel applications in cloud

Abstract

As the growth of energy consumption has been explosive in current data centres and cloud systems, it has drawn greater attention in academia, industry and government. Task scheduling as a core in systems, it has become an important method to reduce energy dissipation. This paper proposes an energy aware list-based scheduling algorithm called EALS for parallel applications in the context of service level agreement (SLA) on cloud data centres. First, the EALS algorithm comprehensively considers the high power processors to minimise the number of high power processors used. Then, the algorithm try to migrate some tasks from a high power processor to a low power processor for energy saving. Finally, the EALS algorithm takes a more efficient way to assign the time slots among tasks based on the dynamic voltage scaling (DVS) technique. To demonstrate the effectiveness of the EALS algorithm, randomly generated graphs and several real-world applications are tested in our experiments. The experimental results show that the EALS algorithm can save up to 43.96% energy consumption for various parallel applications as well as balance the scheduling performance.