Title: Energy aware list-based scheduling for parallel applications in cloud

Authors: Yongxing Liu; Kenli Li; Zhuo Tang; Keqin Li

Addresses: College of Computer Science and Electronic Engineering, Hunan University, Changsha, 410082, China ' College of Computer Science and Electronic Engineering, Hunan University, Changsha, 410082, China ' College of Computer Science and Electronic Engineering, Hunan University, Changsha, 410082, China ' College of Computer Science and Electronic Engineering, Hunan University, Changsha, 410082, China

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 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 tries 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.

Keywords: cloud data centre; directed acyclic graph; dynamic voltage scaling; DVS; energy aware scheduling; service level agreement; SLA.

DOI: 10.1504/IJES.2018.095021

International Journal of Embedded Systems, 2018 Vol.10 No.5, pp.345 - 355

Received: 09 Mar 2015
Accepted: 12 May 2015
Published online: 01 Oct 2018 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article