A static VM placement and hybrid job scheduling model for green data centers

• Published in: PloS one Vol. 15; no. 8; p. e0237238
• Main Authors: Movahedi Nia, Zahra, Khayyambashi, Mohammad Reza, Miri, Ali
• Format: Journal Article
• Language: English
• Published: San Francisco Public Library of Science 13.08.2020; Public Library of Science (PLoS)
• Subjects: Algorithms; Clean energy; Computer and Information Sciences; Computer centers; Computer engineering; Data centers; Energy consumption; Energy use; Engineering and Technology; Evaluation; Methods; Physical Sciences; Placement; Queues; Queuing theory; Real time; Research and Analysis Methods; Scheduling; Scheduling (Management); Servers; Service level agreements; Social Sciences; Software services; Violations; Virtual environments; Virtual machines; Workloads; Canada; Iran
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0237238

Reducing energy consumption has become a critical issue in today data centers. Reducing the number of required physical and Virtual Machines results in energy-efficiency. In this paper, to avoid the disadvantages of VM migration, a static VM placement algorithm is proposed which places VMs on hosts in a Worst-Fit-Decreasing (WFD) fashion. To reduce energy consumption further, the effect of job scheduling policy on the number of VMs needed for maintaining QoS requirements is studied. Each VM is modeled by an M/M/* queue in space-shared, time-shared, and hybrid job scheduling policies, and energy consumption of real-time as well as non-real-time applications is analyzed. Numerical results show that the hybrid policy outperforms space-shared and time-shared policies, in terms of energy consumption as well as Service Level Agreement (SLA) violations. Moreover, our non-migration method outperforms three different algorithms which use VM migration, in terms of reducing both energy consumption and SLA Violations.