Skip to main navigation Skip to search Skip to main content

Energy-aware dynamic virtual machine consolidation for cloud datacenters

    Research output: Contribution to journalArticlepeer-review

    92 Citations (Scopus)
    361 Downloads (Pure)

    Abstract

    Resource over provisioning in cloud computing consumes energy excessively. Energy-aware dynamic virtual machine consolidation (DVMC) reduces energy consumption without compromising service level agreement. In this paper, we put forward a new framework of DVMC for green cloud computing. In particular, we propose a new virtual machine (VM) placement policy, namely, space aware best fit decreasing (SABFD) and a new migration VM selection policy, namely, high CPU utilization-based migration VM selection (called HS). Thorough simulations are carried out to evaluate the performances of different energy-aware DVMC plans based on real-world workload traces, with DVMC plans as various combinations of host overload detection, migration VM selection, and VM placement policies. The simulation results show that DVMC plans with SABFD policy or with HS policy outperforms alternative DVMC plans. What is more, a DVMC plan with both SABFD and HS policies makes the best performance.
    Original languageEnglish
    Pages (from-to)15259-15273
    Number of pages15
    JournalIEEE Access
    Volume6
    DOIs
    Publication statusPublished - 8 Mar 2018

    UN SDGs

    This output contributes to the following UN Sustainable Development Goals (SDGs)

    1. SDG 7 - Affordable and Clean Energy
      SDG 7 Affordable and Clean Energy

    Keywords

    • cloud computing
    • green cloud computing
    • dynamic virtual machine consolidation
    • virtual machine placement
    • cloud datacenter

    ASJC Scopus subject areas

    • General Engineering
    • General Computer Science
    • General Materials Science

    Fingerprint

    Dive into the research topics of 'Energy-aware dynamic virtual machine consolidation for cloud datacenters'. Together they form a unique fingerprint.

    Cite this