Energy-efficient virtual content distribution network provisioning in cloud-based data centers

Dan Liao, Gang Sun, Guanghua Yang, Victor Chang

    Research output: Contribution to journalArticlepeer-review

    7 Citations (Scopus)

    Abstract

    Cloud-based content distribution networks (CDNs) consist of multiple servers that consume large amounts of energy. However, with the development of a cloud-based software defined network (SDN), a new paradigm of the virtual content distribution network (vCDN) has emerged. In an emerging cloud-based vCDN environment, the development and adjustment of vCDN components has become easier with the aid of SDN technology. This transformation provides the opportunity to use vCDNs to reduce energy consumption by adjusting the scale of the vCDN components. Energy costs can be reduced by deactivating the commercial servers carrying the software components of the vCDN, such as replica servers, the firewall or routers. In addition, the CDN requires a high service level agreement (SLA) to respond to clients’ requests, potentially consuming large amounts of energy. In this research, we focus on the issue of the energy savings of a CDN in a cloud computing environment while maintaining a high quality of service (QoS). We propose an approximate algorithm termed max flow forecast (MFF) to determine the number of software components in the vCDN. Additionally, we use a real traffic trace from a website to assess our algorithm. The experimental results show that MFF can produce a larger energy reduction than the existing algorithms for an identical SLA. We fully justify our research as a good example for the emerging cloud.

    Original languageEnglish
    Pages (from-to)347-357
    Number of pages11
    JournalFuture Generation Computer Systems
    Volume83
    DOIs
    Publication statusPublished - 5 Feb 2018

    Fingerprint

    Dive into the research topics of 'Energy-efficient virtual content distribution network provisioning in cloud-based data centers'. Together they form a unique fingerprint.

    Cite this