Hierarchical and frequency-aware model predictive control for bare-metal cloud applications

Yukio Ogawa, Go Hasegawa, Masayuki Murata

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Bare-metal cloud provides a dedicated set of physical machines (PMs) and enables both PMs and virtual machines (VMs) on the PMs to be scaled in/out dynamically. However, to increase efficiency of the resources and reduce violations of service level agreements (SLAs), resources need to be scaled quickly to adapt to workload changes, which results in high reconfiguration overhead, especially for the PMs. This paper proposes a hierarchical and frequency-aware auto-scaling based on Model Predictive Control, which enable us to achieve an optimal balance between resource efficiency and overhead. Moreover, when performing high-frequency resource control, the proposed technique improves the timing of reconfigurations for the PMs without increasing the number of them, while it increases the reallocations for the VMs to adjust the redundant capacity among the applications; this process improves the resource efficiency. Through trace-based numerical simulations, we demonstrate that when the control frequency is increased to 16 times per hour, the VM insufficiency causing SLA violations is reduced to a minimum of 0.1% per application without increasing the VM pool capacity.

Original languageEnglish
Title of host publicationProceedings - 11th IEEE/ACM International Conference on Utility and Cloud Computing, UCC 2018
EditorsJosef Spillner, Alan Sill
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages11-20
Number of pages10
ISBN (Electronic)9781538655047
DOIs
Publication statusPublished - 2019 Jan 4
Externally publishedYes
Event11th IEEE/ACM International Conference on Utility and Cloud Computing, UCC 2018 - Zurich, Switzerland
Duration: 2018 Dec 172018 Dec 20

Publication series

NameProceedings - 11th IEEE/ACM International Conference on Utility and Cloud Computing, UCC 2018

Conference

Conference11th IEEE/ACM International Conference on Utility and Cloud Computing, UCC 2018
CountrySwitzerland
CityZurich
Period18/12/1718/12/20

Keywords

  • Autoscaling
  • Bare-metal cloud
  • Frequency-aware
  • Model Predictive Control
  • Resource reconfiguration

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Hardware and Architecture
  • Information Systems and Management

Fingerprint Dive into the research topics of 'Hierarchical and frequency-aware model predictive control for bare-metal cloud applications'. Together they form a unique fingerprint.

Cite this