E-VM: An Elastic Virtual Machine Scheduling Algorithm to Minimize the Total Cost of Ownership in a Hybrid Cloud

Milan M. Shetti, Bingzhe Li, David H.C. Du

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

3 Scopus citations

Abstract

A hybrid cloud that combines both public and private clouds is becoming more and more popular due to the advantages of improved security, scalability, and guaranteed SLA (Service-Level Agreement) at a lower cost than a separate private or public cloud. The existing studies rarely consider VM migrations in a hybrid cloud environment with dynamically changed VM workloads. From an enterprise's perspective, these migrations are necessary to minimize the cost of utilizing public clouds and guarantee SLAs of VMs in a hybrid cloud environment. In this paper, we propose an elastic VM allocation and migration algorithm for a hybrid cloud, called E-VM, to fully utilize the resources in a private cloud and to minimize the cost of using a public cloud while guaranteeing the SLAs of all VMs. The E-VM considers the bi-direction migration between private and public clouds. Two components, VM-predictor and VM-selector, are designed and implemented in E-VM to determine if a migration has to be triggered between private and public clouds and which VMs will be migrated to the opposite cloud, respectively. Moreover, E-VM is designed based on the existing public cloud pricing models and can be easily adapted to any cloud service provider. According to simulator results based on a set of captured industrial VM traces/workloads and additional experiments directly on a real-world hybrid cloud, the proposed E-VM can significantly reduce the total cost of using the public cloud compared to the existing VM migration schemes.

Original languageEnglish (US)
Title of host publication19th IEEE International Symposium on Parallel and Distributed Processing with Applications, 11th IEEE International Conference on Big Data and Cloud Computing, 14th IEEE International Conference on Social Computing and Networking and 11th IEEE International Conference on Sustainable Computing and Communications, ISPA/BDCloud/SocialCom/SustainCom 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages202-211
Number of pages10
ISBN (Electronic)9781665435741
DOIs
StatePublished - 2021
Event19th IEEE International Symposium on Parallel and Distributed Processing with Applications, 11th IEEE International Conference on Big Data and Cloud Computing, 14th IEEE International Conference on Social Computing and Networking and 11th IEEE International Conference on Sustainable Computing and Communications, ISPA/BDCloud/SocialCom/SustainCom 2021 - New York, United States
Duration: Sep 30 2021Oct 3 2021

Publication series

Name19th IEEE International Symposium on Parallel and Distributed Processing with Applications, 11th IEEE International Conference on Big Data and Cloud Computing, 14th IEEE International Conference on Social Computing and Networking and 11th IEEE International Conference on Sustainable Computing and Communications, ISPA/BDCloud/SocialCom/SustainCom 2021

Conference

Conference19th IEEE International Symposium on Parallel and Distributed Processing with Applications, 11th IEEE International Conference on Big Data and Cloud Computing, 14th IEEE International Conference on Social Computing and Networking and 11th IEEE International Conference on Sustainable Computing and Communications, ISPA/BDCloud/SocialCom/SustainCom 2021
Country/TerritoryUnited States
CityNew York
Period9/30/2110/3/21

Bibliographical note

Funding Information:
IX. ACKNOWLEDGEMENT This work was partially supported by NSF I/UCRC Center Research in Intelligent Storage and the following NSF awards 1439622, and 1812537.

Publisher Copyright:
© 2021 IEEE.

Keywords

  • Hybrid cloud
  • Scheduling
  • Total cost of ownership
  • Virtual machine

Fingerprint

Dive into the research topics of 'E-VM: An Elastic Virtual Machine Scheduling Algorithm to Minimize the Total Cost of Ownership in a Hybrid Cloud'. Together they form a unique fingerprint.

Cite this