Distributed placement and online optimization of virtual machines for network service chains

Xiaojing Chen, Wei Ni, Iain B. Collings, Xin Wang, Shugong Xu

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionpeer-review

5 Citations (Scopus)

Abstract

This paper proposes a new fully decentralized approach for online placement and optimization of virtual machines (VMs) for network functions virtualization (NFV). The approach is non-trivial as the virtual network functions (VNFs) constituting network services must be executed correctly in order at different VMs, coupling the optimal decisions of VMs on processing or forwarding. Leveraging Lyapunov optimization techniques, we decouple the optimal decisions by minimizing the instantaneous NFV cost in a distributed fashion, and achieve the asymptotically minimum time-average cost. We also reduce the queue length by allowing individual VMs to (un)install VNFs based on local knowledge, adapting to the network topology and the temporal and spatial variations of services. Simulations show that the proposed approach is able to reduce the time-average cost of NFV by 71% and reduce the queue length (or delay) by 74%, as compared to existing approaches.

Original languageEnglish
Title of host publication2018 IEEE International Conference on Communications (ICC)
Subtitle of host publicationproceedings
Place of PublicationPiscataway, NJ
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages1-6
Number of pages6
ISBN (Electronic)9781538631805
ISBN (Print)9781538631812
DOIs
Publication statusPublished - 2018
EventIEEE International Conference on Communications (2018) - Kansas City, United States
Duration: 20 May 201824 May 2018

Conference

ConferenceIEEE International Conference on Communications (2018)
Abbreviated titleICC 2018
Country/TerritoryUnited States
CityKansas City
Period20/05/1824/05/18

Fingerprint

Dive into the research topics of 'Distributed placement and online optimization of virtual machines for network service chains'. Together they form a unique fingerprint.

Cite this