Loughborough University
Browse

Proactive admission control and dynamic resource management in SDN-based virtualized networks

Download (805.48 kB)
conference contribution
posted on 2017-09-21, 15:42 authored by Sara Shakeri, Saeedeh Parsaeefard, Mahsa Derakhshani
Network virtualization is a promising approach in which common physical resources are shared between service providers. Due to the substrate network limitations such as maximum available memory of each node of the substrate network as well as different service priorities and requirements, resource management in this setup is essential. On the other hand, SDN is bringing a considerable flexibility in resource management by introducing a centralized controller which can monitor all the substrate network states. In this paper, we propose a proactive admission control and dynamic resource management in SDNbased virtualized network in which the number of accepted highpriority virtual network (VN) requests is maximized, subject to both substrate limitations and memory requirement of each VN request. In the proposed formulation, based on the prediction of the substrate network utilization, we reserve resources for upcoming high-priority VN requests. Via simulation, we show that the algorithm can increase the acceptance ratio of the highpriority VN requests up to % 100 where the substrate network is congested, i.e., arrival rates of both high-priority and low-priority VN requests are high.

History

School

  • Mechanical, Electrical and Manufacturing Engineering

Published in

Network of the Future (NoF)

Citation

SHAKERI, S., PARSAEEFARD, S. and DERAKHSHANI, M., 2018. Proactive admission control and dynamic resource management in SDN-based virtualized networks. IN: 8th international Conference on the Network of the Future (NOF), London, UK, 22-24 November 2017.

Publisher

© IEEE

Version

  • AM (Accepted Manuscript)

Acceptance date

2017-08-24

Publication date

2018

Notes

© 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

ISBN

9781538605547

Language

  • en

Location

London, UK

Usage metrics

    Loughborough Publications

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC