An optimum network selection solution for multihomed hosts using Hopfield Networks

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

2 Citations (Scopus)

Abstract

This work introduces a Hopfield Neural Network approach to network selection for multihomed hosts which considers a range of relevant network parameters including available radio access technologies and traffic types (VoIP, video streaming, Web browsing and FTP-based). Also proposed is a novel utility function that further improves network selection. Results show that, in terms of QoS, the allocation obtained using proposed algorithm outperforms other two reference allocation schemes under a range of different scenarios.
LanguageEnglish
Title of host publicationNinth International Conference on Networks, 2010
PublisherIEEE
Pages249-254
Number of pages6
ISBN (Print)978-1-4244-6083-0
DOIs
Publication statusPublished - Apr 2010

Fingerprint

Video streaming
Telecommunication traffic
Quality of service

Keywords

  • network selection algorithms
  • Hopfield neural networks
  • Hopfield networks

Cite this

Espi, Jorge ; Atkinson, R.C. ; Harle, D.A. ; Andonovic, Ivan. / An optimum network selection solution for multihomed hosts using Hopfield Networks. Ninth International Conference on Networks, 2010. IEEE, 2010. pp. 249-254
@inproceedings{8d494bb1c39f42ae8fa943f31eab2bc2,
title = "An optimum network selection solution for multihomed hosts using Hopfield Networks",
abstract = "This work introduces a Hopfield Neural Network approach to network selection for multihomed hosts which considers a range of relevant network parameters including available radio access technologies and traffic types (VoIP, video streaming, Web browsing and FTP-based). Also proposed is a novel utility function that further improves network selection. Results show that, in terms of QoS, the allocation obtained using proposed algorithm outperforms other two reference allocation schemes under a range of different scenarios.",
keywords = "network selection algorithms, Hopfield neural networks, Hopfield networks",
author = "Jorge Espi and R.C. Atkinson and D.A. Harle and Ivan Andonovic",
note = "{\circledC} 2010 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.",
year = "2010",
month = "4",
doi = "10.1109/ICN.2010.47",
language = "English",
isbn = "978-1-4244-6083-0",
pages = "249--254",
booktitle = "Ninth International Conference on Networks, 2010",
publisher = "IEEE",

}

An optimum network selection solution for multihomed hosts using Hopfield Networks. / Espi, Jorge; Atkinson, R.C.; Harle, D.A.; Andonovic, Ivan.

Ninth International Conference on Networks, 2010. IEEE, 2010. p. 249-254.

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

TY - GEN

T1 - An optimum network selection solution for multihomed hosts using Hopfield Networks

AU - Espi, Jorge

AU - Atkinson, R.C.

AU - Harle, D.A.

AU - Andonovic, Ivan

N1 - © 2010 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.

PY - 2010/4

Y1 - 2010/4

N2 - This work introduces a Hopfield Neural Network approach to network selection for multihomed hosts which considers a range of relevant network parameters including available radio access technologies and traffic types (VoIP, video streaming, Web browsing and FTP-based). Also proposed is a novel utility function that further improves network selection. Results show that, in terms of QoS, the allocation obtained using proposed algorithm outperforms other two reference allocation schemes under a range of different scenarios.

AB - This work introduces a Hopfield Neural Network approach to network selection for multihomed hosts which considers a range of relevant network parameters including available radio access technologies and traffic types (VoIP, video streaming, Web browsing and FTP-based). Also proposed is a novel utility function that further improves network selection. Results show that, in terms of QoS, the allocation obtained using proposed algorithm outperforms other two reference allocation schemes under a range of different scenarios.

KW - network selection algorithms

KW - Hopfield neural networks

KW - Hopfield networks

UR - http://www.scopus.com/inward/record.url?scp=77954260932&partnerID=8YFLogxK

U2 - 10.1109/ICN.2010.47

DO - 10.1109/ICN.2010.47

M3 - Conference contribution book

SN - 978-1-4244-6083-0

SP - 249

EP - 254

BT - Ninth International Conference on Networks, 2010

PB - IEEE

ER -