A machine learning-based approach for estimating available bandwidth

Ling-Jyh Chen, Cheng Fu Chou, Bo Chun Wang

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

3 Citations (Scopus)

Abstract

In this paper, we propose a machine learning-based approach for estimating available bandwidth. We evaluate the approach via simulations using two probing models: a packet train probing model and a pathChirp-like probing model. The simulation results show that the former cannot yield accurate estimates in our system; however, using the pathChirp-like probing model, the proposed approach can estimate the available bandwidth with moderate traffic overhead more accurately than two widely used tools, pathChirp and Spruce. Moreover, we propose a normalization method that improves our approach's ability to estimate available bandwidth, even if there are no samples with similar properties to the measured path in the training dataset. The effectiveness and simplicity of this novel approach make it a promising scheme that goes a long way toward achieving accurate estimation of available bandwidth on Internet paths.

Original languageEnglish
Title of host publicationTENCON 2007 - 2007 IEEE Region 10 Conference
DOIs
Publication statusPublished - 2007 Dec 1
EventIEEE Region 10 Conference, TENCON 2007 - Taipei, Taiwan
Duration: 2007 Oct 302007 Nov 2

Publication series

NameIEEE Region 10 Annual International Conference, Proceedings/TENCON

Other

OtherIEEE Region 10 Conference, TENCON 2007
CountryTaiwan
CityTaipei
Period07/10/3007/11/2

Fingerprint

Learning systems
Bandwidth
Telecommunication traffic
Internet

ASJC Scopus subject areas

  • Computer Science Applications
  • Electrical and Electronic Engineering

Cite this

Chen, L-J., Chou, C. F., & Wang, B. C. (2007). A machine learning-based approach for estimating available bandwidth. In TENCON 2007 - 2007 IEEE Region 10 Conference [4428812] (IEEE Region 10 Annual International Conference, Proceedings/TENCON). https://doi.org/10.1109/TENCON.2007.4428812

A machine learning-based approach for estimating available bandwidth. / Chen, Ling-Jyh; Chou, Cheng Fu; Wang, Bo Chun.

TENCON 2007 - 2007 IEEE Region 10 Conference. 2007. 4428812 (IEEE Region 10 Annual International Conference, Proceedings/TENCON).

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

Chen, L-J, Chou, CF & Wang, BC 2007, A machine learning-based approach for estimating available bandwidth. in TENCON 2007 - 2007 IEEE Region 10 Conference., 4428812, IEEE Region 10 Annual International Conference, Proceedings/TENCON, IEEE Region 10 Conference, TENCON 2007, Taipei, Taiwan, 07/10/30. https://doi.org/10.1109/TENCON.2007.4428812
Chen L-J, Chou CF, Wang BC. A machine learning-based approach for estimating available bandwidth. In TENCON 2007 - 2007 IEEE Region 10 Conference. 2007. 4428812. (IEEE Region 10 Annual International Conference, Proceedings/TENCON). https://doi.org/10.1109/TENCON.2007.4428812
Chen, Ling-Jyh ; Chou, Cheng Fu ; Wang, Bo Chun. / A machine learning-based approach for estimating available bandwidth. TENCON 2007 - 2007 IEEE Region 10 Conference. 2007. (IEEE Region 10 Annual International Conference, Proceedings/TENCON).
@inproceedings{a0f5a05daa0041c5b4a0bacff73e3fb6,
title = "A machine learning-based approach for estimating available bandwidth",
abstract = "In this paper, we propose a machine learning-based approach for estimating available bandwidth. We evaluate the approach via simulations using two probing models: a packet train probing model and a pathChirp-like probing model. The simulation results show that the former cannot yield accurate estimates in our system; however, using the pathChirp-like probing model, the proposed approach can estimate the available bandwidth with moderate traffic overhead more accurately than two widely used tools, pathChirp and Spruce. Moreover, we propose a normalization method that improves our approach's ability to estimate available bandwidth, even if there are no samples with similar properties to the measured path in the training dataset. The effectiveness and simplicity of this novel approach make it a promising scheme that goes a long way toward achieving accurate estimation of available bandwidth on Internet paths.",
author = "Ling-Jyh Chen and Chou, {Cheng Fu} and Wang, {Bo Chun}",
year = "2007",
month = "12",
day = "1",
doi = "10.1109/TENCON.2007.4428812",
language = "English",
isbn = "1424412722",
series = "IEEE Region 10 Annual International Conference, Proceedings/TENCON",
booktitle = "TENCON 2007 - 2007 IEEE Region 10 Conference",

}

TY - GEN

T1 - A machine learning-based approach for estimating available bandwidth

AU - Chen, Ling-Jyh

AU - Chou, Cheng Fu

AU - Wang, Bo Chun

PY - 2007/12/1

Y1 - 2007/12/1

N2 - In this paper, we propose a machine learning-based approach for estimating available bandwidth. We evaluate the approach via simulations using two probing models: a packet train probing model and a pathChirp-like probing model. The simulation results show that the former cannot yield accurate estimates in our system; however, using the pathChirp-like probing model, the proposed approach can estimate the available bandwidth with moderate traffic overhead more accurately than two widely used tools, pathChirp and Spruce. Moreover, we propose a normalization method that improves our approach's ability to estimate available bandwidth, even if there are no samples with similar properties to the measured path in the training dataset. The effectiveness and simplicity of this novel approach make it a promising scheme that goes a long way toward achieving accurate estimation of available bandwidth on Internet paths.

AB - In this paper, we propose a machine learning-based approach for estimating available bandwidth. We evaluate the approach via simulations using two probing models: a packet train probing model and a pathChirp-like probing model. The simulation results show that the former cannot yield accurate estimates in our system; however, using the pathChirp-like probing model, the proposed approach can estimate the available bandwidth with moderate traffic overhead more accurately than two widely used tools, pathChirp and Spruce. Moreover, we propose a normalization method that improves our approach's ability to estimate available bandwidth, even if there are no samples with similar properties to the measured path in the training dataset. The effectiveness and simplicity of this novel approach make it a promising scheme that goes a long way toward achieving accurate estimation of available bandwidth on Internet paths.

UR - http://www.scopus.com/inward/record.url?scp=48649096734&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=48649096734&partnerID=8YFLogxK

U2 - 10.1109/TENCON.2007.4428812

DO - 10.1109/TENCON.2007.4428812

M3 - Conference contribution

SN - 1424412722

SN - 9781424412723

T3 - IEEE Region 10 Annual International Conference, Proceedings/TENCON

BT - TENCON 2007 - 2007 IEEE Region 10 Conference

ER -