Neural Networks for Measurement-based Bandwidth Estimation

Research output: Chapter in book/report/conference proceedingConference contributionResearchpeer review

Authors

View graph of relations

Details

Original languageEnglish
Title of host publication2018 IFIP Networking Conference IFIP Networking and Workshops
Subtitle of host publicationIFIP Networking 2018 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages460-468
Number of pages9
ISBN (electronic)9783903176089
Publication statusPublished - 2 Jul 2018
Event17th IFIP Networking Conference IFIP Networking and Workshops, IFIP Networking 2018 - Zurich, Switzerland
Duration: 14 May 201816 May 2018

Abstract

The dispersion that arises when packets traverse a network carries information that can reveal relevant network characteristics. Using a fluid-flow model of a bottleneck link with first-in first-out multiplexing, accepted probing tools measure the packet dispersion to estimate the available bandwidth, i.e., the residual capacity that is left over by other traffic. Difficulties arise, however, if the dispersion is distorted compared to the model, e.g., by non-fluid traffic, multiple bottlenecks, clustering of packets due to interrupt coalescing, and inaccurate time-stamping in general. It is recognized that modeling these effects is cumbersome if not intractable. This motivates us to explore the use of machine learning in bandwidth estimation. We train a neural network using vectors of the packet dispersion that is characteristic of the available bandwidth. Our testing results reveal that even a shallow neural network identifies the available bandwidth with high precision. We also apply the neural network under a variety of notoriously difficult conditions that have not been included in the training, such as heavy traffic burstiness, and multiple bottleneck links. Compared to two state-of-the-art model-based techniques, the neural network approach shows improved performance. Further, the neural network can effectively control the estimation procedure in an iterative implementation.

ASJC Scopus subject areas

Cite this

Neural Networks for Measurement-based Bandwidth Estimation. / Khangura, Sukhpreet Kaur; Fidler, Markus; Rosenhahn, Bodo.
2018 IFIP Networking Conference IFIP Networking and Workshops: IFIP Networking 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2018. p. 460-468 8697023.

Research output: Chapter in book/report/conference proceedingConference contributionResearchpeer review

Khangura, SK, Fidler, M & Rosenhahn, B 2018, Neural Networks for Measurement-based Bandwidth Estimation. in 2018 IFIP Networking Conference IFIP Networking and Workshops: IFIP Networking 2018 - Proceedings., 8697023, Institute of Electrical and Electronics Engineers Inc., pp. 460-468, 17th IFIP Networking Conference IFIP Networking and Workshops, IFIP Networking 2018, Zurich, Switzerland, 14 May 2018. https://doi.org/10.23919/ifipnetworking.2018.8697023
Khangura, S. K., Fidler, M., & Rosenhahn, B. (2018). Neural Networks for Measurement-based Bandwidth Estimation. In 2018 IFIP Networking Conference IFIP Networking and Workshops: IFIP Networking 2018 - Proceedings (pp. 460-468). Article 8697023 Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.23919/ifipnetworking.2018.8697023
Khangura SK, Fidler M, Rosenhahn B. Neural Networks for Measurement-based Bandwidth Estimation. In 2018 IFIP Networking Conference IFIP Networking and Workshops: IFIP Networking 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2018. p. 460-468. 8697023 doi: 10.23919/ifipnetworking.2018.8697023
Khangura, Sukhpreet Kaur ; Fidler, Markus ; Rosenhahn, Bodo. / Neural Networks for Measurement-based Bandwidth Estimation. 2018 IFIP Networking Conference IFIP Networking and Workshops: IFIP Networking 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 460-468
Download
@inproceedings{b7b5099ec731471dadc80f0a69f67706,
title = "Neural Networks for Measurement-based Bandwidth Estimation",
abstract = "The dispersion that arises when packets traverse a network carries information that can reveal relevant network characteristics. Using a fluid-flow model of a bottleneck link with first-in first-out multiplexing, accepted probing tools measure the packet dispersion to estimate the available bandwidth, i.e., the residual capacity that is left over by other traffic. Difficulties arise, however, if the dispersion is distorted compared to the model, e.g., by non-fluid traffic, multiple bottlenecks, clustering of packets due to interrupt coalescing, and inaccurate time-stamping in general. It is recognized that modeling these effects is cumbersome if not intractable. This motivates us to explore the use of machine learning in bandwidth estimation. We train a neural network using vectors of the packet dispersion that is characteristic of the available bandwidth. Our testing results reveal that even a shallow neural network identifies the available bandwidth with high precision. We also apply the neural network under a variety of notoriously difficult conditions that have not been included in the training, such as heavy traffic burstiness, and multiple bottleneck links. Compared to two state-of-the-art model-based techniques, the neural network approach shows improved performance. Further, the neural network can effectively control the estimation procedure in an iterative implementation.",
author = "Khangura, {Sukhpreet Kaur} and Markus Fidler and Bodo Rosenhahn",
year = "2018",
month = jul,
day = "2",
doi = "10.23919/ifipnetworking.2018.8697023",
language = "English",
pages = "460--468",
booktitle = "2018 IFIP Networking Conference IFIP Networking and Workshops",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",
note = "17th IFIP Networking Conference IFIP Networking and Workshops, IFIP Networking 2018 ; Conference date: 14-05-2018 Through 16-05-2018",

}

Download

TY - GEN

T1 - Neural Networks for Measurement-based Bandwidth Estimation

AU - Khangura, Sukhpreet Kaur

AU - Fidler, Markus

AU - Rosenhahn, Bodo

PY - 2018/7/2

Y1 - 2018/7/2

N2 - The dispersion that arises when packets traverse a network carries information that can reveal relevant network characteristics. Using a fluid-flow model of a bottleneck link with first-in first-out multiplexing, accepted probing tools measure the packet dispersion to estimate the available bandwidth, i.e., the residual capacity that is left over by other traffic. Difficulties arise, however, if the dispersion is distorted compared to the model, e.g., by non-fluid traffic, multiple bottlenecks, clustering of packets due to interrupt coalescing, and inaccurate time-stamping in general. It is recognized that modeling these effects is cumbersome if not intractable. This motivates us to explore the use of machine learning in bandwidth estimation. We train a neural network using vectors of the packet dispersion that is characteristic of the available bandwidth. Our testing results reveal that even a shallow neural network identifies the available bandwidth with high precision. We also apply the neural network under a variety of notoriously difficult conditions that have not been included in the training, such as heavy traffic burstiness, and multiple bottleneck links. Compared to two state-of-the-art model-based techniques, the neural network approach shows improved performance. Further, the neural network can effectively control the estimation procedure in an iterative implementation.

AB - The dispersion that arises when packets traverse a network carries information that can reveal relevant network characteristics. Using a fluid-flow model of a bottleneck link with first-in first-out multiplexing, accepted probing tools measure the packet dispersion to estimate the available bandwidth, i.e., the residual capacity that is left over by other traffic. Difficulties arise, however, if the dispersion is distorted compared to the model, e.g., by non-fluid traffic, multiple bottlenecks, clustering of packets due to interrupt coalescing, and inaccurate time-stamping in general. It is recognized that modeling these effects is cumbersome if not intractable. This motivates us to explore the use of machine learning in bandwidth estimation. We train a neural network using vectors of the packet dispersion that is characteristic of the available bandwidth. Our testing results reveal that even a shallow neural network identifies the available bandwidth with high precision. We also apply the neural network under a variety of notoriously difficult conditions that have not been included in the training, such as heavy traffic burstiness, and multiple bottleneck links. Compared to two state-of-the-art model-based techniques, the neural network approach shows improved performance. Further, the neural network can effectively control the estimation procedure in an iterative implementation.

UR - http://www.scopus.com/inward/record.url?scp=85065503619&partnerID=8YFLogxK

U2 - 10.23919/ifipnetworking.2018.8697023

DO - 10.23919/ifipnetworking.2018.8697023

M3 - Conference contribution

AN - SCOPUS:85065503619

SP - 460

EP - 468

BT - 2018 IFIP Networking Conference IFIP Networking and Workshops

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 17th IFIP Networking Conference IFIP Networking and Workshops, IFIP Networking 2018

Y2 - 14 May 2018 through 16 May 2018

ER -

By the same author(s)