Details
| Originalsprache | Englisch |
|---|---|
| Titel des Sammelwerks | 31st International Teletraffic Congress, ITC 2019 |
| Untertitel | Proceedings |
| Herausgeber (Verlag) | Institute of Electrical and Electronics Engineers Inc. |
| Seiten | 95-103 |
| Seitenumfang | 9 |
| ISBN (elektronisch) | 978-0-9883045-7-4 |
| ISBN (Print) | 978-1-7281-2513-8 |
| Publikationsstatus | Veröffentlicht - Aug. 2019 |
| Veranstaltung | 31st International Teletraffic Congress, ITC 2019 - Budapest, Ungarn Dauer: 27 Aug. 2019 → 29 Aug. 2019 |
Abstract
An accurate and fast estimation of the available bandwidth in a network with varying cross-traffic is a challenging task. The accepted probing tools, based on the fluid-flow model of a bottleneck link with first-in, first-out multiplexing, estimate the available bandwidth by measuring packet dispersions. The estimation becomes more difficult if packet dispersions deviate from the assumptions of the fluid-flow model in the presence of non-fluid bursty cross-traffic, multiple bottleneck links, and inaccurate time-stamping. This motivates us to explore the use of machine learning tools for available bandwidth estimation. Hence, we consider reinforcement learning and implement the single-state multi-armed bandit technique, which follows the ϵ-greedy algorithm to find the available bandwidth. Our measurements and tests reveal that our proposed method identifies the available bandwidth with high precision. Furthermore, our method converges to the available bandwidth under a variety of notoriously difficult conditions, such as heavy traffic burstiness, different cross-traffic intensities, multiple bottleneck links, and in networks where the tight link and the bottleneck link are not same. Compared to the piece-wise linear network a model based direct probing technique that employs a Kalman filter, our method shows more accurate estimates and faster convergence in certain network scenarios and does not require measurement noise statistics.
ASJC Scopus Sachgebiete
- Informatik (insg.)
- Computernetzwerke und -kommunikation
- Informatik (insg.)
- Hardware und Architektur
- Entscheidungswissenschaften (insg.)
- Informationssysteme und -management
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
31st International Teletraffic Congress, ITC 2019: Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. S. 95-103 8879445.
Publikation: Beitrag in Buch/Bericht/Sammelwerk/Konferenzband › Aufsatz in Konferenzband › Forschung › Peer-Review
}
TY - GEN
T1 - Measurement-Based Online Available Bandwidth Estimation Employing Reinforcement Learning
AU - Khangura, Sukhpreet Kaur
AU - Akin, Sami
PY - 2019/8
Y1 - 2019/8
N2 - An accurate and fast estimation of the available bandwidth in a network with varying cross-traffic is a challenging task. The accepted probing tools, based on the fluid-flow model of a bottleneck link with first-in, first-out multiplexing, estimate the available bandwidth by measuring packet dispersions. The estimation becomes more difficult if packet dispersions deviate from the assumptions of the fluid-flow model in the presence of non-fluid bursty cross-traffic, multiple bottleneck links, and inaccurate time-stamping. This motivates us to explore the use of machine learning tools for available bandwidth estimation. Hence, we consider reinforcement learning and implement the single-state multi-armed bandit technique, which follows the ϵ-greedy algorithm to find the available bandwidth. Our measurements and tests reveal that our proposed method identifies the available bandwidth with high precision. Furthermore, our method converges to the available bandwidth under a variety of notoriously difficult conditions, such as heavy traffic burstiness, different cross-traffic intensities, multiple bottleneck links, and in networks where the tight link and the bottleneck link are not same. Compared to the piece-wise linear network a model based direct probing technique that employs a Kalman filter, our method shows more accurate estimates and faster convergence in certain network scenarios and does not require measurement noise statistics.
AB - An accurate and fast estimation of the available bandwidth in a network with varying cross-traffic is a challenging task. The accepted probing tools, based on the fluid-flow model of a bottleneck link with first-in, first-out multiplexing, estimate the available bandwidth by measuring packet dispersions. The estimation becomes more difficult if packet dispersions deviate from the assumptions of the fluid-flow model in the presence of non-fluid bursty cross-traffic, multiple bottleneck links, and inaccurate time-stamping. This motivates us to explore the use of machine learning tools for available bandwidth estimation. Hence, we consider reinforcement learning and implement the single-state multi-armed bandit technique, which follows the ϵ-greedy algorithm to find the available bandwidth. Our measurements and tests reveal that our proposed method identifies the available bandwidth with high precision. Furthermore, our method converges to the available bandwidth under a variety of notoriously difficult conditions, such as heavy traffic burstiness, different cross-traffic intensities, multiple bottleneck links, and in networks where the tight link and the bottleneck link are not same. Compared to the piece-wise linear network a model based direct probing technique that employs a Kalman filter, our method shows more accurate estimates and faster convergence in certain network scenarios and does not require measurement noise statistics.
KW - Available bandwidth estimation
KW - multi-hop networks
KW - network measurements
KW - reinforcement learning
UR - http://www.scopus.com/inward/record.url?scp=85074749289&partnerID=8YFLogxK
U2 - 10.1109/ITC31.2019.00022
DO - 10.1109/ITC31.2019.00022
M3 - Conference contribution
AN - SCOPUS:85074749289
SN - 978-1-7281-2513-8
SP - 95
EP - 103
BT - 31st International Teletraffic Congress, ITC 2019
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 31st International Teletraffic Congress, ITC 2019
Y2 - 27 August 2019 through 29 August 2019
ER -