Details
| Original language | English |
|---|---|
| Pages (from-to) | 18-30 |
| Number of pages | 13 |
| Journal | Computer communications |
| Volume | 144 |
| Early online date | 17 May 2019 |
| Publication status | Published - 15 Aug 2019 |
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 randomly generated networks with the multiple bottleneck links and heavy cross traffic burstiness. Compared to two state-of-the-art model-based techniques as well as a recent machine learning-based technique (Yin et al., 2016), our neural network approach shows improved performance. Further, our neural network can effectively control the estimation procedure in an iterative implementation. We also evaluate our method with other supervised machine learning techniques.
Keywords
- Available bandwidth estimation, Machine learning
ASJC Scopus subject areas
- Computer Science(all)
- Computer Networks and Communications
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Computer communications, Vol. 144, 15.08.2019, p. 18-30.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Machine learning for measurement-based bandwidth estimation
AU - Khangura, Sukhpreet Kaur
AU - Fidler, Markus
AU - Rosenhahn, Bodo
PY - 2019/8/15
Y1 - 2019/8/15
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 randomly generated networks with the multiple bottleneck links and heavy cross traffic burstiness. Compared to two state-of-the-art model-based techniques as well as a recent machine learning-based technique (Yin et al., 2016), our neural network approach shows improved performance. Further, our neural network can effectively control the estimation procedure in an iterative implementation. We also evaluate our method with other supervised machine learning techniques.
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 randomly generated networks with the multiple bottleneck links and heavy cross traffic burstiness. Compared to two state-of-the-art model-based techniques as well as a recent machine learning-based technique (Yin et al., 2016), our neural network approach shows improved performance. Further, our neural network can effectively control the estimation procedure in an iterative implementation. We also evaluate our method with other supervised machine learning techniques.
KW - Available bandwidth estimation
KW - Machine learning
UR - http://www.scopus.com/inward/record.url?scp=85065878754&partnerID=8YFLogxK
U2 - 10.1016/j.comcom.2019.05.005
DO - 10.1016/j.comcom.2019.05.005
M3 - Article
AN - SCOPUS:85065878754
VL - 144
SP - 18
EP - 30
JO - Computer communications
JF - Computer communications
SN - 0140-3664
ER -