Analytical Modeling of Network Throughput Prediction on the Internet

Chunghan LEE; Hirotake ABE; Toshio HIROTSU; Kyoji UMEMURA

doi:10.1587/transinf.E95.D.2870

Analytical Modeling of Network Throughput Prediction on the Internet

Chunghan LEE, Hirotake ABE, Toshio HIROTSU, Kyoji UMEMURA

Full Text Views

0

Cite this

Summary :

Predicting network throughput is important for network-aware applications. Network throughput depends on a number of factors, and many throughput prediction methods have been proposed. However, many of these methods are suffering from the fact that a distribution of traffic fluctuation is unclear and the scale and the bandwidth of networks are rapidly increasing. Furthermore, virtual machines are used as platforms in many network research and services fields, and they can affect network measurement. A prediction method that uses pairs of differently sized connections has been proposed. This method, which we call connection pair, features a small probe transfer using the TCP that can be used to predict the throughput of a large data transfer. We focus on measurements, analyses, and modeling for precise prediction results. We first clarified that the actual throughput for the connection pair is non-linearly and monotonically changed with noise. Second, we built a previously proposed predictor using the same training data sets as for our proposed method, and it was unsuitable for considering the above characteristics. We propose a throughput prediction method based on the connection pair that uses ν-support vector regression and the polynomial kernel to deal with prediction models represented as a non-linear and continuous monotonic function. The prediction results of our method compared to those of the previous predictor are more accurate. Moreover, under an unstable network state, the drop in accuracy is also smaller than that of the previous predictor.

Publication: IEICE TRANSACTIONS on Information Vol.E95-D No.12 pp.2870-2878

Publication Date: 2012/12/01

Publicized

Online ISSN: 1745-1361

DOI: 10.1587/transinf.E95.D.2870

Type of Manuscript: Special Section PAPER (Special Section on Parallel and Distributed Computing and Networking)

Category: Network and Communication

Cite this

Copy

Chunghan LEE, Hirotake ABE, Toshio HIROTSU, Kyoji UMEMURA, "Analytical Modeling of Network Throughput Prediction on the Internet" in IEICE TRANSACTIONS on Information, vol. E95-D, no. 12, pp. 2870-2878, December 2012, doi: 10.1587/transinf.E95.D.2870.
Abstract: Predicting network throughput is important for network-aware applications. Network throughput depends on a number of factors, and many throughput prediction methods have been proposed. However, many of these methods are suffering from the fact that a distribution of traffic fluctuation is unclear and the scale and the bandwidth of networks are rapidly increasing. Furthermore, virtual machines are used as platforms in many network research and services fields, and they can affect network measurement. A prediction method that uses pairs of differently sized connections has been proposed. This method, which we call connection pair, features a small probe transfer using the TCP that can be used to predict the throughput of a large data transfer. We focus on measurements, analyses, and modeling for precise prediction results. We first clarified that the actual throughput for the connection pair is non-linearly and monotonically changed with noise. Second, we built a previously proposed predictor using the same training data sets as for our proposed method, and it was unsuitable for considering the above characteristics. We propose a throughput prediction method based on the connection pair that uses ν-support vector regression and the polynomial kernel to deal with prediction models represented as a non-linear and continuous monotonic function. The prediction results of our method compared to those of the previous predictor are more accurate. Moreover, under an unstable network state, the drop in accuracy is also smaller than that of the previous predictor.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E95.D.2870/_p

Copy

@ARTICLE{e95-d_12_2870,
author={Chunghan LEE, Hirotake ABE, Toshio HIROTSU, Kyoji UMEMURA, },
journal={IEICE TRANSACTIONS on Information},
title={Analytical Modeling of Network Throughput Prediction on the Internet},
year={2012},
volume={E95-D},
number={12},
pages={2870-2878},
abstract={Predicting network throughput is important for network-aware applications. Network throughput depends on a number of factors, and many throughput prediction methods have been proposed. However, many of these methods are suffering from the fact that a distribution of traffic fluctuation is unclear and the scale and the bandwidth of networks are rapidly increasing. Furthermore, virtual machines are used as platforms in many network research and services fields, and they can affect network measurement. A prediction method that uses pairs of differently sized connections has been proposed. This method, which we call connection pair, features a small probe transfer using the TCP that can be used to predict the throughput of a large data transfer. We focus on measurements, analyses, and modeling for precise prediction results. We first clarified that the actual throughput for the connection pair is non-linearly and monotonically changed with noise. Second, we built a previously proposed predictor using the same training data sets as for our proposed method, and it was unsuitable for considering the above characteristics. We propose a throughput prediction method based on the connection pair that uses ν-support vector regression and the polynomial kernel to deal with prediction models represented as a non-linear and continuous monotonic function. The prediction results of our method compared to those of the previous predictor are more accurate. Moreover, under an unstable network state, the drop in accuracy is also smaller than that of the previous predictor.},
keywords={},
doi={10.1587/transinf.E95.D.2870},
ISSN={1745-1361},
month={December},}

Copy

TY - JOUR
TI - Analytical Modeling of Network Throughput Prediction on the Internet
T2 - IEICE TRANSACTIONS on Information
SP - 2870
EP - 2878
AU - Chunghan LEE
AU - Hirotake ABE
AU - Toshio HIROTSU
AU - Kyoji UMEMURA
PY - 2012
DO - 10.1587/transinf.E95.D.2870
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E95-D
IS - 12
JA - IEICE TRANSACTIONS on Information
Y1 - December 2012
AB - Predicting network throughput is important for network-aware applications. Network throughput depends on a number of factors, and many throughput prediction methods have been proposed. However, many of these methods are suffering from the fact that a distribution of traffic fluctuation is unclear and the scale and the bandwidth of networks are rapidly increasing. Furthermore, virtual machines are used as platforms in many network research and services fields, and they can affect network measurement. A prediction method that uses pairs of differently sized connections has been proposed. This method, which we call connection pair, features a small probe transfer using the TCP that can be used to predict the throughput of a large data transfer. We focus on measurements, analyses, and modeling for precise prediction results. We first clarified that the actual throughput for the connection pair is non-linearly and monotonically changed with noise. Second, we built a previously proposed predictor using the same training data sets as for our proposed method, and it was unsuitable for considering the above characteristics. We propose a throughput prediction method based on the connection pair that uses ν-support vector regression and the polynomial kernel to deal with prediction models represented as a non-linear and continuous monotonic function. The prediction results of our method compared to those of the previous predictor are more accurate. Moreover, under an unstable network state, the drop in accuracy is also smaller than that of the previous predictor.
ER -