HOAH

A hybrid TCP throughput prediction with Autoregressive Model and Hidden Markov Model for mobile networks

Bo Wei, Kenji Kanai, Wataru Kawakami, Jiro Katto

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Throughput prediction is one of the promising techniques to improve the quality of service (QoS) and quality of experience (QoE) of mobile applications. To address the problem of predicting future throughput distribution accurately during the whole session, which can exhibit large throughput fluctuations in different scenarios (especially scenarios of moving user), we propose a history-based throughput prediction method that utilizes time series analysis and machine learning techniques for mobile network communication. This method is called the Hybrid Prediction with the Autoregressive Model and Hidden Markov Model (HOAH). Different from existing methods, HOAH uses Support Vector Machine (SVM) to classify the throughput transition into two classes, and predicts the transmission control protocol (TCP) throughput by switching between the Autoregressive Model (AR Model) and the Gaussian Mixture Model-Hidden Markov Model (GMM-HMM). We conduct field experiments to evaluate the proposed method in seven different scenarios. The results show that HOAH can predict future throughput effectively and decreases the prediction error by a maximum of 55.95% compared with other methods.

Original languageEnglish
Pages (from-to)1612-1624
Number of pages13
JournalIEICE Transactions on Communications
VolumeE101B
Issue number7
DOIs
Publication statusPublished - 2018 Jul 1

Fingerprint

Transmission control protocol
Hidden Markov models
Wireless networks
Throughput
Time series analysis
Support vector machines
Learning systems
Quality of service
Communication

Keywords

  • Autoregressive model
  • Hidden Markov model
  • Mobile networks
  • Support vector machine
  • Throughput prediction

ASJC Scopus subject areas

  • Software
  • Computer Networks and Communications
  • Electrical and Electronic Engineering

Cite this

HOAH : A hybrid TCP throughput prediction with Autoregressive Model and Hidden Markov Model for mobile networks. / Wei, Bo; Kanai, Kenji; Kawakami, Wataru; Katto, Jiro.

In: IEICE Transactions on Communications, Vol. E101B, No. 7, 01.07.2018, p. 1612-1624.

Research output: Contribution to journalArticle

@article{31d4958655a24a3484ec952dc38e0e7d,
title = "HOAH: A hybrid TCP throughput prediction with Autoregressive Model and Hidden Markov Model for mobile networks",
abstract = "Throughput prediction is one of the promising techniques to improve the quality of service (QoS) and quality of experience (QoE) of mobile applications. To address the problem of predicting future throughput distribution accurately during the whole session, which can exhibit large throughput fluctuations in different scenarios (especially scenarios of moving user), we propose a history-based throughput prediction method that utilizes time series analysis and machine learning techniques for mobile network communication. This method is called the Hybrid Prediction with the Autoregressive Model and Hidden Markov Model (HOAH). Different from existing methods, HOAH uses Support Vector Machine (SVM) to classify the throughput transition into two classes, and predicts the transmission control protocol (TCP) throughput by switching between the Autoregressive Model (AR Model) and the Gaussian Mixture Model-Hidden Markov Model (GMM-HMM). We conduct field experiments to evaluate the proposed method in seven different scenarios. The results show that HOAH can predict future throughput effectively and decreases the prediction error by a maximum of 55.95{\%} compared with other methods.",
keywords = "Autoregressive model, Hidden Markov model, Mobile networks, Support vector machine, Throughput prediction",
author = "Bo Wei and Kenji Kanai and Wataru Kawakami and Jiro Katto",
year = "2018",
month = "7",
day = "1",
doi = "10.1587/transcom.2017CQP0007",
language = "English",
volume = "E101B",
pages = "1612--1624",
journal = "IEICE Transactions on Communications",
issn = "0916-8516",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "7",

}

TY - JOUR

T1 - HOAH

T2 - A hybrid TCP throughput prediction with Autoregressive Model and Hidden Markov Model for mobile networks

AU - Wei, Bo

AU - Kanai, Kenji

AU - Kawakami, Wataru

AU - Katto, Jiro

PY - 2018/7/1

Y1 - 2018/7/1

N2 - Throughput prediction is one of the promising techniques to improve the quality of service (QoS) and quality of experience (QoE) of mobile applications. To address the problem of predicting future throughput distribution accurately during the whole session, which can exhibit large throughput fluctuations in different scenarios (especially scenarios of moving user), we propose a history-based throughput prediction method that utilizes time series analysis and machine learning techniques for mobile network communication. This method is called the Hybrid Prediction with the Autoregressive Model and Hidden Markov Model (HOAH). Different from existing methods, HOAH uses Support Vector Machine (SVM) to classify the throughput transition into two classes, and predicts the transmission control protocol (TCP) throughput by switching between the Autoregressive Model (AR Model) and the Gaussian Mixture Model-Hidden Markov Model (GMM-HMM). We conduct field experiments to evaluate the proposed method in seven different scenarios. The results show that HOAH can predict future throughput effectively and decreases the prediction error by a maximum of 55.95% compared with other methods.

AB - Throughput prediction is one of the promising techniques to improve the quality of service (QoS) and quality of experience (QoE) of mobile applications. To address the problem of predicting future throughput distribution accurately during the whole session, which can exhibit large throughput fluctuations in different scenarios (especially scenarios of moving user), we propose a history-based throughput prediction method that utilizes time series analysis and machine learning techniques for mobile network communication. This method is called the Hybrid Prediction with the Autoregressive Model and Hidden Markov Model (HOAH). Different from existing methods, HOAH uses Support Vector Machine (SVM) to classify the throughput transition into two classes, and predicts the transmission control protocol (TCP) throughput by switching between the Autoregressive Model (AR Model) and the Gaussian Mixture Model-Hidden Markov Model (GMM-HMM). We conduct field experiments to evaluate the proposed method in seven different scenarios. The results show that HOAH can predict future throughput effectively and decreases the prediction error by a maximum of 55.95% compared with other methods.

KW - Autoregressive model

KW - Hidden Markov model

KW - Mobile networks

KW - Support vector machine

KW - Throughput prediction

UR - http://www.scopus.com/inward/record.url?scp=85049408067&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85049408067&partnerID=8YFLogxK

U2 - 10.1587/transcom.2017CQP0007

DO - 10.1587/transcom.2017CQP0007

M3 - Article

VL - E101B

SP - 1612

EP - 1624

JO - IEICE Transactions on Communications

JF - IEICE Transactions on Communications

SN - 0916-8516

IS - 7

ER -