The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
La prédiction du débit est l'une des techniques prometteuses pour améliorer la qualité de service (QoS) et la qualité d'expérience (QoE) des applications mobiles. Pour résoudre le problème de la prévision précise de la distribution future du débit pendant toute la session, qui peut présenter d'importantes fluctuations de débit dans différents scénarios (en particulier les scénarios d'utilisateur en mouvement), nous proposons une méthode de prédiction du débit basée sur l'historique qui utilise l'analyse de séries chronologiques et des techniques d'apprentissage automatique. pour la communication sur réseau mobile. Cette méthode est appelée prédiction hybride avec le modèle autorégressif et le modèle de Markov caché (HOAH). Différent des méthodes existantes, HOAH utilise Support Vector Machine (SVM) pour classer la transition de débit en deux classes et prédit le débit du protocole de contrôle de transmission (TCP) en basculant entre le modèle autorégressif (modèle AR) et le modèle de mélange gaussien-Markov caché. Modèle (GMM-HMM). Nous menons des expériences sur le terrain pour évaluer la méthode proposée dans sept scénarios différents. Les résultats montrent que HOAH peut prédire efficacement le débit futur et réduit l’erreur de prédiction d’un maximum de 55.95 % par rapport à d’autres méthodes.
Bo WEI
Waseda University
Kenji KANAI
Waseda University
Wataru KAWAKAMI
Waseda University
Jiro KATTO
Waseda University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copier
Bo WEI, Kenji KANAI, Wataru KAWAKAMI, Jiro KATTO, "HOAH: A Hybrid TCP Throughput Prediction with Autoregressive Model and Hidden Markov Model for Mobile Networks" in IEICE TRANSACTIONS on Communications,
vol. E101-B, no. 7, pp. 1612-1624, July 2018, doi: 10.1587/transcom.2017CQP0007.
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.
URL: https://global.ieice.org/en_transactions/communications/10.1587/transcom.2017CQP0007/_p
Copier
@ARTICLE{e101-b_7_1612,
author={Bo WEI, Kenji KANAI, Wataru KAWAKAMI, Jiro KATTO, },
journal={IEICE TRANSACTIONS on Communications},
title={HOAH: A Hybrid TCP Throughput Prediction with Autoregressive Model and Hidden Markov Model for Mobile Networks},
year={2018},
volume={E101-B},
number={7},
pages={1612-1624},
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={},
doi={10.1587/transcom.2017CQP0007},
ISSN={1745-1345},
month={July},}
Copier
TY - JOUR
TI - HOAH: A Hybrid TCP Throughput Prediction with Autoregressive Model and Hidden Markov Model for Mobile Networks
T2 - IEICE TRANSACTIONS on Communications
SP - 1612
EP - 1624
AU - Bo WEI
AU - Kenji KANAI
AU - Wataru KAWAKAMI
AU - Jiro KATTO
PY - 2018
DO - 10.1587/transcom.2017CQP0007
JO - IEICE TRANSACTIONS on Communications
SN - 1745-1345
VL - E101-B
IS - 7
JA - IEICE TRANSACTIONS on Communications
Y1 - July 2018
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.
ER -