Time series prediction with performance guarantee. / Dashevskiy, Mikhail; Luo, Zhiyuan.

In: IET Communications, Vol. 5, No. 8, 20.05.2011, p. 1044–1051 .

Research output: Contribution to journalArticlepeer-review

Published

Standard

Time series prediction with performance guarantee. / Dashevskiy, Mikhail; Luo, Zhiyuan.

In: IET Communications, Vol. 5, No. 8, 20.05.2011, p. 1044–1051 .

Research output: Contribution to journalArticlepeer-review

Harvard

Dashevskiy, M & Luo, Z 2011, 'Time series prediction with performance guarantee', IET Communications, vol. 5, no. 8, pp. 1044–1051 . https://doi.org/10.1049/iet-com.2010.0121

APA

Vancouver

Dashevskiy M, Luo Z. Time series prediction with performance guarantee. IET Communications. 2011 May 20;5(8):1044–1051 . https://doi.org/10.1049/iet-com.2010.0121

Author

Dashevskiy, Mikhail ; Luo, Zhiyuan. / Time series prediction with performance guarantee. In: IET Communications. 2011 ; Vol. 5, No. 8. pp. 1044–1051 .

BibTeX

@article{8123dcfebb8f4ee3a72bf3dfe865347f,
title = "Time series prediction with performance guarantee",
abstract = "Time series prediction has many important real applications such as network resource management and quality-of-service assurance. Many different techniques have been developed to deal with time series predictions, for example, the Box–Jenkins approach and machine learning. In this study, the authors focus on the problem of time series prediction with performance guarantees and describe two machine-learning techniques, namely prediction with expert advice and conformal predictors. The authors investigate the application of these techniques to network traffic demand and propose a novel way of combining these two techniques to provide performance guarantee on predictions. The method is generic and the authors demonstrate this approach by carrying out extensive experiments on both artificially generated data and publicly available network traffic demand datasets. Empirical results show that the proposed method can increase the performance of the prediction system.",
author = "Mikhail Dashevskiy and Zhiyuan Luo",
year = "2011",
month = may,
day = "20",
doi = "10.1049/iet-com.2010.0121",
language = "English",
volume = "5",
pages = "1044–1051 ",
journal = "IET Communications",
issn = "1751-8628",
publisher = "Institution of Engineering and Technology",
number = "8",

}

RIS

TY - JOUR

T1 - Time series prediction with performance guarantee

AU - Dashevskiy, Mikhail

AU - Luo, Zhiyuan

PY - 2011/5/20

Y1 - 2011/5/20

N2 - Time series prediction has many important real applications such as network resource management and quality-of-service assurance. Many different techniques have been developed to deal with time series predictions, for example, the Box–Jenkins approach and machine learning. In this study, the authors focus on the problem of time series prediction with performance guarantees and describe two machine-learning techniques, namely prediction with expert advice and conformal predictors. The authors investigate the application of these techniques to network traffic demand and propose a novel way of combining these two techniques to provide performance guarantee on predictions. The method is generic and the authors demonstrate this approach by carrying out extensive experiments on both artificially generated data and publicly available network traffic demand datasets. Empirical results show that the proposed method can increase the performance of the prediction system.

AB - Time series prediction has many important real applications such as network resource management and quality-of-service assurance. Many different techniques have been developed to deal with time series predictions, for example, the Box–Jenkins approach and machine learning. In this study, the authors focus on the problem of time series prediction with performance guarantees and describe two machine-learning techniques, namely prediction with expert advice and conformal predictors. The authors investigate the application of these techniques to network traffic demand and propose a novel way of combining these two techniques to provide performance guarantee on predictions. The method is generic and the authors demonstrate this approach by carrying out extensive experiments on both artificially generated data and publicly available network traffic demand datasets. Empirical results show that the proposed method can increase the performance of the prediction system.

U2 - 10.1049/iet-com.2010.0121

DO - 10.1049/iet-com.2010.0121

M3 - Article

VL - 5

SP - 1044

EP - 1051

JO - IET Communications

JF - IET Communications

SN - 1751-8628

IS - 8

ER -