IEICE TRANSACTIONS on Communications
Forecasting Service Performance on the Basis of Temporal Information by the Conditional Restricted Boltzmann Machine
Summary :
Predicting the service performance of Internet applications is important in service selection, especially for video services. In order to design a predictor for forecasting video service performance in third-party application, two famous service providers in China, Iqiyi and Letv, are monitored and analyzed. The study highlights that the measured performance in the observation period is time-series data, and it has strong autocorrelation, which means it is predictable. In order to combine the temporal information and map the measured data to a proper feature space, the authors propose a predictor based on a Conditional Restricted Boltzmann Machine (CRBM), which can capture the potential temporal relationship of the historical information. Meanwhile, the measured data of different sources are combined to enhance the training process, which can enlarge the training size and avoid the over-fit problem. Experiments show that combining the measured results from different resolutions for a video can raise prediction performance, and the CRBM algorithm shows better prediction ability and more stable performance than the baseline algorithms.
- Publication
- IEICE TRANSACTIONS on Communications Vol.E101-B No.5 pp.1210-1221
- Publication Date
- 2018/05/01
- Publicized
- 2017/11/10
- Online ISSN
- 1745-1345
- DOI
- 10.1587/transcom.2017EBP3219
- Type of Manuscript
- PAPER
- Category
- Network
Authors
Jiali YOU
Institute of Acoustics, Chinese Academy of Sciences
Hanxing XUE
Institute of Acoustics, Chinese Academy of Sciences,the University of Chinese Academy of Sciences
Yu ZHUO
Institute of Acoustics, Chinese Academy of Sciences,the University of Chinese Academy of Sciences
Xin ZHANG
Institute of Acoustics, Chinese Academy of Sciences,the University of Chinese Academy of Sciences
Jinlin WANG
Institute of Acoustics, Chinese Academy of Sciences
Keyword
Latest Issue
Copyrights notice of machine-translated contents
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.
Cite this
Copy
Jiali YOU, Hanxing XUE, Yu ZHUO, Xin ZHANG, Jinlin WANG, "Forecasting Service Performance on the Basis of Temporal Information by the Conditional Restricted Boltzmann Machine" in IEICE TRANSACTIONS on Communications,
vol. E101-B, no. 5, pp. 1210-1221, May 2018, doi: 10.1587/transcom.2017EBP3219.
Abstract: Predicting the service performance of Internet applications is important in service selection, especially for video services. In order to design a predictor for forecasting video service performance in third-party application, two famous service providers in China, Iqiyi and Letv, are monitored and analyzed. The study highlights that the measured performance in the observation period is time-series data, and it has strong autocorrelation, which means it is predictable. In order to combine the temporal information and map the measured data to a proper feature space, the authors propose a predictor based on a Conditional Restricted Boltzmann Machine (CRBM), which can capture the potential temporal relationship of the historical information. Meanwhile, the measured data of different sources are combined to enhance the training process, which can enlarge the training size and avoid the over-fit problem. Experiments show that combining the measured results from different resolutions for a video can raise prediction performance, and the CRBM algorithm shows better prediction ability and more stable performance than the baseline algorithms.
URL: https://global.ieice.org/en_transactions/communications/10.1587/transcom.2017EBP3219/_p
Copy
@ARTICLE{e101-b_5_1210,
author={Jiali YOU, Hanxing XUE, Yu ZHUO, Xin ZHANG, Jinlin WANG, },
journal={IEICE TRANSACTIONS on Communications},
title={Forecasting Service Performance on the Basis of Temporal Information by the Conditional Restricted Boltzmann Machine},
year={2018},
volume={E101-B},
number={5},
pages={1210-1221},
abstract={Predicting the service performance of Internet applications is important in service selection, especially for video services. In order to design a predictor for forecasting video service performance in third-party application, two famous service providers in China, Iqiyi and Letv, are monitored and analyzed. The study highlights that the measured performance in the observation period is time-series data, and it has strong autocorrelation, which means it is predictable. In order to combine the temporal information and map the measured data to a proper feature space, the authors propose a predictor based on a Conditional Restricted Boltzmann Machine (CRBM), which can capture the potential temporal relationship of the historical information. Meanwhile, the measured data of different sources are combined to enhance the training process, which can enlarge the training size and avoid the over-fit problem. Experiments show that combining the measured results from different resolutions for a video can raise prediction performance, and the CRBM algorithm shows better prediction ability and more stable performance than the baseline algorithms.},
keywords={},
doi={10.1587/transcom.2017EBP3219},
ISSN={1745-1345},
month={May},}
Copy
TY - JOUR
TI - Forecasting Service Performance on the Basis of Temporal Information by the Conditional Restricted Boltzmann Machine
T2 - IEICE TRANSACTIONS on Communications
SP - 1210
EP - 1221
AU - Jiali YOU
AU - Hanxing XUE
AU - Yu ZHUO
AU - Xin ZHANG
AU - Jinlin WANG
PY - 2018
DO - 10.1587/transcom.2017EBP3219
JO - IEICE TRANSACTIONS on Communications
SN - 1745-1345
VL - E101-B
IS - 5
JA - IEICE TRANSACTIONS on Communications
Y1 - May 2018
AB - Predicting the service performance of Internet applications is important in service selection, especially for video services. In order to design a predictor for forecasting video service performance in third-party application, two famous service providers in China, Iqiyi and Letv, are monitored and analyzed. The study highlights that the measured performance in the observation period is time-series data, and it has strong autocorrelation, which means it is predictable. In order to combine the temporal information and map the measured data to a proper feature space, the authors propose a predictor based on a Conditional Restricted Boltzmann Machine (CRBM), which can capture the potential temporal relationship of the historical information. Meanwhile, the measured data of different sources are combined to enhance the training process, which can enlarge the training size and avoid the over-fit problem. Experiments show that combining the measured results from different resolutions for a video can raise prediction performance, and the CRBM algorithm shows better prediction ability and more stable performance than the baseline algorithms.
ER -
English
