Presentation | 2019-11-21 Investigation of The Effect of Using Attribute Information in Network Traffic Prediction with Deep Learning Yusuke Tokuyama, Yukinobu Fukushima, Yuya Tarutani, Tokumi Yokohira, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | It is crucial for network operators to predict network traffic in the future as accurate as possible for appropriate resource provisioning and traffic engineering. In conventional studies, recurrent neural network (RNN) methods are considered to be the most promising prediction methods because of their high prediction accuracy. RNN methods use only time series of traffic volume as input, and do not use any attribute information (e.g., timestamp and day of the week) of the time series data. However, traffic volume changes depending on both time and day of the week. Therefore, it is possible that we can further improve the prediction accuracy of the RNN methods by using the attribute information as input, in addition to the time series of traffic volume. In this paper, we investigate the effect of using the attribute information on prediction accuracy in network traffic prediction using RNN methods. Experimental results show that both timestamp and day of the week information are effective for improving the prediction accuracy, especially day of the week information significantly improves the prediction accuracy. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Network Traffic Prediction / Deep Learning / Recurrent Neural Network |
Paper # | NS2019-122 |
Date of Issue | 2019-11-14 (NS) |
Conference Information | |
Committee | NS / ICM / CQ |
---|---|
Conference Date | 2019/11/21(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Rokkodai 2nd Campus, Kobe Univ. |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | Network quality, Network measurement/management, Network virtualization, Network service, Blockchain, Security, Network intelligence, etc. |
Chair | Yoshikatsu Okazaki(NTT) / Kiyohito Yoshihara(KDDI Research) / Hideyuki Shimonishi(NEC) |
Vice Chair | Akihiro Nakao(Univ. of Tokyo) / Takumi Miyoshi(Shibaura Inst. of Tech.) / Yoichi Sato(NEC) / Jun Okamoto(NTT) / Takefumi Hiraguri(Nippon Inst. of Tech.) |
Secretary | Akihiro Nakao(Osaka Pref Univ.) / Takumi Miyoshi(NTT) / Yoichi Sato(NTT) / Jun Okamoto(NTT) / Takefumi Hiraguri(Nippon Inst. of Tech.) |
Assistant | Shinya Kawano(NTT) / Hiroki Nakayama(Bosco) / Chikara Sasaki(KDDI Research) / Yoshiaki Nishikawa(NEC) / Takuto Kimura(NTT) |
Paper Information | |
Registration To | Technical Committee on Network Systems / Technical Committee on Information and Communication Management / Technical Committee on Communication Quality |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Investigation of The Effect of Using Attribute Information in Network Traffic Prediction with Deep Learning |
Sub Title (in English) | |
Keyword(1) | Network Traffic Prediction |
Keyword(2) | Deep Learning |
Keyword(3) | Recurrent Neural Network |
1st Author's Name | Yusuke Tokuyama |
1st Author's Affiliation | Okayama University(Okayama Univ.) |
2nd Author's Name | Yukinobu Fukushima |
2nd Author's Affiliation | Okayama University(Okayama Univ.) |
3rd Author's Name | Yuya Tarutani |
3rd Author's Affiliation | Okayama University(Okayama Univ.) |
4th Author's Name | Tokumi Yokohira |
4th Author's Affiliation | Okayama University(Okayama Univ.) |
Date | 2019-11-21 |
Paper # | NS2019-122 |
Volume (vol) | vol.119 |
Number (no) | NS-297 |
Page | pp.pp.13-18(NS), |
#Pages | 6 |
Date of Issue | 2019-11-14 (NS) |