| Presentation | 2021-03-05 Prediction of Network Traffic through Gaussian Process Yitu Wang, Takayuki Nakachi, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | With accurate network traffic prediction, future communication networks can realize self-management and enjoy intelligent and efficient automation. Gaussian process, which encodes domain/expert knowledge into the kernel function, allows better learning and understanding of the traffic process from a Bayesian perspective. However, the evolving nature of network traffic challenges existing models to adaptively learn and predict its behavior. To this end, we establish a dynamic learning framework for multi-slot-ahead network traffic prediction based on Gaussian process. Specifically, 1). To track the dynamic traffic characteristics, we use a mixture of Gaussian in the spectrum domain to approximate the optimal kernel adapting to the designated training dataset, and dynamically discover the patterns at different times and time-scales. 2). To predict in a large time horizon without significantly hurt the performance, we adopt linear model of coregionalization to fully exploit the output correlations, and establish an integrated multi-slot-ahead prediction framework. Finally, our proposed algorithm is evaluated by simulation to show its superiority over the conventional schemes such as stochastic based ARIMA, deep learning based LSTM etc. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Traffic / Multislot prediction / Gaussian process / Linear model of coreginalization |
| Paper # | SIS2020-54 |
| Date of Issue | 2021-02-25 (SIS) |
| Conference Information | |
| Committee | SIS |
|---|---|
| Conference Date | 2021/3/4(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Soft Computing, etc. |
| Chair | Noriaki Suetake(Yamaguchi Univ.) |
| Vice Chair | Tomoaki Kimura(Kanagawa Inst. of Tech.) / Naoto Sasaoka(Tottori Univ.) |
| Secretary | Tomoaki Kimura(Kindai Univ.) / Naoto Sasaoka(National Inst. of Tech., Ube College) |
| Assistant | Yukihiro Bandoh(NTT) / Soh Yoshida(Kansai Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Smart Info-Media Systems |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Prediction of Network Traffic through Gaussian Process |
| Sub Title (in English) | |
| Keyword(1) | Traffic |
| Keyword(2) | Multislot prediction |
| Keyword(3) | Gaussian process |
| Keyword(4) | Linear model of coreginalization |
| 1st Author's Name | Yitu Wang |
| 1st Author's Affiliation | NTT(NTT) |
| 2nd Author's Name | Takayuki Nakachi |
| 2nd Author's Affiliation | NTT(NTT) |
| Date | 2021-03-05 |
| Paper # | SIS2020-54 |
| Volume (vol) | vol.120 |
| Number (no) | SIS-415 |
| Page | pp.pp.103-108(SIS), |
| #Pages | 6 |
| Date of Issue | 2021-02-25 (SIS) |