| Presentation | 2021-01-20 [Invited Talk] A machine learning approach to data generation in networks Kohei Watabe, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | When we evaluate communication networks and protocols/applications running on them, it is important to demonstrate their performance through experiments and simulations with real data. By performing experiments/simulations based on various real data such as network topology, traffic, trajectories of mobile devices, and communication quality, it is possible to demonstrate the performance in the real environment. However, most of real data related to communication networks are used only within specific companies and organizations, and they are not open to the public. Then many researchers and developers cannot access these data. In addition, there is not always enough real data with desirable characteristics that suit a purpose of a simulation or an experiment. Traditionally, if real data are not available, we have no choice but to obtain experimental results with data generated based on a stochastic model. However, it does not always match the result with real data. In this paper, we introduce recent trends in related research and our recent works that enable realistic data generation. The generator developed by the authors enables tuning of any parameters while maintaining characteristics of real data, thereby enables flexible simulations and experiments. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | communication data generation / traffic / network topology / trajectory / machine learning |
| Paper # | CQ2020-71 |
| Date of Issue | 2021-01-13 (CQ) |
| Conference Information | |
| Committee | CQ |
|---|---|
| Conference Date | 2021/1/20(3days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | AR/VR, Broadcasting Service, Video/Voice Services Quality, High Realistic, User Behavior/Psychology, User Experience, Media Quality, Network Quality and QoS Control, Networks and Communications at Disaster, User Behavior, Machine Learning, Video Communication, etc. |
| Chair | Hideyuki Shimonishi(NEC) |
| Vice Chair | Jun Okamoto(NTT) / Takefumi Hiraguri(Nippon Inst. of Tech.) |
| Secretary | Jun Okamoto(Doshisha Univ.) / Takefumi Hiraguri(NICT) |
| Assistant | Yoshiaki Nishikawa(NEC) / Takuto Kimura(NTT) / Ryoichi Kataoka(KDDI Research) |
| Paper Information | |
| Registration To | Technical Committee on Communication Quality |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | [Invited Talk] A machine learning approach to data generation in networks |
| Sub Title (in English) | |
| Keyword(1) | communication data generation |
| Keyword(2) | traffic |
| Keyword(3) | network topology |
| Keyword(4) | trajectory |
| Keyword(5) | machine learning |
| 1st Author's Name | Kohei Watabe |
| 1st Author's Affiliation | Nagaoka University of Technology(Nagaoka Univ. of Tech.) |
| Date | 2021-01-20 |
| Paper # | CQ2020-71 |
| Volume (vol) | vol.120 |
| Number (no) | CQ-314 |
| Page | pp.pp.57-57(CQ), |
| #Pages | 1 |
| Date of Issue | 2021-01-13 (CQ) |