| Presentation | 2020-08-04 [Invited Talk] Reinforcement Learning Based Channel Selection Algorithm for IoT Devices and Its Application to Wireless Sensor Network for Building Monitoring System So Hasegawa, Ryoma Kitagawa, Takumi Ito, Takashi Nakajima, Song-Ju Kim, Yoshito Watanabe, Yozo Shoji, Mikio Hasegawa, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | The IoT wave have spread and the number of IoT devices have rapidly increased. In IoT system using numerous IoT devices which generate enormous traffic, it is considered effective to introduce a multi-channel selection function to avoid communication congestion. We have proposed a channel selection algorithm based reinforcement learning for IoT devices with limited computational resource. Furthermore, We have confirmed IoT devices implemented proposed method learn the surrounding communication environment and select optimal channel by experiments. In this paper, we describe the requirements for dynamic channel selection technology in IoT networks constructed with fixed or mobile devices, and explain the demonstration experiment of building monitoring using the devices implemented our proposed scheme. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Machine Learning / Reinforcement Learning / Multi-Armed Bandit / IoT / Distributed Channel Selection / Building Monitoring System |
| Paper # | CCS2020-13 |
| Date of Issue | 2020-07-27 (CCS) |
| Conference Information | |
| Committee | IN / CCS |
|---|---|
| Conference Date | 2020/8/3(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Network Science, Future Network, Cloud/SDN/Virtualization, Contents Delivery/Contents Exchange, and others |
| Chair | Kenji Ishida(Hiroshima City Univ.) / Shigeki Shiokawa(Kanagawa Inst. of Tech.) |
| Vice Chair | Kunio Hato(INTERNET MULTIFEED CO.) / Tetsuya Asai(Hokkaido Univ.) / Megumi Akai(Hokkaido Univ.) |
| Secretary | Kunio Hato(Hiroshima City Univ.) / Tetsuya Asai(KDDI Research) / Megumi Akai(NTT) |
| Assistant | / Hidehiro Nakano(Tokyo City Univ.) / Hiroyasu Ando(Tsukuba Univ.) / Takashi Matsubara(Kobe Univ.) / Kosuke Sanada(Mie Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Information Networks / Technical Committee on Complex Communication Sciences |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | [Invited Talk] Reinforcement Learning Based Channel Selection Algorithm for IoT Devices and Its Application to Wireless Sensor Network for Building Monitoring System |
| Sub Title (in English) | |
| Keyword(1) | Machine Learning |
| Keyword(2) | Reinforcement Learning |
| Keyword(3) | Multi-Armed Bandit |
| Keyword(4) | IoT |
| Keyword(5) | Distributed Channel Selection |
| Keyword(6) | Building Monitoring System |
| 1st Author's Name | So Hasegawa |
| 1st Author's Affiliation | National Institute of Information and Communications Technology(NICT) |
| 2nd Author's Name | Ryoma Kitagawa |
| 2nd Author's Affiliation | Tokyo Univesity of Science(TUS) |
| 3rd Author's Name | Takumi Ito |
| 3rd Author's Affiliation | Tokyo Univesity of Science(TUS) |
| 4th Author's Name | Takashi Nakajima |
| 4th Author's Affiliation | Tokyo Univesity of Science(TUS) |
| 5th Author's Name | Song-Ju Kim |
| 5th Author's Affiliation | Keio University(KU) |
| 6th Author's Name | Yoshito Watanabe |
| 6th Author's Affiliation | National Institute of Information and Communications Technology(NICT) |
| 7th Author's Name | Yozo Shoji |
| 7th Author's Affiliation | National Institute of Information and Communications Technology(NICT) |
| 8th Author's Name | Mikio Hasegawa |
| 8th Author's Affiliation | Tokyo Univesity of Science(TUS) |
| Date | 2020-08-04 |
| Paper # | CCS2020-13 |
| Volume (vol) | vol.120 |
| Number (no) | CCS-124 |
| Page | pp.pp.5-10(CCS), |
| #Pages | 6 |
| Date of Issue | 2020-07-27 (CCS) |