| Presentation | 2021-05-21 Performance Evaluation of Distributed Channel Selection Algorithm Based on Reinforcement Learning for Massive Mobile IoT Systems Daisuke Yamamoto, Honami Furukawa, Yusuke Ito, Aohan Li, Song-Ju Kim, Mikio Hasegawa, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In a Massive IoT environment, degradation of communication quality due to network congestion is a serious problem. In previous research, the channel selection problem for each IoT device is modeled as a Multi-Armed Bandit (MAB) problem, and channel selection based on reinforcement learning called Tug-of-War (TOW) dynamics, known as a high-performance MAB algorithm, has been shown to improve communication quality. In this paper, we perform a simulation evaluation under various ad-hoc network environments and compare the effectiveness of the proposed algorithm with other methods based on MAB algorithms in terms of frame success rate. Simulation evaluations show that the proposed algorithm can improve the communication quality between IoT devices in high density and dynamic network environment. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Machine Learning / Reinforcement Learning / Multi-Armed Bandit / IoT / Distributed Channel Selection |
| Paper # | SR2021-11 |
| Date of Issue | 2021-05-13 (SR) |
| Conference Information | |
| Committee | SR |
|---|---|
| Conference Date | 2021/5/20(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Software Radio, Machine Learning for Wireless Communication, etc. |
| Chair | Masayuki Ariyoshi(NEC) |
| Vice Chair | Suguru Kameda(Tohoku Univ.) / Osamu Takyu(Shinshu Univ.) / Kentaro Ishidu(NICT) |
| Secretary | Suguru Kameda(ATR) / Osamu Takyu(Univ. of Electro-Comm.) / Kentaro Ishidu(Mie Univ.) |
| Assistant | Mai Ohta(Fukuoka Univ.) / Teppei Oyama(Fujitsu Lab.) / Kentaro Kobayashi(Nagoya Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Smart Radio |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Performance Evaluation of Distributed Channel Selection Algorithm Based on Reinforcement Learning for Massive Mobile IoT Systems |
| 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 |
| 1st Author's Name | Daisuke Yamamoto |
| 1st Author's Affiliation | Tokyo University of Science(TUS) |
| 2nd Author's Name | Honami Furukawa |
| 2nd Author's Affiliation | Tokyo University of Science(TUS) |
| 3rd Author's Name | Yusuke Ito |
| 3rd Author's Affiliation | Tokyo University of Science(TUS) |
| 4th Author's Name | Aohan Li |
| 4th Author's Affiliation | Tokyo University of Science(TUS) |
| 5th Author's Name | Song-Ju Kim |
| 5th Author's Affiliation | Keio University(Keio Univ.) |
| 6th Author's Name | Mikio Hasegawa |
| 6th Author's Affiliation | Tokyo University of Science(TUS) |
| Date | 2021-05-21 |
| Paper # | SR2021-11 |
| Volume (vol) | vol.121 |
| Number (no) | SR-30 |
| Page | pp.pp.73-78(SR), |
| #Pages | 6 |
| Date of Issue | 2021-05-13 (SR) |