| Presentation | 2019-01-28 Deep Reinforcement Learning-Based Optimum Channel Control for Wireless LAN Kota Nakashima, Syotaro Kamiya, Kazuki Ohtsu, Koji Yamamoto, Takayuki Nishio, Masahiro Morikura, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | This report proposes deep reinforcement learning-based channel selection method when access points (APs) are located densely. In densely deployed WLANs, APs could have many APs in their carrier sensing range and throughput of the APs becomes low due to high contention. We apply graph convolution networks (GCN) to a contention graph where APs in their carrier sense range are connected for extracting the features of carrier sensing relationship. Moreover, by selecting an action according to spatial adaptive play (SAP) method, we improve the learning efficiency. The simulation results show that the proposal method can control the channels appropriately in comparison to other methods. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | deep reinforcement learning / graph convolutional networks / spatial adaptive play |
| Paper # | ASN2018-80 |
| Date of Issue | 2019-01-21 (ASN) |
| Conference Information | |
| Committee | ASN |
|---|---|
| Conference Date | 2019/1/28(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Kyuukamura Ibusuki |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Ambient intelligence, Sensor networks, Poster session, etc. |
| Chair | Hiraku Okada(Nagoya Univ.) |
| Vice Chair | Koji Yamamoto(Kyoto Univ.) / Jin Nakazawa(Keio Univ.) / Kazuya Monden(Hitachi) |
| Secretary | Koji Yamamoto(NICT) / Jin Nakazawa(Sophia Univ.) / Kazuya Monden(Kanagawa Inst. of Tech.) |
| Assistant | Masafumi Hashimoto(Osaka Univ.) / Tomoyuki Ota(Hiroshima City Univ.) / Tatsuya Kikuzuki(Fujitu Lab.) / Ryo Nakano(HITACHI) / Yoshifumi Hotta(Mitsubishi Electric) |
| Paper Information | |
| Registration To | Technical Committee on Ambient intelligence and Sensor Networks |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Deep Reinforcement Learning-Based Optimum Channel Control for Wireless LAN |
| Sub Title (in English) | |
| Keyword(1) | deep reinforcement learning |
| Keyword(2) | graph convolutional networks |
| Keyword(3) | spatial adaptive play |
| 1st Author's Name | Kota Nakashima |
| 1st Author's Affiliation | Kyoto University(Kyoto Univ.) |
| 2nd Author's Name | Syotaro Kamiya |
| 2nd Author's Affiliation | Kyoto University(Kyoto Univ.) |
| 3rd Author's Name | Kazuki Ohtsu |
| 3rd Author's Affiliation | Kyoto University(Kyoto Univ.) |
| 4th Author's Name | Koji Yamamoto |
| 4th Author's Affiliation | Kyoto University(Kyoto Univ.) |
| 5th Author's Name | Takayuki Nishio |
| 5th Author's Affiliation | Kyoto University(Kyoto Univ.) |
| 6th Author's Name | Masahiro Morikura |
| 6th Author's Affiliation | Kyoto University(Kyoto Univ.) |
| Date | 2019-01-28 |
| Paper # | ASN2018-80 |
| Volume (vol) | vol.118 |
| Number (no) | ASN-428 |
| Page | pp.pp.13-18(ASN), |
| #Pages | 6 |
| Date of Issue | 2019-01-21 (ASN) |