| Presentation | 2022-01-21 [Short Paper] Study of ACK-Less Rate Adaptation for IEEE 802.11bc Using Deep Reinforcement Learning Takamochi Kanda, Yusuke Koda, Yuto Kihira, Koji Yamamoto, Takayuki Nishio, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | This paper introduces an ACK-less rate adaptation to locational variation of recipient stations (STAs) for broadcast wireless local area networks (WLANs). It is basically challenging in broadcast WLANs to adapt transmit rate to locational variation in recipient STAs owing to the lack of acknowledgement (ACK) mechanisms from STAs. Our key idea is that the broadcast access point (AP) control the rate based on received signal strength (RSS) of uplink frames transmitted by a partial recipient STAs to non-broadcast APs. Hence, by exploiting the RSS of the uplink frames, the broadcast AP can learn the statistics of the performance, thereby performing the ACK-less adaptation to the various STA deployments. For learning the statistics, we apply deep reinforcement learning. Simulations confirm that learning the expected value of the indicator enables the broadcast AP to alleviate the reception failures while keeping the transmit rate higher. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | IEEE 802.11bc / broadcast WLAN / deep reinforcement learning / rate control |
| Paper # | SeMI2021-74 |
| Date of Issue | 2022-01-13 (SeMI) |
| Conference Information | |
| Committee | SeMI |
|---|---|
| Conference Date | 2022/1/20(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Koji Yamamoto(Kyoto Univ.) |
| Vice Chair | Kazuya Monden(Hitachi) / Yasunori Owada(NICT) |
| Secretary | Kazuya Monden(Cyber Univ.) / Yasunori Owada(Waseda Univ.) |
| Assistant | Yuki Katsumata(NTT DOCOMO) / Akihito Taya(Aoyama Gakuin Univ.) / Yu Nakayama(Tokyo Univ. of Agri. and Tech.) |
| Paper Information | |
| Registration To | Technical Committee on Sensor Network and Mobile Intelligence |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | [Short Paper] Study of ACK-Less Rate Adaptation for IEEE 802.11bc Using Deep Reinforcement Learning |
| Sub Title (in English) | |
| Keyword(1) | IEEE 802.11bc |
| Keyword(2) | broadcast WLAN |
| Keyword(3) | deep reinforcement learning |
| Keyword(4) | rate control |
| 1st Author's Name | Takamochi Kanda |
| 1st Author's Affiliation | Kyoto University(Kyoto Univ.) |
| 2nd Author's Name | Yusuke Koda |
| 2nd Author's Affiliation | University of Oulu(Univ. of Oulu) |
| 3rd Author's Name | Yuto Kihira |
| 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/Tokyo Institute of Technology(Kyoto Univ./Tokyo Tech.) |
| Date | 2022-01-21 |
| Paper # | SeMI2021-74 |
| Volume (vol) | vol.121 |
| Number (no) | SeMI-333 |
| Page | pp.pp.86-88(SeMI), |
| #Pages | 3 |
| Date of Issue | 2022-01-13 (SeMI) |