Presentation | 2019-01-16 A Study on Application of Contextual Bandit Problem to Wireless LAN Access Point Selection Taichi Sakakibara, Takayuki Nishio, Masahiro Morikura, Koji Yamamoto, Toshihisa Nabetani, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | This paper models access point (AP) selection problem wireless LAN as an bandit problem and evaluate a performance of an AP selection method based on contextual bandit algorithm. Multiple wireless LAN services are provided in public places, and user devices have to select an AP from them. Common strategy of AP selection is to select an AP which has the maximum received signal strength indicator (RSSI), but there are cases where throughput becomes low due to congestion and narrow bandwidths of core networks. Reinforcement learning based AP selection is a promising way to solve the problem. This paper employs contextual bandit algorithm, which is one of reinforcement learning algorithms and try to maximize cumulative throughput including exploration duration, for the AP selection. The proposed method efficiently learns the optimal AP that depends on the user's position by using RSSI as features that represent the location of the user. Simulations results confirm that the proposed method achieves larger throughput than the RSSI-based method where bandwidths of core networks are limited. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Bandit problem / Reinforcement learning / AP selection / Wireless LAN |
Paper # | MoNA2018-58 |
Date of Issue | 2019-01-09 (MoNA) |
Conference Information | |
Committee | MoNA |
---|---|
Conference Date | 2019/1/16(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | T. B. D. |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Ryoichi Shinkuma(Kyoto Univ.) |
Vice Chair | Shigeaki Tagashira(Kansai Univ.) / Gen Kitagata(Tohoku Univ.) |
Secretary | Shigeaki Tagashira(Kyushu Univ.) / Gen Kitagata(NEC) |
Assistant | Ken Usui(KDDI Research) / Kenji Kanai(Waseda Univ.) |
Paper Information | |
Registration To | Technical Committee on Mobile Network and Applications |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | A Study on Application of Contextual Bandit Problem to Wireless LAN Access Point Selection |
Sub Title (in English) | |
Keyword(1) | Bandit problem |
Keyword(2) | Reinforcement learning |
Keyword(3) | AP selection |
Keyword(4) | Wireless LAN |
1st Author's Name | Taichi Sakakibara |
1st Author's Affiliation | Kyoto University(Kyoto Univ.) |
2nd Author's Name | Takayuki Nishio |
2nd Author's Affiliation | Kyoto University(Kyoto Univ.) |
3rd Author's Name | Masahiro Morikura |
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 | Toshihisa Nabetani |
5th Author's Affiliation | TOSHIBA CORPORATION(TOSHIBA) |
Date | 2019-01-16 |
Paper # | MoNA2018-58 |
Volume (vol) | vol.118 |
Number (no) | MoNA-389 |
Page | pp.pp.7-11(MoNA), |
#Pages | 5 |
Date of Issue | 2019-01-09 (MoNA) |