講演抄録/キーワード |
講演名 |
2019-03-08 09:50
[依頼講演]強化学習による自律分散型のマルチ無線インターフェース帰属制御法 ○金子めぐみ・ディン ティ ハー リー(NII)・若尾佳佑・アベセカラ ヒランタ・鷹取泰司(NTT) RCS2018-322 |
抄録 |
(和) |
(まだ登録されていません) |
(英) |
This work investigates the issue of distributed user-to-multiple Acess Points (AP) association, where a user requiring several applications may be served by several APs simultaneously. The problem is formulated as a network sum-rate maximization subject to the required QoS constraints for each user and application, and AP load constraints. We propose a distributed user-to-multiple AP association method, where each user can take an optimized decision locally, leveraging reinforcement learning. Simulation results show that, compared to baseline schemes, the proposed method enables large throughput enhancements while satisfying the stringent and diverse user Quality of Service (QoS) requirements as well as AP load limitations, thereby reducing user outage probabilities. |
キーワード |
(和) |
/ / / / / / / |
(英) |
Wireless Networks / WLAN / Reinforcement Learning / Q-Learning / user-to-AP association / sum-rate maximization / QoS constraints / |
文献情報 |
信学技報, vol. 118, no. 474, RCS2018-322, pp. 205-205, 2019年3月. |
資料番号 |
RCS2018-322 |
発行日 |
2019-02-27 (RCS) |
ISSN |
Online edition: ISSN 2432-6380 |
著作権に ついて |
技術研究報告に掲載された論文の著作権は電子情報通信学会に帰属します.(許諾番号:10GA0019/12GB0052/13GB0056/17GB0034/18GB0034) |
PDFダウンロード |
RCS2018-322 |