| 講演抄録/キーワード |
| 講演名 |
2022-08-26 09:50
Joint UAV Positioning and User Pairing via Reinforcement Learning Based Selection in NOMA Systems ○Ahmad Gendia・Osamu Muta(Kyushu Univ.)・Sherief Hashima(RIKEN-AIP)・Kohei Hatano(Kyushu Univ.) RCS2022-114 |
| 抄録 |
(和) |
(まだ登録されていません) |
| (英) |
This paper proposes two reinforcement learning (RL)-based algorithms for millimeter wave (mmWave)-enabled unmanned aerial vehicle (UAV) communications toward beyond-5G (B5G). This can be especially useful in ad-hoc communication scenarios within a neighborhood with main-network connectivity problems such as in areas affected by natural disasters. Downlink non-orthogonal multiple access (NOMA) is an efficient protocol that can be utilized by the UAV to improve the overall sum-rate performance of the system. The dynamic selection of suitable hovering spots within the target zone where the UAV needs to be positioned as well as the proper node activation and NOMA power allocation are critical for optimized performance. Multiarmed bandit (MAB) and double deep Q-network (DDQN)-based solutions are proposed to address the joint problem of UAV positioning and node selection and power allocation for data transmission in downlink NOMA systems. To ensure that the proposed RL-based solutions can support high sum-rates, numerical simulations are presented. In addition, exhaustive and random search benchmarks are provided as baselines for the achievable upper and lower sum-rate levels, respectively. |
| キーワード |
(和) |
/ / / / / / / |
| (英) |
NOMA / UAV communications / Reinforcement learning / / / / / |
| 文献情報 |
信学技報, vol. 122, no. 164, RCS2022-114, pp. 96-101, 2022年8月. |
| 資料番号 |
RCS2022-114 |
| 発行日 |
2022-08-18 (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 |
RCS2022-114 |