期刊
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS
卷 21, 期 11, 页码 9417-9431出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TWC.2022.3176480
关键词
UAV; drone; mmWave communication; 5G; cellular network; air to ground; channel model; ray tracing; variational autoencoder; generative neural network; 3GPP
资金
- NSF [1302336, 1564142, 1547332, 1824434]
- National Institute of Standards and Technology (NIST)
- Semiconductor Research Corporation
- Industrial Affiliates of New York University (NYU) Wireless
- European Research Council (ERC) [694974]
- MINECO [RTI2018101040]
- ICREA
- Junior Leader Fellowship Program from la Caixa Banking Foundation
- Academy of Finland
- Div Of Electrical, Commun & Cyber Sys
- Directorate For Engineering [1824434] Funding Source: National Science Foundation
This paper proposes a general modeling methodology based on data-training a generative neural network for mmWave air-to-ground channels between UAVs and a cellular system. The proposed approach is able to capture complex statistical relations in the data and significantly outperforms standard 3GPP models.
The millimeter wave bands are being increasingly considered for wireless communication to unmanned aerial vehicles (UAVs). Critical to this undertaking are statistical channel models that describe the distribution of constituent parameters in scenarios of interest. This paper presents a general modeling methodology based on data-training a generative neural network. The proposed generative model has a two-stage structure that first predicts the link state (line-of-sight, non-line-of-sight, or outage), and subsequently feeds this state into a conditional variational autoencoder (VAE) that generates the path losses, delays, and angles of arrival and departure for all the propagation paths. The methodology is demonstrated for 28GHz air-to-ground channels between UAVs and a cellular system in representative urban environments, with training datasets produced through ray tracing. The demonstration extends to both standard base stations (installed at street level and downtilted) as well as dedicated base stations (mounted on rooftops and uptilted). The proposed approach is able to capture complex statistical relations in the data and it significantly outperforms standard 3GPP models, even after refitting the parameters of those models to the data.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据