Generative Neural Network Channel Modeling for Millimeter-Wave UAV Communication
| Autor: | William Xia, Sundeep Rangan, Marco Mezzavilla, Angel Lozano, Giovanni Geraci, Vasilii Semkin, Giuseppe Loianno |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2022 |
| Předmět: |
Signal Processing (eess.SP)
ray tracing Applied Mathematics UAV cellular network mmWave communication drone Computer Science Applications FOS: Electrical engineering electronic engineering information engineering 3GPP channel model variational autoencoder Electrical Engineering and Systems Science - Signal Processing Electrical and Electronic Engineering generative neural network air to ground 5G |
| Zdroj: | Xia, W, Rangan, S, Mezzavilla, M, Lozano, A, Geraci, G, Semkin, V & Loianno, G 2022, ' Generative Neural Network Channel Modeling for Millimeter-Wave UAV Communication ', IEEE Transactions on Wireless Communications, vol. 21, no. 11, pp. 9417-9431 . https://doi.org/10.1109/TWC.2022.3176480 |
| ISSN: | 1558-2248 1536-1276 |
| DOI: | 10.1109/TWC.2022.3176480 |
| Popis: | 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 28 GHz 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. Comment: 28 pages one column, submitted to Transactions in Wireless Communications Journal. arXiv admin note: text overlap with arXiv:2008.11006 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|