CLC number: TN928
On-line Access: 2022-09-21
Received: 2022-02-01
Revision Accepted: 2022-09-21
Crosschecked: 2022-07-15
Cited: 0
Clicked: 1525
Citations: Bibtex RefMan EndNote GB/T7714
https://orcid.org/0000-0002-4995-5970
Minghui PANG, Qiuming ZHU, Zhipeng LIN, Fei BAI, Yue TIAN, Zhuo LI, Xiaomin CHEN. Machine learning based altitude-dependent empirical LoS probability model for air-to-ground communications[J]. Frontiers of Information Technology & Electronic Engineering,in press.https://doi.org/10.1631/FITEE.2200041 @article{title="Machine learning based altitude-dependent empirical LoS probability model for air-to-ground communications", %0 Journal Article TY - JOUR
基于机器学习的空地通信高度相关视距概率经验性模型1南京航空航天大学电子信息工程学院电磁频谱空间认知动态系统工信部重点实验室,中国南京市,211106 2西安电子科技大学综合业务网理论及关键技术国家重点实验室,中国西安市,710000 3南京航空航天大学电子信息工程学院雷达成像与微波光子技术教育部重点实验室,中国南京市,211106 摘要:视距(line-of-sight, LoS)概率预测对于无线通信系统的性能优化至关重要。然而,由于无人机等飞行器飞行高度从十几米到数千米不等,空地(air-to-ground, A2G)通信的LoS概率预测具有挑战性。本文针对A2G场景,提出一种高度相关的经验性LoS概率模型。在模型参数估计之前,设计了一种基于K近邻(K-nearest neighbors, KNN)的策略对LoS和非视距(none-line-of-sight, NLoS)路径进行分类。然后,开发了一种基于双层反向传播神经网络(back propagation neural network, BPNN)的参数估计方法来建立每个模型参数与无人机高度之间的关系。仿真表明该模型获得的结果与射线追踪(ray trancing, RT)数据、实测数据和标准模型结果具有良好一致性。该模型还可提供比其他LoS概率模型更广泛的适用高度,能够应用于各种A2G场景下的不同通信高度。 关键词组: Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article
Reference[1]3GPP, 2016a. 5G Channel Model for Bands up to 100 GHz. 3rd Generation Partnership Project (3GPP). [2]3GPP, 2016b. Technical Specification Group Radio Access Network; Channel Model for Frequency Spectrum above 6 GHz (Release 14). TR 38.900 V14.2.0. 3rd Generation Partnership Project (3GPP). [3]Al-Hourani A, 2020. On the probability of line-of-sight in urban environments. IEEE Wirel Commun Lett, 9(8):1178-1181. [4]Al-Hourani A, Kandeepan S, Jamalipour A, 2014. Modeling air-to-ground path loss for low altitude platforms in urban environments. Proc IEEE Global Communications Conf, p.2898-2904 [5]Alladi T, Naren, Bansal G, et al., 2020. SecAuthUAV: a novel authentication scheme for UAV-ground station and UAV-UAV communication. IEEE Trans Veh Technol, 69(12):15068-15077. [6]Cui ZZ, Guan K, Briso-Rodríguez C, et al., 2020. Frequency-dependent line-of-sight probability modeling in built-up environments. IEEE Int Things J, 7(1):699-709. [7]Fan W, Carton I, Nielsen J, et al., 2016. Measured wideband characteristics of indoor channels at centimetric and millimetric bands. EURASIP J Wirel Commun Netw, 2016:58. [8]Gapeyenko M, Moltchanov D, Andreev S, et al., 2021. Line-of-sight probability for mmwave-based UAV communications in 3D urban grid deployments. IEEE Trans Wirel Commun, 20(10):6566-6579. [9]Holis J, Pechac P, 2008. Elevation dependent shadowing model for mobile communications via high altitude platforms in built-up areas. IEEE Trans Antenn Propag, 56(4):1078-1084. [10]Huang C, Molisch AF, He RS, et al., 2020. Machine learning-enabled LOS/NLOS identification for MIMO systems in dynamic environments. IEEE Trans Wirel Commun, 19(6):3643-3657. [11]Huang J, Wang CX, Bai L, et al., 2020. A big data enabled channel model for 5G wireless communication systems. IEEE Trans Big Data, 6(2):211-222. [12]ITU-R, 2003. P.1410-2: Propagation Data and Prediction Methods Required for the Design of Terrestrial Broadband Millimetric Radio Access Systems Operating in a Frequency Range of About 20–50 GHz. [13]Järveläinen J, Nguyen SLH, Haneda K, et al., 2016. Evaluation of millimeter-wave line-of-sight probability with point cloud data. IEEE Wirel Commun Lett, 5(3):228-231. [14]Khawaja W, Ozdemir O, Guvenc I, 2018. Temporal and spatial characteristics of mm wave propagation channels for UAVs. Proc 11th Global Symp on Millimeter Waves, p.1-6. [15]Lee JH, Choi JS, Kim SC, 2018. Cell coverage analysis of 28 GHz millimeter wave in urban microcell environment using 3-D ray tracing. IEEE Trans Antenn Propag, 66(3):1479-1487. [16]Li W, Zhang JH, Ma XC, et al., 2019. The way to apply machine learning to IoT driven wireless network from channel perspective. China Commun, 16(1):148-164. [17]Lin ZP, Lv TJ, Mathiopoulos PT, 2018. 3-D indoor positioning for millimeter-wave massive MIMO systems. IEEE Trans Commun, 66(6):2472-2486. [18]Liu X, Xu J, Tang HY, 2018. Analysis of frequency-dependent line-of-sight probability in 3-D environment. IEEE Commun Lett, 22(8):1732-1735. [19]Mao K, Zhu QM, Song MZ, et al., 2020. A geometry-based beamforming channel model for UAV mmWave communications. Sensors, 20(23):6957. [20]Samimi MK, Rappaport TS, MacCartney GR, 2015. Probabilistic omnidirectional path loss models for millimeter-wave outdoor communications. IEEE Wirel Commun Lett, 4(4):357-360. [21]Sun S, Thomas TA, Rappaport TS, et al., 2015. Path loss, shadow fading, and line-of-sight probability models for 5G urban macro-cellular scenarios. Proc IEEE Globe-com Workshops, p.1-7. [22]Vitucci EM, Semkin V, Arpaio MJ, et al., 2021. Experimental characterization of air-to-ground propagation at mm-wave frequencies in dense urban environment. Proc 15th European Conf on Antennas and Propagation, p.1-5. [23]WINNER, 2008. WINNER II Channel Models. IST-4-027756, WINNER II D1.1.2 V1.2. [24]Xiao ZY, Dong H, Bai L, et al., 2020. Unmanned aerial vehicle base station (UAV-BS) deployment with millimeter-wave beamforming. IEEE Int Things J, 7(2):1336-1349. [25]Yang GS, Zhang Y, He ZW, et al., 2019. Machine-learning-based prediction methods for path loss and delay spread in air-to-ground millimetre-wave channels. IET Microw Antenn Propag, 13(8):1113-1211. [26]Yang M, Ai B, He RS, et al., 2021. Machine-learning-based fast angle-of-arrival recognition for vehicular communications. IEEE Trans Veh Technol, 70(2):1592-1605. [27]Yang WF, Zhang JL, Zhang J, 2019. Machine learning based in-door line-of-sight probability prediction. Int Symp on Antennas and Propagation, p.1-3. [28]You XH, Wang CX, Huang J, et al., 2021. Towards 6G wireless communication networks: vision, enabling technologies, and new paradigm shifts. Sci China Inform Sci, 64(1):110301. [29]Zhang XF, Xu LY, Xu L, et al., 2010. Direction of departure (DOD) and direction of arrival (DOA) estimation in MIMO radar with reduced-dimension MUSIC. IEEE Commun Lett, 14(12):1161-1163. [30]Zhang Y, Wen JX, Yang GS, et al., 2018. Air-to-air path loss prediction based on machine learning methods in urban environments. Wirel Commun Mob Comput, Article 8489326. [31]Zheng QB, He RS, Ai B, et al., 2020. Channel non-line-of-sight identification based on convolutional neural networks. IEEE Wirel Commun Lett, 9(9):1500-1504. [32]Zhu QM, Wang YW, Jiang KL, et al., 2019. 3D non-stationary geometry-based multi-input multi-output channel model for UAV-ground communication systems. IET Microw Antenn Propag, 13(8):1104-1112. [33]Zhu QM, Wang CX, Hua BY, et al., 2021a. 3GPP TR 38.901 Channel Model. In: Wiley 5G REF: the Essential 5G Reference Online. Wiley Press. [34]Zhu QM, Yao MT, Bai F, et al., 2021b. A general altitude-dependent path loss model for UAV-to-ground millimeter-wave communications. Front Inform Technol Electron Eng, 22(6):767-776. [35]Zhu QM, Mao K, Song MZ, et al., 2022. Map-based channel modeling and generation for U2V mmWave communication. IEEE Trans Veh Technol, 71(8):8004-8015. Journal of Zhejiang University-SCIENCE, 38 Zheda Road, Hangzhou
310027, China
Tel: +86-571-87952783; E-mail: cjzhang@zju.edu.cn Copyright © 2000 - 2024 Journal of Zhejiang University-SCIENCE |
Open peer comments: Debate/Discuss/Question/Opinion
<1>