APPLYING MACHINE LEARNING ALGORITHMS FOR PATH LOSS PREDICTION OF MILLIMETER WAVES
68 viewsKeywords:
K-Nearest Neighbor; Linear Regression; Gradient Descent; 5G; Millimeter waves; Path loss models.Abstract
In this paper, we develop and apply Linear Regression and K-Nearest Neighbor algorithm to predict the path loss models of millimeter waves. The experimental data is obtained by using Wireless Insite software, the experiments in both line-of-sight and non-line-of-sight scenarios use a transmitter and receivers placed randomly at locations. The proposed method is applied to impove and adjust path loss models at 28 GHz and 38 GHz in Times City urban area and Nguyen Hue high school, Hanoi, Vietnam. The combination of these two algorithms to predict the path loss models of millimeter waves achieved the suitable results when compared with 3GPP and NYU Wireless path loss models, therefore improving the optimal results of path loss models.
References
[1]. T. S. Rappaport, R. W. Heath, Jr., R. C. Daniels, and J. N. Murdock, “Millimeter Wave Wireless Communications,” Pearson/Prentice Hall, 2015.
[2]. Z. Pi and F. Khan, “An introduction to millimeter-wave mobile broadband systems,” IEEE Commun. Mag., vol. 49, no. 6, Jun. 2011, pp. 101–107.
[3]. G. R. MacCartney Jr., M. K. Samimi, and T. S. Rappaport, “Omnidirectional path loss models at 28 GHz and 73 GHz in New York City,” Proc. IEEE Int. Symp. PIMRC, Sep. 2014.
[4]. Östlin, E.; Zepernick, H.J.; Suzuki, H., “Macrocell path-loss prediction using artificial neural networks,” IEEE Trans. Veh. Technol. 2010, 59, 2735–2747.
[5]. Isabona, J.; Srivastava, V.M., “Hybrid neural network approach for predicting signal propagation loss in urban microcells,” Proceedings of the 2016 IEEE Region 10 Humanitarian Technology Conference (R10-HTC), Agra, India, 21–23 December 2016, pp. 1-5.
[6]. Cheikh A. L. DIAKHATE, “Propagation Channel Modeling at Centimeter–and–Millimeter–Wave Frequencies in 5G Urban Micro–cell Context”, Paris, France, 28 March 2019, pp. 56.
[7]. Trevor Hastie, Robert Tibshirani, Jerome Friedman, “The Elements of Statistical Learning, Data Mining, Inference and Prediction”, Springer, 2009, pp. 14.
[8]. “5G; Study on channel model for frequencies from 0.5 to 100 GHz” 07-2018 3GPP TR 38.901 version 14.0.0 Release 15, pp. 24-27.
