Title :
Prediction of slant path rain attenuation based on artificial neural network
Author :
Hongwei Yang ; He, Chen ; Zhu, Hongwen ; Song, Wentao
Author_Institution :
Dept. of Electron. Eng., Shanghai Jiaotong Univ., China
Abstract :
Rain attenuation is predicted in various compositions of the frequency, the elevation angle, the rain-fall rate, the percent of the time, the polarization angle, the altitude of the earth station and the latitude of the earth station by means of artificial neural network in this paper. The rain attenuation prediction model of millimeter waves based on an artificial neural network is proposed for the first time, and the predicted results are compared with the CCIR recommendation model. The results show that the artificial neural network can obtain the nonlinear relation of the rain attenuation and the other factors that affect millimeter wave propagation attenuation and improve the accuracy of rain attenuation prediction with a 1.3 dB increase on average. It is a useful approach to construct the rain attenuation prediction model of millimeter wave with artificial neural network
Keywords :
millimetre wave propagation; neural nets; rain; satellite communication; telecommunication computing; tropospheric electromagnetic wave propagation; ANN; EHF; MM-wave propagation attenuation; artificial neural network; earth station altitude; earth station latitude; elevation angle; millimeter waves; nonlinear relation; polarization angle; rain attenuation prediction; rain-fall rate; signal frequency; slant path rain attenuation; Artificial neural networks; Atmospheric modeling; Attenuation; Frequency; Millimeter wave communication; Millimeter wave propagation; Millimeter wave technology; Optical attenuators; Predictive models; Rain;
Conference_Titel :
Circuits and Systems, 2000. Proceedings. ISCAS 2000 Geneva. The 2000 IEEE International Symposium on
Conference_Location :
Geneva
Print_ISBN :
0-7803-5482-6
DOI :
10.1109/ISCAS.2000.857049
