Rain Attenuation Prediction Using Artificial Neural Network for Dynamic Rain Fade Mitigation

Atmospheric processes from which rainfall is formed are complex and cannot be accurately predicted using mathematical or statistical models. In this paper, the backpropagation neural network (BPNN) is trained to predict rainfall rates, and hence attenuation that is likely to be experienced on a link. This study is carried out over the sub-tropical region of Durban, South Africa (29.8587°S, 31.0218°E). Utilizing the non-linear mapping capability between inputs and outputs, the backpropagation neural network is trained using rainfall data collected from 2013 to 2016 to predict rainfall rates. Long-term rain attenuation statistics arising from predicted rain rates are compared with actual and ITU-R model, and results show a relatively small margin of error between predicted rain attenuation exceeded for 0.01 % of an average year. Furthermore, analysis of predicted and actual rain attenuation within individual rain events from different rainfall regimes was carried out and results show that the proposed model can be used to predict the state of the link. This is demonstrated when the trained BPNN was tested using unseen data that was collected from January 2017 to May 2018, a period that spans through all four different climatic seasons of summer, autumn, winter and spring. Results of the test show a correlation coefficient of 0.8298. Finally, the proposed rain prediction model was tested on rainfall data from Butare, Rwanda (2.6078°S, 29.7368°E), which is a tropical region and results obtained indicate the portability of the proposed model to other regions.

[1]  C. Riva,et al.  The search for the most reliable long-term rain attenuation CDF of a slant path and the impact on prediction models , 2005, IEEE Transactions on Antennas and Propagation.

[2]  G. Brussaard,et al.  Rain attenuation statistics from rain cell diameters and heights , 2001, Int. J. Satell. Commun. Netw..

[3]  Roelof K. Brouwer.  The Backpropagation Algorithm in J, a Fast Prototyping Tool for Researching Neural Networks , 1999, Int. J. Neural Syst..

[4]  C.S. Pattichis,et al.  Prediction of rainfall rate based on weather radar measurements , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[5]  H. Purnomo,et al.  Artificial Neural Network for Monthly Rainfall Rate Prediction , 2017 .

[6]  Thomas J. Afullo,et al.  30-Second and One-Minute Rainfall Rate Modelling and Conversion for Millimetric Wave Propagation in South Africa , 2016 .

[7]  F. Moupfouma,et al.  Model of rainfall-rate distribution for radio system design , 1985 .

[8]  Thomas J. Afullo,et al.  Rainfall rate prediction based on artificial neural networks for rain fade mitigation over earth-satellite link , 2017, 2017 IEEE AFRICON.

[9]  Deepak Ranjan Nayak,et al.  A Survey on Rainfall Prediction using Artificial Neural Network , 2013 .

[10]  Nitin K. Tripathi,et al.  An artificial neural network model for rainfall forecasting in Bangkok, Thailand , 2008 .

[11]  G. Ajayi,et al.  Some Tropical Rainfall Rate Characteristics at Ile-Ife for Microwave and Millimeter Wave Applications , 1984 .

[12]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[13]  Emilio Matricciani.  Rate of change of signal attenuation from sirio at 11.6 GHz , 1981 .

[14]  K. Abhishek,et al.  A rainfall prediction model using artificial neural network , 2012, 2012 IEEE Control and System Graduate Research Colloquium.

[15]  L. Luini,et al.  Analysis and Parameterization of Methodologies for the Conversion of Rain-Rate Cumulative Distributions from Various Integration Times to One Minute , 2009, IEEE Antennas and Propagation Magazine.