Macrocell Path-Loss Prediction Using Artificial Neural Networks

This paper presents and evaluates artificial neural network (ANN) models used for macrocell path-loss prediction. Measurement data obtained by utilizing the IS-95 pilot signal from a commercial code-division multiple-access (CDMA) mobile network in rural Australia are used to train and evaluate the models. A simple neuron model and feed-forward networks with different numbers of hidden layers and neurons are evaluated regarding their training time, prediction accuracy, and generalization properties. Furthermore, different backpropagation training algorithms, such as gradient descent and Levenberg-Marquardt, are evaluated. The artificial neural network inputs are chosen to be distance to base station, parameters easily obtained from terrain path profiles, land usage, and vegetation type and density near the receiving antenna. The path-loss prediction results obtained by using the ANN models are evaluated against different versions of the semi-terrain based propagation model Recommendation ITU-R P.1546 and the Okumura-Hata model. The statistical analysis shows that a non-complex ANN model performs very well compared with traditional propagation models with regard to prediction accuracy, complexity, and prediction time. The average ANN prediction results were 1) maximum error: 22 dB; 2) mean error: 0 dB; and 3) standard deviation: 7 dB. A multilayered feed-forward network trained using the standard backpropagation algorithm was compared with a neuron model trained using the Levenberg-Marquardt algorithm. It was found that the training time decreases from 150 000 to 10 iterations, while the prediction accuracy is maintained.

[1]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[2]  Theodore S. Rappaport,et al.  Wireless Communications: Principles and Practice (2nd Edition) by , 2012 .

[3]  Martin T. Hagan,et al.  Gauss-Newton approximation to Bayesian learning , 1997, Proceedings of International Conference on Neural Networks (ICNN'97).

[4]  B. Milovanovic,et al.  The hybrid-neural empirical model for the electromagnetic field level prediction in urban environments , 2004, 7th Seminar on Neural Network Applications in Electrical Engineering, 2004. NEUREL 2004. 2004.

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

[6]  Charles R. Johnson,et al.  Matrix analysis , 1985, Statistical Inference for Engineers and Data Scientists.

[7]  H. Suzuki,et al.  Macrocell radio wave propagation prediction using an artificial neural network , 2004, IEEE 60th Vehicular Technology Conference, 2004. VTC2004-Fall. 2004.

[8]  J. D. Parsons,et al.  The Mobile Radio Propagation Channel , 1991 .

[9]  Philip Constantinou,et al.  ANN Prediction Models for Outdoor Environment , 2006, 2006 IEEE 17th International Symposium on Personal, Indoor and Mobile Radio Communications.

[10]  Martin T. Hagan,et al.  Neural network design , 1995 .

[11]  F. M. Landstorfer,et al.  Empirical prediction of radiowave propagation by neural network simulator , 1992 .

[12]  Theodore S. Rappaport,et al.  Wireless communications - principles and practice , 1996 .

[13]  Dacheng Yang,et al.  A recursive algorithm for radio propagation model calibration based on CDMA forward pilot channel , 2003, 14th IEEE Proceedings on Personal, Indoor and Mobile Radio Communications, 2003. PIMRC 2003..

[14]  David J. C. MacKay,et al.  A Practical Bayesian Framework for Backpropagation Networks , 1992, Neural Computation.

[15]  George A. Hufford,et al.  An Integral Equation Approach to the Problem of Wave Propagation over an Irregular Surface , 1952 .

[16]  Raúl Rojas,et al.  Neural Networks - A Systematic Introduction , 1996 .

[17]  Aleksandar Neskovic,et al.  Indoor electric field level prediction model based on the artificial neural networks , 2000, IEEE Communications Letters.

[18]  Philip A. Araman,et al.  Automated methods of tree boundary extraction and foliage transparency estimation from digital imagery , 2003 .

[19]  Hans-Jürgen Zepernick,et al.  Evaluation of the Propagation Model Recommendation ITU-R P.1546 for Mobile Services in Rural Australia , 2008, IEEE Transactions on Vehicular Technology.

[20]  David J. C. MacKay,et al.  Bayesian Interpolation , 1992, Neural Computation.

[21]  H. Suzuki,et al.  Evaluation of a New Effective Antenna Height Definition in ITU-R Recommendation P. 1546-1 , 2005, 2005 Asia-Pacific Conference on Communications.

[22]  C. C. Constantinou,et al.  A three-dimensional parabolic equation applied to VHF/UHF propagation over irregular terrain , 1999 .

[23]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[24]  Simon R. Saunders,et al.  A comparison of the accuracy of propagation models using hit rate analysis , 2001, IEEE 54th Vehicular Technology Conference. VTC Fall 2001. Proceedings (Cat. No.01CH37211).

[25]  Martin T. Hagan,et al.  Neural networks for control , 1999, Proceedings of the 1999 American Control Conference (Cat. No. 99CH36251).

[26]  R. Luebbers,et al.  Propagation prediction for hilly terrain using GTD wedge diffraction , 1984 .

[27]  H. Suzuki,et al.  Evaluation of the new semi-terrain based propagation model recommendation ITU-R P.1546 , 2003, 2003 IEEE 58th Vehicular Technology Conference. VTC 2003-Fall (IEEE Cat. No.03CH37484).