Macrocell electric field strength prediction model based upon artificial neural networks

IEEE Journal on Selected Areas in Communications - Tập 20 Số 6 - Trang 1170-1177 - 2002
A. Neskovic1, N. Neskovic1, D. Paunovic1
1School of Electrical Engineering, University of Belgrade, Belgrade, Serbia

Tóm tắt

A new macrocell prediction model for mobile radio environment is presented. The use of feedforward artificial neural networks makes it possible to overcome some important disadvantages of previous prediction models, including both deterministic and statistical types. Our sample implementation is based upon extensive electric field strength measurements (in the 900-MHz frequency band) that were carried out in the city of Belgrade using six different test transmitter locations. Comparison between the data obtained by the proposed electric field strength prediction model and independent measurement sets show that the proposed model is sufficiently accurate for use in planning mobile radio systems.

Từ khóa

#Macrocell networks #Predictive models #Artificial neural networks #Land mobile radio #Radio transmitters #Electric variables measurement #Propagation losses #Diffraction #Integral equations #Frequency measurement

Tài liệu tham khảo

10.1109/T-VT.1984.24014 10.1109/72.286917 rumelhart, 1986, learning internal representations by error propagation, Parallel Distributed Processing Explorations in the Microstructure of Cognition, 318 10.1109/4234.848409 hassoun, 1995, Fundamentals of Artificial Neural Networks 10.1109/2.485892 1988, special issue on mobile radio propagation, IEEE Trans Veh Technol, 37, 3 10.1109/8.14401 ikegami, 1984, theoretical prediction of mean field strength on urban streets, IEEE Trans on Antennas and Propagat, ap–39, 292 10.1109/TAP.1984.1143419 ericsson radio systems ab, 1997, EET-Ericsson engineering tool user reference guide 10.1109/8.366349 moroney, 1995, a fast integral equation approach to uhf coverage estimation, Proc Joint COST 227/231 Workshop, 343 10.1109/VETEC.1994.345139 berg, 1994, a macrocell model based on the parabolic differential equation, Proc Virginia Tech s 4th Symp Wireless Personal Communications, 9.1 10.1109/8.182444 10.1109/VETEC.1998.686635 10.1109/T-VT.1980.23859 wölfle wolfe, 1996, adaptive propagation modeling based on neural network techniques, Proc IEEE 46th Vehicular Technology Conf (VTC), 623 0, ITU-R recommendations P 529-2 P 370-7 P 1146 P 1145 10.1002/9780470930427 leros, 1998, feasibility of neural networks in modeling radio propagation for field strength prediction, Proc Int J Commun Syst, 11, 359, 10.1002/(SICI)1099-1131(199811/12)11:6<359::AID-DAC377>3.0.CO;2-9 ccir study groups period 1978–1982 european broadcasting union, 1980, Improvement of predictions of field strengths in VHF and UHF bands ibrahim, 1983, signal strength prediction in built-up areas, Proc Inst Elect Eng, 130, 377 commission of the european communities, 1984, Digital land mobile radio communications okumura, 1968, field strength and its variability in vhf and uhf land-mobile services, Rev Electr Commun Lab, 16, 825 atefi, 1986, urban radio propagation in mobile radio frequency bands, Proc Inst Elect Eng Communications 86 10.1109/COMST.2000.5340727 kuhlmann, 1995, A forward-scattering algorithm for prediction of the direct-link in a three-dimensional model stocker, 1993, neural network approach to prediction of terrestrial wave propagation for mobile radio, Microwaves Antennas and Propagation IEE Proceedings H, 140, 315, 10.1049/ip-h-2.1993.0048 causebrook, 1993, Vodafone s field strength prediction method balandier, 1995, multi-layer perceptron for field strength prediction in cellular network design, Proc Int Conf Engineering Applications of Artificial Neural Networks EANN 95, 613 10.1109/GLOCOM.1996.587621 caminada, 1997, neural nets: an alternative method for field strength prediction, EURO-COST 231 10.1109/PIMRC.1995.476416