Predição de perda de percurso utilizando redes neurais artificiais em um canal de TV UHF em Uberlândia/Brasil
DOI:
https://doi.org/10.53660/CONJ-2239-2W39Palavras-chave:
Levenberg-Marquardt, Perda de Percurso, Propagação, Redes Neurais Artificiais, UHFResumo
Este artigo apresenta um novo modelo para a previsão da propagação de ondas eletromagnéticas. Para atingir o objetivo deste estudo, a intensidade do sinal recebido na frequência de 569 MHz na banda UHF foi medida na cidade de Uberlândia (Brasil). A partir dessas medições, foi realizado o cálculo da perda de caminho e desenvolvida uma Rede Neural Artificial (RNA), que possui a capacidade de prever tal fenômeno. Os resultados obtidos por esta rede neural demonstraram resultados superiores quando comparados a outros modelos, como a Recomendação de Perda de Espaço Livre ITU-R P.1546-6, Hata, Egli, COST 231 e ECC-33. Os resultados obtidos, com o modelo proposto, também foram superiores aos obtidos com os modelos apresentados na literatura publicada mais recentemente. Através da utilização do modelo apresentado, foi realizada uma análise estatística, que obteve os seguintes resultados 2,23-dB Erro Médio Absoluto, 8,287-dB Erro Médio Quadrado, 2,879-dB Erro RMS, 1,82-dB Desvio Padrão e 93,6% de Coeficiente de Determinação.
Downloads
Referências
ABHAYAWARDHANA, V. S. et al. Comparison of empirical propagation path loss models for fixed wireless access systems. 2005 IEEE 61st Vehicular Technology Conference. [S.l.]: [s.n.]. 2005. p. 73-77 Vol. 1.
AYADI, M.; BEN ZINEB, A.; TABBANE, S. A UHF Path Loss Model Using Learning Machine for Heterogeneous Networks. IEEE Transactions on Antennas and Propagation, v. 65, p. 3675-3683, 2017.
BENMUS, T. A.; ABBOUD, R.; SHATTER, M. K. Neural network approach to model the propagation path loss for great Tripoli area at 900, 1800, and 2100 MHz bands. 2015 16th International Conference on Sciences and Techniques of Automatic Control and Computer Engineering (STA). [S.l.]: [s.n.]. 2015. p. 793-798.
BRAZILIAN AGENCY OF TELECOMMUNICATIONS (ANATEL). Relatório do Canal. Mosaico Anatel, Brasília, 2022. Available from: <http://sistemas.anatel.gov.br/se/public/view/b/srd.php>. Acesso em: 2022 nov. 11.
BRAZILIAN INSTITUTE OF GEOGRAPHY AND STATISTICS (IBGE). Produto Interno Bruto dos Municípios 2019, 2019. ISSN ISBN: 9786588162033. Available from: <https://www.ibge.gov.br/apps/pibmunic/pdf/PC3%A1gina%20de%20rosto%20Geral%202019.pdf>.
CHEERLA, S.; RATNAM, D. V.; BORRA, H. S. Neural network-based path loss model for cellular mobile networks at 800 and 1800 MHz bands. AEU - International Journal of Electronics and Communications, v. 94, p. 179–186, September 2018. Available from: <https://doi.org/10.1016/j.aeue.2018.07.007>.
EGLI, J. J. Radio Propagation above 40 MC over Irregular Terrain. Proceedings of the IRE, v. 45, p. 1383-1391, 1957.
EICHIE, J. O. et al. Comparative Analysis of Basic Models and Artificial Neural Network Based Model for Path Loss Prediction. Progress In Electromagnetics Research M, v. 61, p. 133–146, 2017. Available from: <https://doi.org/10.2528/pierm17060601>.
FANAN, A. et al. Comparison of propagation models with real measurement around Hull, UK. 2016 24th Telecommunications Forum (TELFOR), p. 1-4, 2016.
FENG, C. et al. A new prediction method for propagation loss in VHF. 2015 IEEE 6th International Symposium on Microwave, Antenna, Propagation, and EMC Technologies (MAPE). [S.l.]: [s.n.]. 2015. p. 1-3.
FERREIRA, G. P.; MATOS, L. J.; SILVA, J. M. M. Improvement of Outdoor Signal Strength Prediction in UHF Band by Artificial Neural Network. IEEE Transactions on Antennas and Propagation, v. 64, p. 5404–5410, December 2016. Available from: <https://doi.org/10.1109/tap.2016.2617379>.
HAGAN, M. T.; MENHAJ, M. B. Training feedforward networks with the Marquardt algorithm. IEEE Transactions on Neural Networks, v. 5, p. 989-993, 1994.
HATA, M. Empirical formula for propagation loss in land mobile radio services. IEEE Transactions on Vehicular Technology, v. 29, p. 317–325, August 1980. Disponivel em: <https://doi.org/10.1109/t-vt.1980.23859>.
HAYKIN, S. S. Neural networks and learning machines. Third. ed. Upper Saddle River, NJ: Pearson Education, 2009.
INTERNATIONAL TELECOMMUNICATION UNION. Validation examples for software implementations of Recommendation ITU-R P.1546. Tabulated values for the field strength curves of Rec. ITU-R P.1546, 2022. Available from: <https://www.itu.int/en/ITU-R/study-groups/rsg3/Pages/iono-tropo-spheric.aspx>. Acesso em: 10 nov. 2022.
ITU-R RECOMMENDATION ITU-R P.1546-6. Method for point-to-area predictions for terrestrial services in the frequency range 30 MHz to 4 000 MHz. [S.l.]. 2019.
MALOKU, H. et al. Path loss model fitting for TV bands based on experimental measurements for urban environments in Kosovo. 2019 42nd International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO). [S.l.]: [s.n.]. 2019. p. 480-485.
MATLAB. version 9.4.0 (R2018a). Natick: The MathWorks Inc., 2018.
MOLLEL, M.; KISANGIRI, M. Comparison of Empirical Propagation Path Loss Models for Mobile Communication. Computer Engineering and Intelligent Systems, v. 5, January 2014.
PARK, C.; TETTEY, D. K.; JO, H.-S. Artificial Neural Network Modeling for Path Loss Prediction in Urban Environment. ArXiv, v. abs/1904.02383, 2019.
POPESCU, I. et al. Neural networks applications for the prediction of propagation path loss in urban environments. IEEE VTS 53rd Vehicular Technology Conference, Spring 2001. Proceedings (Cat. No.01CH37202). [S.l.]: [s.n.]. 2001. p. 387-391 vol.1.
POPOOLA, S. I. et al. Characterization of Path Loss in the VHF Band using Neural Network Modeling Technique. 2019 19th International Conference on Computational Science and Its Applications (ICCSA). [S.l.]: [s.n.]. 2019. p. 166-171.
RHODE & SCHARTWZ. R&S®TSMW Universal Radio Network Analyzer: supoported by many drive test tools Munich: Product Brochure version 22.00, 2019. Available from: <https://cdn-docs.av-iq.com/dataSheet/TSMW_Datasheet.pdf>
SOTIROUDIS, S. P.; SIAKAVARA, K. Mobile radio propagation path loss prediction using Artificial Neural Networks with optimal input information for urban environments. AEU - International Journal of Electronics and Communications, v. 69, p. 1453-1463, 2015. ISSN ISSN: 1434-8411. Available from: <https://www.sciencedirect.com/science/article/pii/S1434841115001855>.
Downloads
Publicado
Como Citar
Edição
Seção
Licença
Copyright (c) 2022 Conjecturas
Este trabalho está licenciado sob uma licença Creative Commons Attribution 4.0 International License.
