Performance analysis of artificial neural networks for predicting propagation losses in suburban environments for 4G LTE and 5G networks

Bruno Jácome Cavalcanti

ORCID iD Instituto Federal da Paraíba (IFPB), João Pessoa, Paraíba, Brasil

Gustavo Araújo Cavalcante

ORCID iD Instituto Federal da Paraíba (IFPB), João Pessoa, Paraíba, Brasil

Laércio Martins de Mendonça

ORCID iD Universidade Federal do Rio Grande do Norte (UFRN), Natal, Rio Grande do Norte, Brasil

Resumo

This study analyzes two distinct approaches for predicting path loss at frequencies of 800 MHz, 1800 MHz, and 2600 MHz in suburban areas. These frequencies are commonly utilized in broadcasting, 4G LTE, and 5G networks. Two models of Artificial Neural Networks (ANN) were implemented: an Error-Based Neural Network (EBNN), which incorporates error correction by combining empirical propagation models with an ANN, and a Terrain Parameters Based Neural Network (TBNN), which uses input parameters commonly applied in related studies, such as the distance from the transmitter to the receiver, receiver altitude, average terrain level, and azimuth angle between the transmitter and receiver. The performance of these models was evaluated using root mean square error (RMSE) and the Wilcoxon rank-sum test, comparing them with empirical propagation models such as SUI, ECC-33, Ericsson, and TR 25.942. The results were then compared with data obtained from a measurement campaign conducted along three routes in the city of Natal, Brazil. The findings from both simulations and actual measurements showed good metric alignment, particularly highlighting the performance of the error-based model. The primary contribution of this study is demonstrating that these techniques enable more accurate prediction of signal information, thereby reducing errors in the planning and implementation of wireless networks.

Palavras-chave


4G LTE; 5G networks; artificial neural networks; path loss


Texto completo:

Referências


GPP. TR 25.942. 3rd generation partnership project. Technical specification group radio access network. Radio Frequency (RF) system scenarios. V18.0.0, March. 2024a. Available at: https://portal.3gpp.org/desktopmodules/Specifications/SpecificationDetails.aspx?specificationId=1362. Acessed on: 06 sep. 2024.

GPP. TS 36.101. 3rd generation partnership project. Technical specification group radio access network. Evolved universal terrestrial radio access (E-UTRA). User equipment (UE) radio transmission and reception. V18.6.0, July, 2024b. Available at: https://portal.3gpp.org/desktopmodules/Specifications/SpecificationDetails.aspx?specificationId=2411. Acessed on: 06 sep. 2024.

GPP. TR 36.942. 3rd generation partnership project. Technical specification group radio access network. Evolved universal terrestrial radio access (E-UTRA). Radio Frequency (RF) system scenarios. V18.0.0, April. 2024c. Avaliable at: https://portal.3gpp.org/desktopmodules/Specifications/SpecificationDetails.aspx?specificationId=2592. Acessed on: 06 sep. 2024.

GPP. TS 38.101-1. 3rd generation partnership project. Technical specification group radio access network. NR. User Equipment (UE) radio transmission and reception. Part 1: range standalone. V18.6.0, July, 2024d. Avaliable at: https://portal.3gpp.org/desktopmodules/Specifications/SpecificationDetails.aspx?specificationId=3283. Acessed on: 06 sep. 2024.

ANDRADE, C. The P value and statistical significance: misunderstandings, explanations, challenges, and alternatives. Indian Journal of Psychological Medicine, v. 41, n. 3, p. 210-215, 2019. DOI: https://doi.org/10.4103/ijpsym.ijpsym_193_19.

ASHRAFIJOO, B.; FARAHMAND, N. F-H.; MATIN, Y. A.; RAHMANI, K. Designing an optimal model using artificial neural networks to predict non-linear time series (case study: Tehran Stock Exchange Index). Journal of System Management, v. 8, n. 4, p. 65-80, 2022. DOI: https://doi.org/10.30495/jsm.2022.1965914.1679.

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. In: 2015 INTERNATIONAL CONFERENCE ON SCIENCES AND TECHNIQUES OF AUTOMATIC CONTROL AND COMPUTER ENGINEERING (STA), 16., 2015, Monastir. Proceedings […] Monastir: IEEE, 2015. p. 793-798. DOI: https://doi.org/10.1109/STA.2015.7505236.

CINTRA, R. S.; VELHO, H. F. C. Global data assimilation using artificial neural networks in Speedy model. In: INTERNATIONAL SYMPOSIUM UNCERTAINTY QUANTIFICATION AND STOCHASTIC MODELING, 2012, São Sebastião. Proceedings […]. São Sebastião, 2012, p. 648-654. Available at: http://mtc-m16d.sid.inpe.br/col/sid.inpe.br/mtc-m19/2012/10.17.17.02/doc/106RCintra.pdf. Accessed on: 25 aug. 2024.

DAI, Q. A competitive ensemble pruning approach based on cross-validation technique. Knowledge-Based Systems, v. 37, p. 394-414, 2013. DOI: https://doi.org/10.1016/j.knosys.2012.08.024.

EICHIE, J. O.; OYEDUM, O. D..; AJEWOLE, M.; AIBINU, A. M. Comparative analysis of basic models and artificial neural network based model for path loss prediction. Progress In Electromagnetics Research, v. 61, p. 133-146, 2017. DOI: http://dx.doi.org/10.2528/PIERM17060601.

Google Maps. Available at: https://maps.app.goo.gl/dgGymVNzCGGyxRhW8. Accessed on: 06 sep. 2024.

HAYKIN, S. Neural networks and learning machines. Prentice Hall, 2009.

HERNÁNDEZ, G.; ZAMORA, E.; SOSSA, H.; TÉLLEZ, G.; FURLÁN, F. Hybrid neural networks for big data classification. Neurocomputing, v. 390, p. 327-340, 2020. DOI: https://doi.org/10.1016/j.neucom.2019.08.095.

JI, X.; HE, X.; LV, C.; LIU, Y.; WU, J. Adaptive-neural-network-based robust lateral motion control for autonomous vehicle at driving limits. Control Engineering Practice, v. 76, p. 41-53, 2018. DOI: https://doi.org/10.1016/j.conengprac.2018.04.007.

JO, H.-S.; PARK, C.; LEE, E.; CHOI, H. K.; PARK, J. Path loss prediction based on machine learning techniques: principal component analysis, artificial neural network, and Gaussian process. Sensors, v. 20, n. 7, 1927, 2020. DOI: https://doi.org/10.3390/s20071927.

KUMARI, M.; YADAV, T.; YADAV, P.; SHARMA, P. K.; SHARMA, D. Comparative study of path loss models in different environments. International Journal of Engineering Science and Technology, v. 3, n. 4, p. 2945-2949, 2011.

MA, S.; ZHANG, X.; JIA, C.; ZHAO, Z.; WANG, S.; WANG, S. Image and video compression with neural networks: a review. IEEE Transactions on Circuits and Systems for Video Technology, v. 30, n. 6, p. 1683-1698, 2019. DOI: https://doi.org/10.1109/TCSVT.2019.2910119.

MATHEW, B.; GEORGE, W.; PEREIRA, M. QoS Enhancement in 4G heterogeneous networks using Kalman Filter & EWMA. International Journal of Electronics and Communications Engineering and Technology (IJECET), v. 8, n. 3, p. 28-43, 2017. Available at: https://iaeme.com/Home/article_id/IJECET_08_03_004. Accessed on: 25 aug. 2024.

MORAITIS, N.; TSIPI, L.; VOUYIOUKAS, D. Machine learning-based methods for path loss prediction in urban environment for LTE networks. In: 2020 INTERNATIONAL CONFERENCE ON WIRELESS AND MOBILE COMPUTING, NETWORKING AND COMMUNICATIONS (WiMob), 16.,.2020, Thessaloniki. Proceedings […]. Thessaloniki: IEEE, 2020. DOI: https://doi.org/10.1109/WiMob50308.2020.9253369.

PASTERNACK. PE51043 and PE51054 antennas. Pasternack. Available at: https://www.pasternack.com/panel-antenna-n-female-2500-2700-mhz-14-dbi-pe51043-p.aspx and https://www.everythingrf.com/products/all-antennas/pasternack-enterprises-inc/741-20-pe51054. Accessed on: 11 Aug. 2024.

POPESCU, I.; KANSTAS, A.; ANGELOU, E.; NAFORNITA, L.; CONSTANTIOU, P. Applications of generalized RBF-NN for path loss prediction. In: IEEE INTERNATIONAL SYMPOSIUM ON PERSONAL, INDOOR AND MOBILE RADIO COMMUNICATIONS, 13., Lisbon, 2002. Proceedings […]. Lisbon: IEEE, p. 484-488, 2002. DOI: https://doi.org/10.1109/PIMRC.2002.1046748.

POPESCU, I.; NAFORNITA, I.; CONSTANTINOU, P. Comparison of neural network models for path loss prediction. In: IEEE INTERNATIONAL CONFERENCE ON WIRELESS AND MOBILE COMPUTING, NETWORKING AND COMMUNICATIONS (WiMob'2005), 2005, Montreal. Proceedings […]. Montreal: IEEE, 2005. p. 44-49. DOI: https://doi.org/10.1109/WIMOB.2005.1512814.

POPOOLA, S. I.; FARUK, N.; SURAJUDEEN-BAKINDE, N. T.; ATAYERO, A. A.; MISRA, S. Artificial neural network model for path loss predictions in the VHF band. In: TRIPATHI, M., UPADHYAYA, S. (eds) Conference Proceedings of ICDLAIR2019. ICDLAIR 2019. Lecture Notes in Networks and Systems, v. 175. Cham: Springer, 2019. DOI: https://doi.org/10.1007/978-3-030-67187-7_18.

RAJENDRA, P.; MURTHY, K. V. N.; SUBBARAO, A.; BOADH, R. Use of ANN models in the prediction of meteorological data. Modeling Earth Systems and Environment, v. 5, p. 1051-1058, 2019. DOI: https://doi.org/10.1007/s40808-019-00590-2.

RIEDEL, T.; TAKAHASHI, M.; TATSUKAWA, T.; ITOH, E. Evaluating applied flight-deck interval management using Monte Carlo simulations on the K-Supercomputer. Transactions of the Japan Society for Aeronautical and Space Sciences, v. 62, n. 6, p. 299-309, 2019. DOI: https://doi.org/10.2322/tjsass.62.299.

SAEED, M. A.; KHAN, M. Z.; KHAN, A.; SAEED, M. U.; HASSAN, M. A. S.; JAVED, T. Impact of propagation path loss by varying BTS height and frequency for combining multiple path loss approaches in macro-femto environment. Arabian Journal for Science and Engineering, v. 47, n. 2, p. 1227-1238, 2022. DOI: https://doi.org/10.1007/s13369-021-05819-w.

SANCHES, M. A. R.; CAVALCANTE, G. P. S. Modelos neuro-adaptados para prediçao de radiopropagaçao em sistemas móveis terrestres. Revista da Sociedade Brasileira de Telecomunicações, v. 1, n. 1, p. 11-15, 2015. Available at: https://jcis.sbrt.org.br/jcis/article/view/246. Accessed on: 25 aug. 2024. In Portuguese.

SIDDIQUI, S. A.; FATIMA, N.; AHMAD, A. Comparative analysis of propagation path loss models in LTE networks. In: 2019 INTERNATIONAL CONFERENCE ON POWER ELECTRONICS, CONTROL AND AUTOMATION (ICPECA), 2019, New Delhi. Proceedings […]. New Delhi: IEEE, 2019. DOI: https://doi.org/10.1109/ICPECA47973.2019.8975464.

SILVA, P. H. F.; PASSOS, M. G. Numerical analysis of the SIGAnatel tool for technical feasibility studies of TV and FM broadcast channels. In: 2007 SBMO/IEEE MTT-S INTERNATIONAL MICROWAVE AND OPTOELECTRONICS CONFERENCE, 2007, Salvador. Proceedings […]. Salvador: IEEE, 2007. p. 569-573.DOI: https://doi.org/10.1109/IMOC.2007.4404329.

SUN, S.; RAPPAPORT, T. S.; THOMAS, T. A.; GHOSH, A.; NGUYEN, H. C.; KOVÁCS, I. Z.; RODRIGUEUZ, I.; KOYMEN, O.; PARTYKA, A. Investigation of prediction accuracy, sensitivity, and parameter stability of large-scale propagation path loss models for 5G wireless communications. IEEE Transactions on Vehicular Technology, v. 65, n. 5, p. 2843-2860, 2016. DOI: https://doi.org/10.1109/TVT.2016.2543139.

SUNG, S.; CHOI, W.; KIM, H.; JUNG, J.-I. Deep learning-based path loss prediction for fifth-generation new radio vehicle communications. IEEE Access, v. 11, p. 75295-75310, 2023. DOI: https://doi.org/10.1109/ACCESS.2023.3297215.

WEINSTOCK, H. C. (ed.) Focus on cognitive radio technology. Nova Publishers, 2007.


DOI: http://dx.doi.org/10.18265/2447-9187a2024id8532

O arquivo PDF selecionado deve ser carregado no navegador caso tenha instalado um plugin de leitura de arquivos PDF (por exemplo, uma versão atual do Adobe Acrobat Reader).

Como alternativa, pode-se baixar o arquivo PDF para o computador, de onde poderá abrí-lo com o leitor PDF de sua preferência. Para baixar o PDF, clique no link abaixo.

Caso deseje mais informações sobre como imprimir, salvar e trabalhar com PDFs, a Highwire Press oferece uma página de Perguntas Frequentes sobre PDFs bastante útil.

Download do PDF
Imprimir artigo
Exibir metadados
Como citar este documento

Visitas a este artigo: 149

Total de downloads do artigo: 65