Predicción experimental de cobertura en una red LTE mediante el uso de algoritmos de machine learning

Share:

Resumen

Objetivo: Predecir de forma experimental la cobertura de una red Long Term Evolution (LTE) mediante el uso de algoritmos de machine learning. Metodología: La investigación es de tipo descriptiva por el análisis de las causas  y factores que influyen en las variables, según el método cuasi-experimental por las mediciones de potencia en condiciones controladas de campo. Se realiza el estudio de las variables físicas que determinar la cobertura en la prestación del servicio de una red móvil mediante el trazado de cuatro rutas; los datos son evaluados, pre procesados y filtrados para probarlos en mediante modelos matemáticos clásicos, luego se aplican los métodos estadísticos de predicción, como también los algoritmos de predicción con la ayuda del aprendizaje automático (ML) para la generación de modelos que categoricen el uso de cada celda dentro de la agrupación, entre los métodos a usar son: estadística descriptiva, Random Forest (RD), cuantificación de densidad, Isolation Forest (IF) y Multivariable Outliers (MO). Posteriormente se realiza la validación cruzada y la predicción del uso de la celda. Resultados: Con los valores obtenidos se establece la correlación entre el comportamiento de los parámetros de potencia y distancia, y con las variables óptimas de cobertura se compara con los modelos tradicionales para una celda estudiada. Conclusiones: El proceso de la integración de técnicas matemáticas y computacionales facilita la toma de decisiones de los ingenieros de radio  en el diagnóstico, gestión, planificación y redimensionamiento de redes LTE bajo condiciones en donde las redes se hacen mucho más heterogéneas y los servicios móviles requieren de más recursos de la infraestructura tecnológica.

Citas

  1. A. Kulkarni, A. Seetharam, A. Ramesh, and J. D. Herath, “DeepChannel: Wireless channel quality prediction using deep learning,” IEEE Trans. Veh. Technol., vol. 69, no. 1, pp. 443–456, 2020, doi: 10.1109/TVT.2019.2949954.
  2. I.-R. Recommandation P-1411-9, Datos de propagación y métodos de predicción para la planificación de sistemas de radiocomunicaciones en interiores y redes radioeléctricas de área local en la gama de frecuencias de 900 MHz a 100 GHz Serie P, vol. 7. 2017.
  3. I. M. M Mohamed, “Accurate Path-Loss Estimation for Wireless Cellular Networks,” J. Kejuruter., vol. 33, no. 2, pp. 317–328, 2021, doi: 10.17576/jkukm-2021-33(2)-16.
  4. Q. He, A. Moayyedi, G. Dan, G. P. Koudouridis, and P. Tengkvist, “A Meta-Learning Scheme for Adaptive Short-Term Network Traffic Prediction,” IEEE J. Sel. Areas Commun., vol. 38, no. 10, pp. 2271–2283, 2020, doi: 10.1109/JSAC.2020.3000408.
  5. S. Bi, J. Lyu, Z. Ding, and R. Zhang, “Engineering radio maps for wireless resource management,” IEEE Wirel. Commun., vol. 26, no. 2, pp. 133–141, 2019, doi: 10.1109/MWC.2019.1800146.
  6. T. S. Rappaport and S. Sandhu, “Radio wave propagation for emerging wireless personal communication systems,” in Wireless Personal Communications, Springer, 2002, pp. 1–27.
  7. Z. Chen and Y. Zhang, “Distributed spectrum monitoring system based on RSSI optimization algorithm,” Prog. Electromagn. Res. Symp., vol. 2017-Novem, pp. 2350–2355, 2017, doi: 10.1109/PIERS-FALL.2017.8293529.
  8. M. Chen, U. Challita, W. Saad, C. Yin, and M. Debbah, “Artificial Neural Networks-Based Machine Learning for Wireless Networks: A Tutorial,” IEEE Commun. Surv. Tutorials, vol. 21, no. 4, pp. 3039–3071, 2019, doi: 10.1109/COMST.2019.2926625.
  9. P. Campos, Á. Hernández-Solana, and A. Valdovinos-Bardají, “Machine Learning for Hidden Nodes Detection in Unlicensed LTE Networks,” Comput. Networks, vol. 208, no. February, 2022, doi: 10.1016/j.comnet.2022.108862.
  10. O. O. Erunkulu, A. M. Zungeru, C. K. Lebekwe, and J. M. Chuma, “Cellular Communications Coverage Prediction Techniques: A Survey and Comparison,” IEEE Access, vol. 8, pp. 113052–113077, 2020, doi: 10.1109/ACCESS.2020.3003247.
  11. M. D. Yacoub, Foundations of Mobile Radio Engineering. 2019.
  12. Y. Zhang, J. Wen, G. Yang, Z. He, and J. Wang, “Path loss prediction based on machine learning: Principle, method, and data expansion,” Appl. Sci., vol. 9, no. 9, 2019, doi: 10.3390/app9091908.
  13. H. S. Jo, C. Park, E. Lee, H. K. Choi, and J. Park, “Path loss prediction based on machine learning techniques: Principal component analysis, artificial neural network and gaussian process,” Sensors (Switzerland), vol. 20, no. 7, 2020, doi: 10.3390/s20071927.
  14. C. E. G. Moreta, M. R. C. Acosta, and I. Koo, “Prediction of digital terrestrial television coverage using machine learning regression,” IEEE Trans. Broadcast., vol. 65, no. 4, pp. 702–712, 2019, doi: 10.1109/TBC.2019.2901409.
  15. H. Elsherbiny, H. M. Abbas, H. Abou-Zeid, H. S. Hassanein, and A. Noureldin, “4G LTE Network Throughput Modelling and Prediction,” 2020 IEEE Glob. Commun. Conf. GLOBECOM 2020 - Proc., pp. 3–8, 2020, doi: 10.1109/GLOBECOM42002.2020.9322410.
  16. J. Isabona et al., “Development of a Multilayer Perception Neural Network for Optimal Predictive Modeling in Urban Microcellular Radio Environments,” Appl. Sci., vol. 12, no. 11, 2022, doi: 10.3390/app12115713.
  17. C. Gijón, M. Toril, S. Luna-Ramírez, M. L. Marí-Altozano, and J. M. Ruiz-Avilés, “Long-term data traffic forecasting for network dimensioning in lte with short time series,” Electron., vol. 10, no. 10, 2021, doi: 10.3390/electronics10101151.
  18. J. Riihijarvi and P. Mahonen, “Machine Learning for Performance Prediction in Mobile Cellular Networks,” IEEE Comput. Intell. Mag., vol. 13, no. 1, pp. 51–60, 2018, doi: 10.1109/MCI.2017.2773824.
  19. N. Moraitis, L. Tsipi, and D. Vouyioukas, “Machine learning-based methods for path loss prediction in urban environment for LTE networks,” Int. Conf. Wirel. Mob. Comput. Netw. Commun., vol. 2020-Octob, 2020, doi: 10.1109/WiMob50308.2020.9253369.
  20. R. Bureau, “HANDBOOK Spectrum Monitoring,” Int. Telecommun. Union, p. 168, 2011.
  21. Francois Rancy, “Handbook on national spectrum management,” Itu-R, pp. 1–326, 2015.
  22. B. Charbuty and A. Abdulazeez, “Classification Based on Decision Tree Algorithm for Machine Learning,” J. Appl. Sci. Technol. Trends, vol. 2, no. 01, pp. 20–28, 2021, doi: 10.38094/jastt20165.
  23. L. Alho, A. Burian, J. Helenius, and J. Pajarinen, “Machine learning based mobile network throughput classification,” IEEE Wirel. Commun. Netw. Conf. WCNC, vol. 2021-March, 2021, doi: 10.1109/WCNC49053.2021.9417365.
  24. L. Huang, L. Lu, and W. Hua, “A survey on next-cell prediction in cellular networks: Schemes and applications,” IEEE Access, vol. 8, pp. 201468–201485, 2020, doi: 10.1109/ACCESS.2020.3036070.
  25. Unión Internacional de Telecomunicaciones, “Recomendación UIT-R P.1411-7,” Recom. UIT-R P.1411-7, vol. 1, pp. 1–39, 2013, [Online]. Available: https://www.itu.int/.
  26. J. Herrera, “Metodología de medición del espectro con técnicas experimentales para obtener modelos de propagación,” vol. 1, p. 165, 2021, [Online]. Available: https://www.unipamplona.edu.co/unipamplona/portalIG/home_10/recursos/2015_s1/pag_contenido/02032015/libros_2015.jsp.
  27. A. Bhuvaneshwari, R. Hemalatha, and T. Satyasavithri, “Semi Deterministic Hybrid Model for Path Loss Prediction Improvement,” Procedia Comput. Sci., vol. 92, pp. 336–344, 2016, doi: 10.1016/j.procs.2016.07.388.
  28. N. Heydarishahreza and N. Ansari, “Mobile Node Localization in Wireless Networks: Path-Loss Model, Trilateration, and Error Mitigation in a 5G Sub-6 GHz Scenario,” J. Netw. Netw. Appl., vol. 3, no. 3, pp. 129–136, 2023, doi: 10.33969/j-nana.2023.030304.
  29. M. Bouzidi, M. Mohamed, Y. Dalveren, A. Moldsvor, F. A. Cheikh, and M. Derawi, “Propagation Measurements for IQRF Network in an Urban Environment,” Sensors, vol. 22, no. 18, pp. 1–21, 2022, doi: 10.3390/s22187012.
  30. S. Kumar, P., Patil, B., & Ram, “Selection of Radio Propagation Model for Long Term Evolution ( LTE ) Network,” Int. J. Eng. Res. Gen. Sci., vol. 3, no. 1, pp. 373–379, 2015, Accessed: Jul. 15, 2018. [Online]. Available: www.ijergs.org.
  31. G. L. Stüber, Principles of mobile communication: Fourth edition. 2017.
  32. A. L. Imoize and T. E. Ogunfuwa, “Propagation Measurements of a 4G LTE Network in Lagoon Environment,” Niger. J. Technol. Dev., vol. 16, no. 1, pp. 1–9, 2019, doi: 10.4314/njtd.v16i1.1.
  33. S. Saunders and A. Aragon, Antennas and propagation for wireless communications systems. England, 2018.
  34. B. Golman, “A set of Jupyter notebooks for the analysis of transport phenomena and reaction in porous catalyst pellet,” Comput. Appl. Eng. Educ., vol. 27, no. 3, pp. 531–542, 2019, doi: 10.1002/cae.22095.
  35. I. Pintye, E. Kail, P. Kacsuk, and R. Lovas, “Big data and machine learning framework for clouds and its usage for text classification,” Concurr. Comput. Pract. Exp., vol. 33, no. 19, pp. 1–14, 2021, doi: 10.1002/cpe.6164.
  36. Z. Wang, Z. Su, Y. Deng, J. Kurths, and J. Wu, “Spatial network disintegration based on kernel density estimation,” Reliab. Eng. Syst. Saf., vol. 245, no. August 2023, p. 110005, 2024, doi: 10.1016/j.ress.2024.110005.
  37. G. K. Vishwakarma, C. Paul, and A. M. Elsawah, “An algorithm for outlier detection in a time series model using backpropagation neural network,” J. King Saud Univ. - Sci., vol. 32, no. 8, pp. 3328–3336, 2020, doi: 10.1016/j.jksus.2020.09.018.
  38. Y. Pu, W. Yao, X. Li, and A. Alhudhaif, “An adaptive highly improving the accuracy of clustering algorithm based on kernel density estimation,” Inf. Sci. (Ny)., vol. 663, no. August 2023, p. 120187, 2024, doi: 10.1016/j.ins.2024.120187.
  39. O. Lifandali, N. Abghour, and Z. Chiba, “Feature Selection Using a Combination of Ant Colony Optimization and Random Forest Algorithms Applied to Isolation Forest Based Intrusion Detection System,” Procedia Comput. Sci., vol. 220, pp. 796–805, 2023, doi: 10.1016/j.procs.2023.03.106.
  40. Ł. Gałka and P. Karczmarek, “Deterministic attribute selection for isolation forest,” Pattern Recognit., vol. 151, no. March, 2024, doi: 10.1016/j.patcog.2024.110395.
  41. A. Al-Thaedan et al., “Downlink throughput prediction using machine learning models on 4G-LTE networks,” Int. J. Inf. Technol., vol. 15, no. 6, pp. 2987–2993, 2023, doi: 10.1007/s41870-023-01358-9.
  42. M. Mayrhofer and P. Filzmoser, “Multivariate outlier explanations using Shapley values and Mahalanobis distances,” Econom. Stat., no. xxxx, 2023, doi: 10.1016/j.ecosta.2023.04.003.
  43. A. Nowak-Brzezinska and C. Horyn, “Outliers in rules - The comparision of LOF, COF and KMEANS algorithms.,” Procedia Comput. Sci., vol. 176, pp. 1420–1429, 2020, doi: 10.1016/j.procs.2020.09.152.
  44. D. Zou et al., “Outlier detection and data filling based on KNN and LOF for power transformer operation data classification,” Energy Reports, vol. 9, pp. 698–711, 2023, doi: 10.1016/j.egyr.2023.04.094.
Cómo citar
[1]
J. E. Herrera Rubio, G. A. Portilla González, y A. M. Osorio Velazco, «Predicción experimental de cobertura en una red LTE mediante el uso de algoritmos de machine learning », Investigación e Innovación en Ingenierías, vol. 12, n.º 2, nov. 2024.

Send mail to Author


Send Cancel

Custom technologies based on your needs

  • MongoDB
  • ElasticSearch
  • Redis
  • Solr
  • Memcached