Reviewing Methodological Contributions to Large-Scale Mobile Infrastructure Deployment Engineering
DOI:
https://doi.org/10.54536/ajise.v5i3.8517Keywords:
5G Coverage Planning, Dense Urban Deployment, Domain Transfer, Machine Learning Path Loss Prediction, Model Generalization, Propagation Model CalibrationAbstract
Dense urban 5G coverage planning produces coverage holes and cost overruns that commentary attributes to the static functional form of legacy propagation models. This article develops an alternative account: documented planning failures trace to deployment geometries positioned outside a model’s calibrated envelope of frequency, distance, and antenna height, a condition that applies to learned predictive models with the same force it applies to parametric ones once the target environment departs from the training distribution. A structured comparative synthesis of peer-reviewed sources, organized into three evidentiary groups and supplemented by a quantitative extraction of documented error and boundary values, traces the relationship between deployment-geometry divergence and prediction error across both model classes. The extracted evidence shows accuracy scaling with distance from a model’s calibration envelope regardless of whether the model is parametric or learned, with reported degradation ranging from a few tenths of a decibel near a boundary to a documented 2.5-fold residual increase in a geometry absent from training data. The article’s contribution is a reframing of the field’s static-versus-predictive dichotomy around a single operative variable, calibration completeness relative to deployment geometry, supported by a comparative table of boundary conditions and a figure quantifying the error-distance relationship across independent studies.
Downloads
References
3rd Generation Partnership Project. (2017). Study on channel model for frequencies from 0.5 to 100 GHz (3GPP TR 38.901, Version 14.0.0, Release 14). ETSI.
Abedeen, Z., Ekpo, S., Ijaz, M., Raza, U., Alabi, S., & Han, L. (2024). Path loss prediction of 5G in the 24.25-27.5 GHz band based on machine learning. In S. C. Ekpo (Ed.), The Second International Adaptive and Sustainable Science, Engineering and Technology Conference (ASSET 2023) (pp. 19-28). Springer. https://doi.org/10.1007/978-3-031-53935-0_3
Akdeniz, M. R., Liu, Y., Samimi, M. K., Sun, S., Rangan, S., Rappaport, T. S., & Erkip, E. (2014). Millimeter wave channel modeling and cellular capacity evaluation. IEEE Journal on Selected Areas in Communications, 32(6), 1164-1179. https://doi.org/10.1109/JSAC.2014.2328154
Ben Ameur, M., Chebil, J., Habaebi, M. H., & Tahar, J. B. H. (2025). Machine learning for improved path loss prediction in urban vehicle-to-infrastructure communication systems. Frontiers in Artificial Intelligence, 8, Article 1597981. https://doi.org/10.3389/frai.2025.1597981
Ethier, J., & Châteauvert, M. (2024). Machine learning-based path loss modeling with simplified features. IEEE Antennas and Wireless Propagation Letters, 23(11), 3997-4001. https://doi.org/10.1109/LAWP.2024.3388253
Hata, M. (1980). Empirical formula for propagation loss in land mobile radio services. IEEE Transactions on Vehicular Technology, 29(3), 317-325. https://doi.org/10.1109/T-VT.1980.23859
Hervis Santana, Y., Martinez Alonso, R., Guillen Nieto, G., Martens, L., Joseph, W., & Plets, D. (2024). 5G mmWave network planning using machine learning for path loss estimation. IEEE Open Journal of the Communications Society, 5, 3451-3467. https://doi.org/10.1109/OJCOMS.2024.3405742
Kozak, A. A. (2026a). Static propagation model limitations as a root cause of coverage planning failures in dense urban 5G deployments. Austrian Journal of Technical and Natural Sciences, (5-6), 165-170. https://doi.org/10.29013/AJT-26-5.6-165-170
Kozak, A. A. (2026b). Predictive modeling and optimization of radio coverage in next-generation mobile networks. Universum: Technical Sciences, (5), Article 22766. https://doi.org/10.32743/UniTech.2026.146.5.22766
MacCartney, G. R., Rappaport, T. S., Sun, S., & Deng, S. (2015). Indoor office wideband millimeter-wave propagation measurements and channel models at 28 and 73 GHz for ultra-dense 5G wireless networks. IEEE Access, 3, 2388-2424. https://doi.org/10.1109/ACCESS.2015.2486778
Mlinar, T., Podgrajšek, U., & Batagelj, B. (2023). Comparison of coverage-prediction models for modern mobile radio networks. Electronics, 12(22), 4554. https://doi.org/10.3390/electronics12224554
Moraitis, N., Tsipi, L., & Vouyioukas, D. (2020). Machine learning-based methods for path loss prediction in urban environment for LTE networks. In 2020 16th International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob) (pp. 1-6). IEEE. https://doi.org/10.1109/WiMob50308.2020.9253369
Oladimeji, T. T., Kumar, P., & Oyie, N. O. (2022). Propagation path loss prediction modelling in enclosed environments for 5G networks: A review. Heliyon, 8(11), Article e11581. https://doi.org/10.1016/j.heliyon.2022.e11581
Poddar, H., Yoshimura, T., & Ishii, A. (2025). Validation of 3GPP TR 38.901 indoor hotspot path loss model based on measurements conducted at 6.75, 16.95, 28, and 73 GHz for 6G and beyond. In 2025 IEEE 101st Vehicular Technology Conference (VTC2025-Spring) (pp. 1-6). IEEE. https://doi.org/10.1109/VTC2025-Spring65109.2025.11174821
Rafie, I. F. M., Lim, S. Y., & Chung, M. J. H. (2023). Path loss prediction in urban areas: A machine learning approach. IEEE Antennas and Wireless Propagation Letters, 22(4), 809-813. https://doi.org/10.1109/LAWP.2022.3225792
Rappaport, T. S., MacCartney, G. R., Samimi, M. K., & Sun, S. (2015). Wideband millimeter-wave propagation measurements and channel models for future wireless communication system design. IEEE Transactions on Communications, 63(9), 3029-3056. https://doi.org/10.1109/TCOMM.2015.2434384
Seretis, A., & Sarris, C. D. (2022). An overview of machine learning techniques for radiowave propagation modeling. IEEE Transactions on Antennas and Propagation, 70(6), 3970-3985. https://doi.org/10.1109/TAP.2021.3098616
Shaibu, F. E., Onwuka, E. N., Salawu, N., Oyewobi, S. S., Djouani, K., & Abu-Mahfouz, A. M. (2023). Performance of path loss models over mid-band and high-band channels for 5G communication networks: A review. Future Internet, 15(11), Article 362. https://doi.org/10.3390/fi15110362
Sun, S., Rappaport, T. S., Thomas, T. A., Ghosh, A., Nguyen, H. C., Kovacs, I. Z., Rodriguez, I., Koymen, O., & Partyka, A. (2016). Investigation of prediction accuracy, sensitivity, and parameter stability of large-scale propagation path loss models for 5G wireless communications. IEEE Transactions on Vehicular Technology, 65(5), 2843-2860. https://doi.org/10.1109/TVT.2016.2543139
Vasudevan, M., & Yuksel, M. (2024). Machine learning for radio propagation modeling: A comprehensive survey. IEEE Open Journal of the Communications Society, 5, 5123-5153. https://doi.org/10.1109/OJCOMS.2024.3446457
Xu, T., Xu, N., Gao, J., Zhou, Y., & Ma, H. (2025). Path loss prediction model of 5G signal based on fusing data and XGBoost-SHAP method. Sensors, 25(17), Article 5440. https://doi.org/10.3390/s25175440
Zeng, S., Ji, Y., Chen, W., Yan, L., & Zhao, X. (2024). Mobile network coverage prediction using multi-modal model based on deep neural networks and semantic segmentation. Sensors, 24(16), Article 5178. https://doi.org/10.3390/s24165178
Zhang, Y., Wen, J., Yang, G., He, Z., & Wang, J. (2019). Path loss prediction based on machine learning: Principle, method, and data expansion. Applied Sciences, 9(9), Article 1908. https://doi.org/10.3390/app9091908
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Svetlana Igorevna Polyakova
This work is licensed under a Creative Commons Attribution 4.0 International License.
