Static Propagation Model Limitations as a Root Cause of Coverage Planning Failures in Dense Urban 5G Deployments
Authors
Kozak Andrey Aleksandrovich

Share
Annotation
Empirical path-loss models such as Okumura-Hata, calibrated for frequencies below 1500 MHz and base station heights above rooftop level, introduce systematic prediction biases exceeding 9 dB when applied to sub-6 GHz and millimeter-wave small cell deployments in dense urban environments. These biases propagate through the planning pipeline and produce site count overestimates of 65–80% relative to measurement-informed baselines. This paper presents a transfer-adaptive neural framework for 5G coverage planning that combines geospatially conditioned probabilistic propagation prediction, Pareto-weighted joint coverage-capacity deficit optimization, and closed-loop online adaptation with spatially varying regularization proportional to local measurement uncertainty. The framework was evaluated over a 180 km² urban region at 3.5 GHz using drive-test data from 800 km of road segments. Region-specific fine-tuning reduced mean absolute prediction error from 9.1 dB to 5.5 dB and decreased the required site count by 11–13% relative to non-adapted baselines, while compressing the planning cycle from 40–58 days to 14–22 days.
Keywords
Authors
Kozak Andrey Aleksandrovich

Share
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.
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
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
Rangan, S., Rappaport, T. S., & Erkip, E. (2014). Millimeter-wave cellular wireless networks: Potentials and challenges. Proceedings of the IEEE, 102(3), 366–385. https://doi.org/10.1109/JPROC.2014.2299397
Rappaport, T. S., Xing, Y., MacCartney, G. R., Molisch, A. F., Mellios, E., & Zhang, J. (2017). Overview of millimeter wave communications for fifth-generation (5G) wireless networks with a focus on propagation models. IEEE Transactions on Antennas and Propagation, 65(12), 6213–6230. https://doi.org/10.1109/TAP.2017.2734243
Sun, S., Rappaport, T. S., Rangan, S., Thomas, T. A., Ghosh, A., Kovacs, I. Z., Rodriguez, I., Koymen, O., Partyka, A., & Jarvelainen, J. (2016). Propagation path loss models for 5G urban micro- and macro-cellular scenarios. In Proceedings of the IEEE 83rd Vehicular Technology Conference (VTC Spring) (pp. 1–6). IEEE. https://doi.org/10.1109/VTCSpring.2016.7504435
Wang, C.-X., Bian, J., Sun, J., Zhang, W., & Zhang, M. (2018). A survey of 5G channel measurements and models. IEEE Communications Surveys and Tutorials, 20(4), 3142–3168. https://doi.org/10.1109/COMST.2018.2862141
