Autors: Kumar V., Singh H., Bonev, B. G., Petkov, P. J., Saxena K., Manolova, A. H.
Title: Advanced Machine Learning Approach for Accurate Rain Attenuation Prediction in High-Frequency Wireless Networks
Keywords: Artificial Neural Network (ANN), Bagging Regressor, Machine learning, Rain attenuation

Abstract: The reliability of high-frequency wireless communication systems faces substantial impediments from rainfall-caused electromagnetic signal losses especially in relation to modern networking technologies including 5G and next-generation systems. Permanent predictive models such as ITU, Brazilian and RAL perform with different accuracies according to geographical and climatic zones yet none achieves optimal performance throughout all conditions. This research develops a generalized prediction model through a machine learning approach to fulfill the need for an improved solution. The use of weighted sums methods integrating traditional model outputs at 0.1, 0.5 and 0.4 weight values helped generate a realistic prediction for attenuation that represented balanced estimation results. The machine learning models used Bagging Regressor and Artificial Neural Network (ANN) to predict the unified target while processing physical and model-specific parameters.

References

  1. Kumar, V., Singh, H., Saxena, K., Bonev, B., Prasad, R. (2021, October). An ANN model for predicting radio wave attenuation due to rain and its business aspect. In 2021 29th national conference with international participation (TELECOM) (pp. 17-19). IEEE.
  2. Kumar, V., Singh, H., Saxena, K., Bonev, B., Prasad, R. (2023). A Deep Learning Based Model for Prediction of RF Wave Attenuation Due to Rain. Wireless Personal Communications, 131(2), 1437-1460.
  3. Amarjit, Gangwar, R. P. S. (2008). Implementation of artificial neural network for prediction of rain attenuation in microwave and millimeter wave frequencies. IETE Journal of research, 54(5), 346-352.
  4. Ahuna, M. N., Afullo, T. J., Alonge, A. A. (2019). Rain attenuation prediction using artificial neural network for dynamic rain fade mitigation. SAIEE Africa Research Journal, 110(1), 11-18.
  5. Singh, H., Kumar, V., Saxena, K., Kapse, V. M., Prasad, R. (2022). Radio wave attenuation due to clouds from traditional models to ML models-A state of art. Wireless Personal Communications, 125(4), 3287-3309.
  6. Ojo, J. S., Ijomah, C. K., Akinpelu, S. B. (2022). Artificial neural networks for earth-space link applications: A prediction approach and inter-comparison of rain-influenced attenuation models. Int. J. Intell. Syst. Appl. (IJISA), 14(5), 47-58.
  7. Mpoporo, L. J., Owolawi, P. A., Aiyetoro, G. R. (2025, February). Artificial Neural Networks for Prediction of Rain Attenuation on Ku-band in South Africa. In 8th URSI-NG Annual Conference (URSI-NG 2024) (pp. 232-244). Atlantis Press.

Issue

60th International Scientific Conference on Information, Communication and Energy Systems and Technologies, ICEST 2025 - Proceedings, 2025, Macedonia, https://doi.org/10.1109/ICEST66328.2025.11098361

Copyright The Institute of Electrical and Electronics Engineers

Цитирания (Citation/s):
1. Ashidi A.G., Adeola I.A., Synthetic storm technique and machine learning algorithms for rain attenuation characterization across selected locations in tropical Nigeria, 2026, International Journal of Environmental Science and Technology, issue 11, vol. 23, DOI 10.1007/s13762-026-07484-8, issn 17351472, eissn 17352630 - 2026 - в издания, индексирани в Scopus

Вид: публикация в международен форум, публикация в реферирано издание, индексирана в Scopus