volume | PIER Journals

Abstract

The microphysical structure of rain has a significant impact on the quality of radio signal transmission in the upcoming deployment of 5G millimetre-wave wireless communications in South Africa. To address this, mitigation techniques that integrate rain attenuation prediction models into network management systems are essential. This study uses a machine learning technique, symbolic regression coupled with differential evolution, to predict the rain attenuation in urban and rural 5G scenarios. Symbolic regression derives the mathematical models characterizing the attenuation, while differential evolution optimizes the model coefficients. The models' accuracies are validated through predictive performance metrics, including Mean Absolute Error (MAE) and Mean Squared Error (MSE). The urban model showed excellent accuracy, and the rural model improved significantly after optimization. The interpretability of the models provides valuable insights into rain-induced attenuation and supports better design and optimization of 5G mmWave communication systems.

1. Rangan, Sundeep, Theodore S. Rappaport, and Elza Erkip, "Millimeter-wave cellular wireless networks: Potentials and challenges," Proceedings of the IEEE, Vol. 102, No. 3, 366-385, 2014.

2. Andrews, Jeffrey G., Stefano Buzzi, Wan Choi, Stephen V. Hanly, Angel Lozano, Anthony C. K. Soong, and Jianzhong Charlie Zhang, "What will 5G be?," IEEE Journal on Selected Areas in Communications, Vol. 32, No. 6, 1065-1082, 2014.
doi:The server didn't respond in time.

3. Shamsan, Zaid Ahmed, "Rainfall and diffraction modeling for millimeter-wave wireless fixed systems," IEEE Access, Vol. 8, 212961-212978, 2020.

4. Narekar, Neha P. and Dipashree M. Bhalerao, "A survey on obstacles for 5G communication," 2015 International Conference on Communications and Signal Processing (ICCSP), 0831-0835, Melmaruvathur, India, Apr. 2015.

5. Bogale, Tadilo Endeshaw and Long Bao Le, "Massive MIMO and mmWave for 5G wireless HetNet: Potential benefits and challenges," IEEE Vehicular Technology Magazine, Vol. 11, No. 1, 64-75, 2016.

6. Dahlman, E., S. Parkvall, and J. Skold, 5G NR: The Next Generation Wireless Access Technology, Academic Press, 2020.

7. Frenzel, L., "Millimeter waves will expand the wireless future," Electronic Design, No. 04, 30-36, 2013.

8. Huang, Jie, Yusheng Cao, Xavier Raimundo, Adnan Cheema, and Sana Salous, "Rain statistics investigation and rain attenuation modeling for millimeter wave short-range fixed links," IEEE Access, Vol. 7, 156110-156120, 2019.

9. Shayea, Ibraheem, Tharek Abd. Rahman, Marwan Hadri Azmi, and Md. Rafiqul Islam, "Real measurement study for rain rate and rain attenuation conducted over 26 GHz microwave 5G link system in Malaysia," IEEE Access, Vol. 6, 19044-19064, 2018.

10. Diba, Feyisa Debo, Md. Abdus Samad, and Dong-You Choi, "The effects of rain on terrestrial links at K, Ka and E-bands in South Korea: Based on supervised learning," IEEE Access, Vol. 9, 9345-9355, 2021.

11. Sandberg, L., Astrophysicists Show How to “Weigh” Galaxy Clusters with Artificial Intelligence, Institute for Advanced Study, Princeton, NJ, USA, 2023.

12. Kim, Samuel, Peter Y. Lu, Srijon Mukherjee, Michael Gilbert, Li Jing;, Vladimir Čeperić, and Marin Soljačić, "Integration of neural network-based symbolic regression in deep learning for scientific discovery," IEEE Transactions on Neural Networks and Learning Systems, Vol. 32, No. 9, 4166-4177, 2020.

13. Makke, Nour and Sanjay Chawla, "Interpretable scientific discovery with symbolic regression: A review," Artificial Intelligence Review, Vol. 57, No. 1, 2, 2024.

14. Koza, J. R., Genetic programming II, MIT Press, Cambridge, 1994.

15. Storn, Rainer and Kenneth Price, "Differential evolution-a simple and efficient heuristic for global optimization over continuous spaces," Journal of Global Optimization, Vol. 11, 341-359, 1997.

16. Das, Swagatam and Ponnuthurai Nagaratnam Suganthan, "Differential evolution: A survey of the state-of-the-art," IEEE Transactions on Evolutionary Computation, Vol. 15, No. 1, 4-31, 2010.

17. Moupfouma, F., "Improvement of a rain attenuation prediction method for terrestrial microwave links," IEEE Transactions on Antennas and Propagation, Vol. 32, No. 12, 1368-1372, 1984.

18. Ananya, Sharmin Tajria, Md. S. Islam, Md. A. R. Mahmud, Pallab Kanti Podder, and Md. J. Uddin, "Atmospheric propagation impairment effects for wireless communications," International Journal of Wireless & Mobile Networks (IJWMN), Vol. 12, No. 3, 45-61, 2020.

19. Barclay, L. W., Propagation of Radiowaves, Vol. 502, IET, 2003.

20. Das, Saurabh, Animesh Maitra, and Ashish Kumar Shukla, "Rain attenuation modeling in the 10-100 GHz frequency using drop size distributions for different climatic zones in tropical India," Progress In Electromagnetics Research B, Vol. 25, 211-224, 2010.

21. Nagaraj, Pavithra, "Impact of atmospheric impairments on mmwave based outdoor communication," ArXiv Preprint ArXiv:1806.05176, 2018.

22. Afullo, Thomas Joachim Odhiambo, "Raindrop size distribution modeling for radio link design along the eastern coast of South Africa," Progress In Electromagnetics Research B, Vol. 34, 345-366, 2011.

23. 3GPP, , 3rd Generation Partnership Project Technical Specification Group Radio Access Network Study on channel model for frequencies from 0.5 to 100 GHz (Release 18), in TR38.9012024, Vol. 98, 2024.

24. Alencar, G. A., L. P. Caloba, and M. S. Assis, "Artificial neural networks as rain attenuation predictors in earth-space paths," Proceedings of the 2003 International Symposium on Circuits and Systems, 2003. ISCAS '03., Vol. 5, V-V, Bangkok, Thailand, May 2003.

25. Domb, Menachem and Guy Leshem, "Rain Attenuation Prediction for 2.4-72GHz using LTSM, an artificial recurrent neural network technology," 2021 International Conference on Electrical, Communication, and Computer Engineering (ICECCE), 1-6, Kuala Lumpur, Malaysia, Jun. 2021.

26. Ahuna, M. N., T. J. Afullo, and A. A. Alonge, "Rain attenuation prediction using artificial neural network for dynamic rain fade mitigation," SAIEE Africa Research Journal, Vol. 110, No. 1, 11-18, 2019.

27. Rao, Divya, Dalia Nandi, Fernando Pérez-Fontán, Vicente Pastoriza, and Fernando Machado, "Long term prediction of rain rate and attenuation using ANN and RNN algorithms," 2021 IEEE International India Geoscience and Remote Sensing Symposium (InGARSS), 230-233, Ahmedabad, India, Dec. 2021.

28. Sedki, A., D. Ouazar, and E. El Mazoudi, "Evolving neural network using real coded genetic algorithm for daily rainfall-runoff forecasting," Expert Systems with Applications, Vol. 36, No. 3, 4523-4527, 2009.

29. He, Yuanzhi, Biao Sheng, and Zhiqiang Li, "Channel modeling based on transformer symbolic regression for inter-satellite terahertz communication," Applied Sciences, Vol. 14, No. 7, 2929, 2024.

30. Matondo, Sandra Bazebo and Pius Adewale Owolawi, "Impact of rain attenuation on short-range frequency operations in 5G networks," 2024 25th International Microwave and Radar Conference (MIKON), 80-85, Wroclaw, Poland, Jul. 2024.

31. Rezaei, Hossein, Panam Zarfam, Emadaldin Mohammadi Golafshani, and Gholamreza Ghodrati Amiri, "Development of seismic demand prediction models for bridges based on probability approach using symbolic regression method," Computers & Structures, Vol. 282, 106991, 2023.

32. Loftis, Christian, Kunpeng Yuan, Yong Zhao, Ming Hu, and Jianjun Hu, "Lattice thermal conductivity prediction using symbolic regression and machine learning," The Journal of Physical Chemistry A, Vol. 125, No. 1, 435-450, 2020.

33. Kolody, Ana-Helena, Evgeniya Kabliman, Johannes Kronsteiner, Gabriel Kronberger, and Michael Kommenda, "Prediction of stress-strain curves for aluminium alloys using symbolic regression," ESAFORM Magazine, 2019.

34. Such, Felipe Petroski, Vashisht Madhavan, Edoardo Conti, Joel Lehman, Kenneth O. Stanley, and Jeff Clune, "Deep neuroevolution: Genetic algorithms are a competitive alternative for training deep neural networks for reinforcement learning," ArXiv Preprint ArXiv:1712.06567, 2017.

35. Galván, Edgar and Peter Mooney, "Neuroevolution in deep neural networks: Current trends and future challenges," IEEE Transactions on Artificial Intelligence, Vol. 2, No. 6, 476-493, 2021.

36. Baioletti, M., G. Di Bari, V. Poggioni, and M. Tracolli, "Differential evolution for learning large neural networks," 2018.

37. Wang, Bin, Yanan Sun, Bing Xue, and Mengjie Zhang, "A hybrid differential evolution approach to designing deep convolutional neural networks for image classification," AI 2018: Advances in Artificial Intelligence: 31st Australasian Joint Conference, Wellington, New Zealand, December 11-14, 2018, Proceedings 31, 237-250, 2018.

38. Vapnik, Vladimir, "Principles of risk minimization for learning theory," Advances in Neural Information Processing Systems, Vol. 4, 1991.

39. Golberg, David E., "Genetic algorithms in search, optimization, and machine learning. addion wesley," Reading, Vol. 673, 3, 1989.

40. Crane, R. K., Electromagnetic Wave Propagation through Rain, Wiley, 1996.

Ms. Sandra Bazebo Matondo

Dr. Pius Adewale Owolawi