Sustainable Energy and Artificial Intelligence

Distance-Aware Machine Learning Approach for Data Rate Prediction in Cellular Networks

Document Type : Original Article

Authors

Pouya Deabae 1
Siavash Rajabi 2
Reza Shahbazian 3

1 Department of Electrical and Computer Engineering, University of Guilan, Rasht, Iran

2 Department of Electrical Engineering, Hamedan University of Technology, Hamedan, Iran.

3 Department of humanities, University of Palermo, Italy

https://doi.org/10.66224/seai.2508-1034
Abstract
Accurate estimation of cellular network throughput is essential for effective network management and user experience optimization. This study conducts a comprehensive comparative analysis of four prominent machine learning (ML) models (i.e., Random Forest Regressor (RFR), Gaussian Process Regressor (GPR), K-Nearest Neighbors (KNN), and Support Vector Regressor) for predicting downlink and uplink data rates based exclusively on the user-base station distance. Evaluation metrics, including coefficient of determination (R2 score), Mean Squared Error (MSE), Mean Absolute Error (MAE), and computational runtime, were employed to assess model performance. Results indicate that ensemble-based (RFR) and probabilistic kernel-based (GPR) approaches outperform instance-based (KNN) and margin-based (SVR) methods in terms of predictive accuracy and error minimization. Furthermore, RFR achieves a favorable balance between accuracy and computational efficiency, making it a practical choice for real-time throughput prediction. Beyond performance estimation, the proposed approach offers potential benefits for energy optimization, enabling more efficient resource allocation both at the user device and base station (or network infrastructure) level. The findings suggest that incorporating additional network parameters and signal quality features could further improve model effectiveness in capturing the complex dynamics of cellular communications. This study employs a public real-world 4G LTE dataset comprising 135 traces (≈15 minutes each) collected under a static mobility model. The proposed distance-only prediction framework highlights that accurate throughput estimation can be achieved using a single distance feature, showing that lightweight models can remain competitive for real-time deployment.

Keywords

Random Forest Regressor
Gaussian Process Regressor
K-Nearest Neighbors
Support Vector Regressor
cellular networks
Subjects

  1. "A Survey on Energy Optimization Techniques in UAV-Based Cellular Networks: From Conventional to Machine Learning Approaches." Accessed: Aug. 12, 2025. [Online]. Available: https://www.mdpi.com/2504-446X/7/3/214

  2. Khaled, H., & Alkhazraji, E. (2024). AI optimization-based heterogeneous approach for green next-generation communication systems. Sensors, 24(15), 4956.

  3. Das, B. R., Hasan, S. R., Sabuj, S. R., Hossain, M. A., & Ray, S. K. (2025). A Comprehensive Survey on Emerging AI Technologies for 6G Communications: Research Direction, Trends, Challenges, and Opportunities. International Journal of Intelligent Networks.

  4. Andrews, J. G., Buzzi, S., Choi, W., Hanly, S. V., Lozano, A., Soong, A. C., & Zhang, J. C. (2014). What will 5G be?. IEEE Journal on selected areas in communications, 32(6), 1065-1082.

  5. Islam, M. Z., Ali, R., Haider, A., & Kim, H. S. (2022). QoS provisioning: key drivers and enablers toward the tactile internet in beyond 5G Era. IEEE Access, 10, 85720-85754.

  6. Coronado, E., Valero, V., Cambronero, M. E., & Orozco-Barbosa, L. (2023). Modelling, simulation and performance evaluation of the IEEE 802.11 e protocol with station mobility. PeerJ Computer Science, 9, e1457.

  7. Minovski, D., Ögren, N., Mitra, K., & Åhlund, C. (2021). Throughput prediction using machine learning in LTE and 5G networks. IEEE Transactions on Mobile Computing, 22(3), 1825-1840.

  8. Zhang, K., Wang, J., Zhang, W., Wang, K., Zeng, J., Fan, G., & Gui, G. (2019). Random forest algorithm-based lightweight comprehensive evaluation for wireless user perception. IEEE Access, 7, 173477-173484.

  9. Xu, Y., Yin, F., Xu, W., Lin, J., & Cui, S. (2019). Wireless traffic prediction with scalable Gaussian process: Framework, algorithms, and verification. IEEE Journal on Selected Areas in Communications, 37(6), 1291-1306.

  10. Costa, M., Ayanda, D., Sátiro, B., Mate, D., & Ortega, A. (2023, September). Throughput Slopes Prediction in 5G Networks with Gaussian Regression Process. In 2023 16th International Conference on Signal Processing and Communication System (ICSPCS) (pp. 1-5). IEEE.

  11. Tao, L., Bao, D., & Cui, Y. (2024, October). Optimization Analysis of Wireless Sensor Coverage Indoor Positioning Based on KWAP-KNN Algorithm. In 2024 First International Conference on Software, Systems and Information Technology (SSITCON) (pp. 1-5). IEEE.

  12. Shiwei, G. U. O. (2021, July). An improved KNN based decision algorithm for vertical handover in heterogeneous wireless networks. In 2021 40th Chinese Control Conference (CCC) (pp. 3011-3016). IEEE.

  13. Singh, S., Kumar, A., Kankane, B., & Mishra, R. (2025, January). Predicting K-Coverage in Wireless Multihop Networks with Boundary Effects Using Support Vector Regression: A Feature Sensitivity Analysis for Smart City Applications. In 2025 International Conference on Cognitive Computing in Engineering, Communications, Sciences and Biomedical Health Informatics (IC3ECSBHI) (pp. 1516-1521). IEEE.

  14. Kim, W., Park, J., Yoo, J., Kim, H. J., & Park, C. G. (2012). Target localization using ensemble support vector regression in wireless sensor networks. IEEE transactions on cybernetics, 43(4), 1189-1198.

  15. Selvamanju, E., & Shalini, V. B. (2022, October). Deep learning based mobile traffic flow prediction model in 5G cellular networks. In 2022 3rd International Conference on Smart Electronics and Communication (ICOSEC) (pp. 1349-1353). IEEE.

  16. Wongphatcharatham, T., Phakphisut, W., Jaruvitayakovit, T., Boonkajay, A., & Huang, J. (2024, October). Deep Learning Aided Robust RSRP Prediction in Cellular Networks. In 2024 IEEE 100th Vehicular Technology Conference (VTC2024-Fall) (pp. 1-5). IEEE.

  17. Alsuhli, G., Banawan, K., Attiah, K., Elezabi, A., Seddik, K. G., Gaber, A., ... & Gadallah, Y. (2021). Mobility load management in cellular networks: A deep reinforcement learning approach. IEEE Transactions on Mobile Computing, 22(3), 1581-1598.

  18. Lin, Y., Tong, Y., Zhong, Q., Gao, R., Yin, B., Liu, L., ... & Chai, H. (2021, December). Dccp: Deep convolutional neural networks for cellular network positioning. In 2021 IEEE Global Communications Conference (GLOBECOM) (pp. 1-6). IEEE.

  19. Wang, Z., & Wong, V. W. (2022, May). Cellular traffic prediction using deep convolutional neural network with attention mechanism. In ICC 2022-IEEE International Conference on Communications (pp. 2339-2344). IEEE.

  20. "4G LTE Speed Dataset and Bandwidth." Accessed: Aug. 12, 2025. [Online]. Available: https://www.kaggle.com/datasets/aeryss/lte-dataset

  21. Fauzi, M. F. A., Nordin, R., Abdullah, N. F., & Alobaidy, H. A. (2022). Mobile network coverage prediction based on supervised machine learning algorithms. Ieee Access, 10, 55782-55793.

  22. Jeske, M., Sansò, B., Aloise, D., & Nascimento, M. C. (2024). Received Signal Strength Indicator Prediction for Mesh Networks in a Real Urban Environment Using Machine Learning. IEEE Access.

  23. Azoulay, R., Edery, E., Haddad, Y., & Rozenblit, O. (2023). Machine learning techniques for received signal strength indicator prediction. Intelligent Data Analysis, 27(4), 1167-1184.

  24. "A machine learning approach to TCP throughput prediction | Proceedings of the 2007 ACM SIGMETRICS international conference on Measurement and modeling of computer systems," ACM Conferences. Accessed: Aug. 13, 2025. [Online]. Available: https://dl.acm.org/doi/10.1145/1254882.1254894

Sustainable Energy and Artificial Intelligence
Volume 2, Issue 1
Winter 2026
Pages 25-35

  • Receive Date 30 August 2025
  • Accept Date 24 November 2025
  • First Publish Date 24 November 2025

Home

Guide for Authors

Submit Manuscript

Reviewers

Contact Us