A.A. Korobkov1, A.K. Gaysin2, A.F. Nadeev3, I.A. Safiullin4, I.P. Ashaev5

1–5 Kazan National Research Technical University named after A.N. Tupolev – KAI (Kazan, Russia)

1 aakorobkov@kai.ru, 2 akgaysin@kai.ru, 3 afnadeev@kai.ru, 4 iasafiullin@kai.ru, 5 ipashaev@kai.ru

Modern networks are heterogeneous and are based on the principles of open networks. This provides new opportunities for improving the performance of these networks. The new approach to managing handover, using the results of a complex estimation of mobile user trajectory and speed, is proposed in this paper. To this end, classification based on standard parameters such as received signal power and SINR (Signal-to-Interference-plus-Noise Ratio) can be used to classify user mobility patterns. Two classifiers are considered in this paper: Naïve Bayes Classifier and Full Bayes Classifier. Both are trained on data generated using a developed model of an O-RAN network, with two scenarios involving mobile users moving. The simulation results indicate that the classification based on received signal power provides better results than using SINR. Additionally, both classifiers showed similar results for the considered scenarios.

Korobkov A.A., Gaysin A.K., Nadeev A.F., Safiullin I.A., Ashaev I.P. Investigation of the classification methods for user mobility patterns in O-RAN. Electromagnetic waves and electronic systems. 2025. V. 30. № 5. P. 40−60. DOI: https://doi.org/10.18127/ j15604128-202505-04 (in Russian)

1. Korobkov A.A., Safiullin I.A., Ashaev I.P., Gaysin A.K., Nadeev A.F. Model order estimation method for user mobility classificationin heterogeneous RAN systems. Radiotekhnika. 2024. V. 88. № 1. P. 44−58. DOI 10.18127/j00338486-202401-05 (in Russian)
2. Gaysin A.K., Korobkov A.A., Safiullin I.A., Ashaev I.P., Nadeev A.F. Investigation of the dependence of the multi-linear model parameters on the user mobility pattern in O-RAN in the context of user groups classification. Electromagnetic waves and electronic systems. 2024. V. 29. № 4. P. 6−22. DOI 10.18127/j15604128-202404-02 (in Russian)
3. Spirina E.A., Kozlov S.V., Bukharina A.A. Traffic model in heterogeneous networks based on experimental data. Radiotekhnika. 2024. V. 88. № 1. P. 92−110. DOI 10.18127/j00338486-202401-09 (in Russian)
4. Lerner I.M., Fayzullin R.R., Ryabov I.V. High performance algorithm for capacity estimation of communication channels functioning on the basis of resolution time theory. Radiotekhnika. 2022. V. 86. № 4. P. 91–109. DOI 10.18127/j00338486-202204-13. (in Russian)
5. 3GPP TS 32.500 V17.0.0 (2022-04). 3rd Generation Partnership Project; Technical Specification Group Services and System Aspects; Telecommunication Management; Self-Organizing Networks (SON); Concepts and requirements (Release 17). [Electronic resource] – Access mode: https://www.3gpp.org/ftp/Specs/archive/32_series/32.500/32500-h00.zip, date of reference 03.06.2025.
6. 3GPP TS 23.501 V17.11.0 (2023-12). 3rd Generation Partnership Project; Technical Specification Group Services and System Aspects; System architecture for the 5G System (5GS); Stage 2 (Release 17). [Electronic resource] – Access mode: https://www.3gpp.org/ftp/Specs/archive/23_series/23.501/23501-hb0.zip, date of reference 03.06.2025.
7. O-RAN ALLIANCE. O-RAN.WG1.O-RAN-Architecture-Description. Version 07.00. [Electronic resource] – Access mode: https://www.o-ran.org/specifications, date of reference 03.06.2025.
8. Orhan O., Swamy V.N., Tetzlaff T., Nassar M., Nikopour H., Talwar S. Connection Management xAPP for O-RAN RIC: A Graph Neural Network and Reinforcement Learning Approach. [Electronic resource] – Access mode: https://arxiv.org/pdf/2110.07525, date of reference 03.06.2025.
9. Zhang Y., Lee H., Kim J. et al. RAN Intelligent Controller (RIC): From open-source implementation to real-world validation. ICT Express. 2024. V. 10. № 3. P. 680–691. DOI 10.1016/j.icte.2024.02.001.
10. Koufos K., EI Haloui K., Dianati M., Higgins M., Elmirghani Ja., Imran M.A., Tafazolli R. Trends in Intelligent Communication Systems: Review of Standards, Major Research Projects, and Identification of Research Gaps. Journal of Sensor and Actuator Networks. 2021. V. 10. №. 4. P. 60. DOI 10.3390/jsan10040060.
11. Prananto B.H., Iskandar, Kurniawan A. A New Method to Improve Frequent-Handover Problem in High-Mobility Communications Using RIC and Machine Learning. IEEE Access. 2023. V. 11. P. 72281–72294. DOI 10.1109/access.2023.3294990.
12. Dzaferagic M., Missi Xavier B., Collins D., D'Onofrio V., Martinello M., Ruffini M. ML-Based Handover Prediction Over a Real O-RAN Deployment Using RAN Intelligent Controller. IEEE Transactions on Network and Service Management. 2025. V. 22. № 1. P. 635–647. DOI 10.1109/TNSM.2024.3468910.
13. Meer I.A., Hörmann B., Ozger M., Geyer F., Viseras A., Schupke D., Cavdar C. Explainable AI for UAV Mobility Management: A Deep Q-Network Approach for Handover Minimization. [Electronic resource] – Access mode: https://arxiv.org/pdf/2504.18371, date of reference 03.06.2025.
14. 3GPP TS 36.214 V15.2.0 (2018-06). 3rd Generation Partnership Project; Technical Specification Group Radio Access Network; Evolved Universal Terrestrial Radio Access (E-UTRA); Physical layer; Measurements (Release 15). [Electronic resource] – Access mode: https://www.3gpp.org/ftp//Specs/archive/36_series/36.214/36214-f20.zip, date of reference 03.06.2025.
15. Ashaev I.P., Safiullin I.A., Gaysin A.K., Nadeev A.F., Korobkov A.A. An Approach for Using a Tensor-Based Method for Mobility-User Pattern Determining. Inventions. 2024. V. 9. № 1. P. 1. DOI 10.3390/inventions9010001.
16. Christopher M.B. Pattern Recognition and Machine Learning. New York: Springer. 2006. 778 p.
17. 3GPP TS 36.133 V15.13.0 (2021-03). 3rd Generation Partnership Project; Technical Specification Group Radio Access Network; Evolved Universal Terrestrial Radio Access (E-UTRA); Requirements for support of radio resource management (Release 15). [Electronic resource] – Access mode: https://www.3gpp.org/ftp/Specs/archive/36_series/36.133/36133-fd0.zip, date of reference 03.06.2025.