Predictive Handover Management in 5G/4G Dual Connectivity: B1 Event Optimization Using the K-Nearest Neighbors Algorithm

Alison M. Fernandes; Hermes I. Del Monego; Bruno S. Chang; Anelise Munaretto

doi:10.5753/jbcs.2026.6875

Authors

Alison M. Fernandes Federal University of Technology – Paraná https://orcid.org/0009-0008-4760-0691
Hermes I. Del Monego Federal University of Technology – Paraná https://orcid.org/0000-0003-1296-7625
Bruno S. Chang Federal University of Technology – Paraná https://orcid.org/0000-0003-0232-7640
Anelise Munaretto Federal University of Technology – Paraná https://orcid.org/0000-0002-0182-7128

DOI:

https://doi.org/10.5753/jbcs.2026.6875

Keywords:

Handover, Machine Learning, K-Nearest Neighbors, KNN, Dual Connectivity, OMNET, Simu5G, User Equipment, 5G Network, 4G Network

Abstract

The constant development of wireless network communications is transforming modern society and bringing new forms of interactivity. The New Radio (5G/NR) network enables unprecedented interactivity, combining a high transfer rate with a significant increase in the coverage area. However, some legacy technologies still persist in our daily lives, such as Long Term Evolution (4G/LTE). This study considers a Dual Connectivity urban scenario between 5G/NR and 4G/LTE, with criteria such as Received Signal Strength Indicator (RSSI), Reference Signal Received Power (RSRP), distance, and Signal-to-Interference-plus-Noise Ratio (SINR) for handover prediction using the K-Nearest Neighbor (KNN) machine learning algorithm. The main goal of this work is to reduce the number of handovers in both 5G and 4G networks using the KNN algorithm. The deployment of this algorithm resulted in a significant reduction in the number of handovers in 5G networks, by approximately 67.32%, and in 4G networks, by about 19.40%, in scenarios involving Dual Connectivity. Another favorable aspect was its computational cost. Even when compared to other machine learning categories, such as reinforcement learning.

Downloads

Download data is not yet available.

References

GPP (2008). 3GPP Release 8 — Technical Specification Group Services and System Aspects. Available at: [link] Accessed: 2024-01-01.

GPP (2019). 3GPP Release 15 — Technical Specification Group Services and System Aspects. Available at: [link] Accessed: 2024-01-01.

GPP (2020). 3GPP Release 16 — Specifications. Available at: [link] Accessed: 2024-06-08.

GPP (2017). 3GPP Report12 - Technical Specification Group Services and System Aspects. Available at: [link] Accessed: 2024-07-01.

Adhikary, S. (2023). Introduction to distributed nearest hash: On further optimizing cloud based distributed knn variant. Procedia Computer Science, 218:1571-1580. DOI: 10.1016/j.procs.2023.01.135.

Agiwal, M., Kwon, H., Park, S., and Jin, H. (2021). A survey on 4g-5g dual connectivity: Road to 5g implementation. IEEE Access, 9:16193-16210. DOI: 10.1109/ACCESS.2021.3052462.

Dahlman, E., Parkvall, S., and Sköld, J. (2016). 4G, LTE-Advanced Pro and The Road to 5G. Academic Press, Amsterdam, The Netherlands. Book.

Gannapathy, V. R., Nordin, R., Abu-Samah, A., Abdullah, N. F., and Ismail, M. (2023). An adaptive ttt handover (ath) mechanism for dual connectivity (5g mmwave—lte advanced) during unpredictable wireless channel behavior. Sensors, 23(9). DOI: 10.3390/s23094357.

Goswami, M., Jacob, R., and Pagh, R. (2020). On the i/o complexity of the k-nearest neighbor problem. Available at: [link].

He, R., Hu, B.-G., Zheng, W.-S., and Kong, X.-W. (2011). Robust principal component analysis based on maximum correntropy criterion. IEEE Transactions on Image Processing, 20(6):1485-1494. DOI: 10.1109/TIP.2010.2103949.

Junejo, Y. S., Shaikh, F. K., Chowdhry, B. S., and Ejaz, W. (2025). Adaptive handover management in high-mobility networks for smart cities. Computers, 14(1). DOI: 10.3390/computers14010023.

Kolodiazhnyi, K. (2020). Hands-On Machine Learning with C++: Build, train, and deploy end-to-end machine learning and deep learning pipelines. Packt Publishing, Birmingham, UK. Available at: [link].

Mumtaz, T., Muhammad, S., Aslam, M. I., and Mohammad, N. (2020). Dual connectivity-based mobility management and data split mechanism in 4g/5g cellular networks. IEEE Access, 8:86495-86509. DOI: 10.1109/ACCESS.2020.2992805.

Nardini, G., Sabella, D., Stea, G., Thakkar, P., and Virdis, A. (2020). Simu5g–an omnet++ library for end-to-end performance evaluation of 5g networks. IEEE Access, 8:181176-181191. DOI: 10.1109/ACCESS.2020.3028550.

Salau, N. O. and Zeeshan Shakir, M. (2023). Machine learning analysis of multi-radio access technology selection in 5g nsa network. In 2023 IEEE Wireless Communications and Networking Conference (WCNC), pages 1-6. DOI: 10.1109/WCNC55385.2023.10118884.

Shiwei, G. (2021). An improved knn based decision algorithm for vertical handover in heterogeneous wireless networks. In 2021 40th Chinese Control Conference (CCC), pages 3011-3016. DOI: 10.23919/CCC52363.2021.9550412.

Taunk, K., De, S., Verma, S., and Swetapadma, A. (2019). A brief review of nearest neighbor algorithm for learning and classification. In 2019 International Conference on Intelligent Computing and Control Systems (ICCS), pages 1255-1260. DOI: 10.1109/ICCS45141.2019.9065747.

Yan, L., Ding, H., Zhang, L., Liu, J., Fang, X., Fang, Y., Xiao, M., and Huang, X. (2019). Machine learning-based handovers for sub-6 ghz and mmwave integrated vehicular networks. IEEE Transactions on Wireless Communications, 18(10):4873-4885. DOI: 10.1109/TWC.2019.2930193.

Yang, Y., Deng, X., He, D., You, Y., and Song, R. (2019). Machine learning inspired codeword selection for dual connectivity in 5g user-centric ultra-dense networks. IEEE Transactions on Vehicular Technology, 68(8):8284-8288. DOI: 10.1109/TVT.2019.2923314.

Zinno, S., Affinito, A., Pasquino, N., Ventre, G., and Botta, A. (2023). Prediction of rtt through radio-layer parameters in 4g/5g dual-connectivity mobile networks. In 2023 IEEE Symposium on Computers and Communications (ISCC), pages 213-218. DOI: 10.1109/ISCC58397.2023.10218091.