Online Approach for Proactive Scaling of Mobile Core Network Functions

• Abrahão Ferreira UFPA http://orcid.org/0009-0004-5832-1488
• Kauan Tavares UFPA https://orcid.org/0009-0006-1541-7783
• Douglas Vidal UFPA https://orcid.org/0009-0000-7039-0436
• Silvia Lins Erricson Research https://orcid.org/0000-0001-5160-7177
• Aldebaro Klautau UFPA http://orcid.org/0000-0001-7773-2080
• Cristiano Bonato UNISINOS https://orcid.org/0000-0002-9776-4888
• Glauco Gonçalves UFPA https://orcid.org/0000-0003-1341-5339

DOI: https://doi.org/10.5753/w6g.2025.8835

Resumo

New use cases for 6G networks introduce stringent requirements, like massive connectivity, which demand effective scaling of core functions. This is often achieved through scaling techniques that utilize machine learning models to proactively predict traffic demand. However, these models face challenges concerning concept drifts, i.e., changes in the statistical patterns previously learned by the model. To address this limitation, this study evaluates a method based on online learning for scheduling core functions. The method was tested using data from a mobile network, simulating scenarios with concept drift. The results demonstrate that the online model effectively adapts to changes, reducing prediction errors and maintaining stability in dynamic environments.

Palavras-chave: Proactive scaling, Core network, Online learning, 6G networks, Traffic prediction

Referências

Akshlley, K., Carvalho, M., and Lopes, R. (2022). Análise de desempenho de estratégias de autoscaling vertical e horizontal: um estudo de caso com o kubernetes. In Anais Estendidos do XL Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos, pages 201–208. SBC.

Alawe, I., Hadjadj-Aoul, Y., Ksentinit, A., Bertin, P., Viho, C., and Darche, D. (2018a). An efficient and lightweight load forecasting for proactive scaling in 5G mobile networks. In IEEE Conference on Standards for Communications and Networking.

Alawe, I., Ksentini, A., Hadjadj-Aoul, Y., and Bertin, P. (2018b). Improving traffic forecasting for 5G core network scalability: A machine learning approach. IEEE Network, 32(6):42–49.

Barlacchi, G., De Nadai, M., Larcher, R., Casella, A., Chitic, C., Torrisi, G., Antonelli, F., Vespignani, A., Pentland, A., and Lepri, B. (2015). A multi-source dataset of urban life in the city of Milan and the province of Trentino. Scientific Data, 2(1):1–15.

Bergstra, J., Yamins, D., and Cox, D. (2013). Making a science of model search: Hyperparameter optimization in hundreds of dimensions for vision architectures. In Dasgupta, S. and McAllester, D., editors, Proceedings of the 30th International Conference on Machine Learning, number 1, pages 115–123, Atlanta, Georgia, USA. PMLR.

Chouman, A., Manias, D. M., and Shami, A. (2023). A reliable AMF scaling and load balancing framework for 5G core networks. In 2023 International Wireless Communications and Mobile Computing (IWCMC), pages 252–257.

da Silva, T., Batista, T., Delicato, F., and Pires, P. (2024). An online ensemble method for auto-scaling NFV-based applications in the edge. Cluster Computing, pages 1–25.

DeAlmeida, J. M., Pontes, C. F. T., DaSilva, L. A., Both, C. B., Gondim, J. J. C., Ralha, C. G., and Marotta, M. A. (2021). Abnormal behavior detection based on traffic pattern categorization in mobile networks. IEEE Transactions on Network and Service Management, 18(4):4213–4224.

Hoi, S. C., Sahoo, D., Lu, J., and Zhao, P. (2021). Online learning: A comprehensive survey. Neurocomputing, 459:249–289.

Kuranage, M. P., Hanser, E., Nuaymi, L., Bouabdallah, A., Bertin, P., and Al-Dulaimi, A. (2023). AI-assisted proactive scaling solution for CNFs deployed in kubernetes. In 2023 IEEE 12th International Conference on Cloud Networking, pages 265–273.

Lu, L., Liu, C., Zhang, C., Hu, Z., Lin, S., Liu, Z., Zhang, M., Liu, X., and Chen, J. (2023). Architecture for self-evolution of 6G core network based on intelligent decision making. Electronics, 12(15).

Manias, D. M., Chouman, A., and Shami, A. (2023). Model drift in dynamic networks. IEEE Communications Magazine, 61(10):78–84.

Mourtada, J., Gaïffas, S., and Scornet, E. (2021). AMF: Aggregated Mondrian Forests for online learning. Journal of the Royal Statistical Society Series B: Statistical Methodology, 83(3):505–533.

Passas, V., Makris, N., Wang, Y., Apostolaras, A., Mpatziakas, A., Drosou, A., Korakis, T., and Tzovaras, D. (2022). Artificial intelligence for network function autoscaling in a cloud-native 5G network. Computers and Electrical Engineering, 103:108327.

Pérez-Sánchez, B., Fontenla-Romero, O., and Guijarro-Berdinãs, B. (2018). A review of adaptive online learning for artificial neural networks. Artificial Intelligence Review, 49:281–299.