Analysis of NWDAF Functionality in 5G Core Using a Dataset

• Leonardo Azalim de Oliveira UFJF
• Rodrigo Oliveira Silva UFJF
• Pedro Campos Lima UFJF
• Antônio Marcos Souza Pereira UFJF
• Júlia Almeida Valadares UFJF
• Edelberto Franco Silva UFJF
• Mário Antônio Ribeiro Dantas UFJF

DOI: https://doi.org/10.5753/sbrc.2024.1474

Abstract

The 5G technology is an evolution of the mobile networks due to the service-oriented paradigm that allows greater flexibility in management and the potential application of data analysis. The 3GPP defines the NWDAF as the network function responsible for data analysis in 5G, however, the literature still lacks works on this function. In order to fill this gap, this paper investigates the NWDAF using a dataset from a simulated 5G network and employing machine learning models as network protocol classifiers. The results have an accuracy of approximately 75%, providing not only reproducibility but also paving the way for future investigations in data analysis as specified by the 3GPP.

References

3GPP (2022). 3GPP TS 23.288 version 17.4.0 Release 17. Technical report, 3rd Generation Partnership Project.

3GPP (2023). 3GPP TS 29.520 version 17.11.0 Release 17. Technical report, 3rd Generation Partnership Project.

Breiman, L. (1996). Bagging predictors. Machine learning, 24(2):123–140.

Coronado, E., Behravesh, R., Subramanya, T., Fernàndez-Fernàndez, A., Siddiqui, M. S., Costa-Pérez, X., and Riggio, R. (2022). Zero touch management: A survey of network automation solutions for 5g and 6g networks. IEEE Communications Surveys & Tutorials, 24(4):2535–2578.

de Oliveira, L. A. and Silva, E. F. (2023). Estudo e Avaliação de Métodos de Autenticação EAP na Infraestrutura de Redes de Telecomunicação 5G. In Anais do Simpósio Brasileiro em Segurança da Informação e de Sistemas Computacionais (SBSeg). SBC.

Duan, Q. (2021). Intelligent and Autonomous Management in Cloud-Native Future Networks. Future Internet, 13(2):42.

free5GC et al. (2020). free5GC: Open source 5G core network base on 3GPP R15. [Online]. Disponível em: [link].

Güngör, A. et al. (2021). UERANSIM: Open source 5G UE and RAN (gNodeB) implementation. [Online]. Disponível em: [link].

Kim, T., Kim, J., Ko, H., Seo, S., Jcon, Y., Jeong, H., Lee, S., and Pack, S. (2022). An implementation study of network data analytic function in 5g. In 2022 IEEE International Conference on Consumer Electronics (ICCE), page 1–3. IEEE.

Pal, S. K. and Mitra, S. (1992). Multilayer perceptron, fuzzy sets, classifiaction.

Pateromichelakis, E., Moggio, F., Mannweiler, C., Arnold, P., Shariat, M., Einhaus, M., Wei, Q., Bulakci, O., and De Domenico, A. (2019). End-to-end data analytics framework for 5g architecture. IEEE Access, 7:40295–40312.

Pell, R., Moschoyiannis, S., and Shojafar, M. (2023). Machine Learning Driven Secure Access Control for 5g Core Networks. SSRN.

Safavian, S. R. and Landgrebe, D. (1991). A survey of decision tree classifier methodology. IEEE transactions on systems, man, and cybernetics, 21(3):660–674.

Storn, R. and Price, K. (1997). Differential Evolution – A Simple and Efficient Heuristic for global Optimization over Continuous Spaces. Journal of Global Optimization, 11(4):341–359.