Evolved NWDAF Towards a Fully Distributed Artificial Intelligence in the 6G Network Architecture

• Natal Vieira de Souza Neto UFU
• Maurício Amaral Gonçalves UFU
• Daniel Ricardo Cunha Oliveira UFU
• Diego Nunes Molinos UFU
• Rodrigo Moreira UFU / UFV
• Flávio de Oliveira Silva UFU / University of Minho

DOI: https://doi.org/10.5753/w6g.2024.3378

Resumo

Artificial Intelligence (AI) is essential for evolving mobile networks towards 6G technology generation and beyond. In this context, the 3GPP has incorporated the Network Data Analytics Function (NWDAF) at the network’s core to leverage network data analytics, focusing on using analytics for automation. However, although NWDAF represents a significant advancement in this area, there is no consensus on deploying AI in the 6G network. This work suggests a framework for developing NWDAF that includes the necessary interfaces and behaviors to enhance the core network with AI capabilities Beyond 5G (B5G) and 6G networks. By analyzing existing literature, we identify a set of potential research directions and propose and suggest a hybrid approach to integrate AI across the entire network using a new distributed network function called Evolved Network Data Analytics Function (eNWDAF).

Referências

3GPP (2019a). 3rd Generation Partnership Project; Technical Specification Group Services and System Aspects; Architecture enhancements for 5G System (5GS) to support network data analytics services (Release 16). Technical Specification TS 23.288, ETSI, Sophia Antipolis.

3GPP (2019b). 5G; 5G System; Network Data Analytics Services; Stage 3 (3GPP TS 29.520 version 15.3.0 Release 15). Technical Specification TS 29.520, ETSI, Sophia Antipolis.

3GPP (2023). 3rd Generation Partnership Project; Technical Specification Group Services and System Aspects; Architecture enhancements for 5G System (5GS) to support network data analytics services (Release 18). Technical Specification 3GPP TS 23.288 V18.4.0, 3GPP, Sophia Antipolis.

Aarna Networks (2022). NWDAF Rel 17 Explained - Architecture, Features and Use Cases.

Abbas, K., Khan, T. A., Afaq, M., and Song, W.-C. (2022). Ensemble Learning-based Network Data Analytics for Network Slice Orchestration and Management: An Intent-Based Networking Mechanism. In NOMS 2022-2022 IEEE/IFIP Network Operations and Management Symposium, pages 1–5. ISSN: 2374-9709.

Aligungr (2023). Aligungr/ueransim: Open source 5g ue and ran (gnodeb) implementation.

Aumayr, E., Caso, G., Bosneag, A.-M., Zayas, A. D., Özgü Alay, Garcia, B., Kousias, K., Brünstrom, A., Gomez, P. M., and Koumaras, H. (2022). Service-based analytics for 5g open experimentation platforms. Computer Networks, 205:108740.

Barmpounakis, S. and Demestichas, P. (2022). Framework for trustworthy ai/ml in b5g/6g. In 2022 1st International Conference on 6G Networking (6GNet), pages 1–6.

Chouman, A., Manias, D. M., and Shami, A. (2022). Towards supporting intelligence in 5g/6g core networks: NWDAF implementation and initial analysis.

Hernández-Chulde, C. and Cervelló-Pastor, C. (2019). Intelligent optimization and machine learning for 5g network control and management. In De La Prieta, F., González-Briones, A., Pawleski, P., Calvaresi, D., Del Val, E., Lopes, F., Julian, V., Osaba, E., and Sánchez-Iborra, R., editors, Highlights of Practical Applications of Survivable Agents and Multi-Agent Systems. The PAAMS Collection, pages 339–342, Cham. Springer International Publishing.

Hernández-Chulde, C. and Cervelló-Pastor, C. (2019). Intelligent Optimization and Machine Learning for 5G Network Control and Management. In De La Prieta, F., González-Briones, A., Pawleski, P., Calvaresi, D., Del Val, E., Lopes, F., Julian, V., Osaba, E., and Sánchez-Iborra, R., editors, Highlights of Practical Applications of Survivable Agents and Multi-Agent Systems. The PAAMS Collection, Communications in Computer and Information Science, pages 339–342, Cham. Springer International Publishing.

Jeon, Y., Jeong, H., Seo, S., Kim, T., Ko, H., and Pack, S. (2022). A distributed nwdaf architecture for federated learning in 5g. In 2022 IEEE International Conference on Consumer Electronics (ICCE), pages 1–2.

Koufos, K., EI Haloui, K., Dianati, M., Higgins, M., Elmirghani, J., Imran, M. A., and Tafazolli, R. (2021). Trends in Intelligent Communication Systems: Review of Standards, Major Research Projects, and Identification of Research Gaps. Journal of Sensor and Actuator Networks, 10(4):60. Number: 4 Publisher: Multidisciplinary Digital Publishing Institute.

Liu, Y., He, Y., Lin, Y., and Tang, L. (2022). Toward native artificial intelligence in 6g. In 2022 IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB), pages 1–6.

netscout.com (2022). What Is Network Data Analytics Function? on5g.es (2022). The 3GPP sets the priorities for 5G Advanced, with specifications expected to be approved in 2024.

Open5GS (2022). Open5GS.

Samdanis, K. and Taleb, T. (2020). The Road beyond 5G: A Vision and Insight of the Key Technologies. IEEE Network, 34(2):135–141.

Sevgican, S., Turan, M., Gökarslan, K., Yilmaz, H. B., and Tugcu, T. (2020). Intelligent network data analytics function in 5G cellular networks using machine learning. Journal of Communications and Networks, 22(3):269–280. Conference Name: Journal of Communications and Networks.

Shehzad, M. K., Rose, L., Butt, M. M., Kovacs, I. Z., Assaad, M., and Guizani, M. (2022). Artificial intelligence for 6g networks: Technology advancement and standardization. IEEE Vehicular Technology Magazine, 17(3):16–25.

Wu, J., Li, R., An, X., Peng, C., Liu, Z., Crowcroft, J., and Zhang, H. (2021). Toward Native Artificial Intelligence in 6G Networks: System Design, Architectures, and Paradigms. arXiv:2103.02823 [cs]. arXiv: 2103.02823.