UPF Autoscaling in Private 5G Networks for Video Transmission: A Comparative Analysis of Reactive and Predictive Approaches

• Pedro Antônio de Andrade da Silva IFPB https://orcid.org/0009-0009-5042-7823
• Paulo Ditarso Maciel Jr IFPB https://orcid.org/0000-0002-0732-752X

DOI: https://doi.org/10.5753/wpeif.2026.24018

Abstract

Industry 4.0 applications demand high reliability and low latency, driving the adoption of Service-Based Architectures in Private 5G networks. However, resource orchestration remains challenging; traditional reactive mechanisms, such as the Kubernetes Horizontal Pod Autoscaler (HPA), fail to address the session affinity of the GPRS Tunneling Protocol. This leads to unbalanced loads where active units saturate while new instances sit idle. This paper proposes a predictive scaling mechanism for the User Plane Function (UPF) that anticipates traffic and instantiates resources prior to session establishment. Validated in a virtualized testbed, the predictive approach ensures proper load balancing and prevents connection drops typical of reactive scenarios.

References

3GPP (2022). System Architecture for the 5G System (5GS); Stage 2 (Release 16). Technical Report TS 23.501 V16.10.0, 3rd Generation Partnership Project (3GPP).

3GPP (2023). Procedures for the 5G System (5GS) (Release 16). Technical Report TS 23.502 V16.16.0, 3rd Generation Partnership Project (3GPP).

Aijaz, A. (2020). Private 5G: The Future of Industrial Wireless. IEEE Industrial Electronics Magazine, 14(4):136–145.

Batalla, J. M. (2020). On Analyzing Video Transmission Over Wireless WiFi and 5G C-Band in Harsh IIoT Environments. IEEE Access, 8:118534–118541.

Botez, R., Costa-Requena, J., Ivanciu, I.-A., Strautiu, V., and Dobrota, V. (2021). SDN-Based Network Slicing Mechanism for a Scalable 4G/5G Core Network: A Kubernetes Approach. Sensors, 21(11):3773.

Choudhari, C. S., Patil, R., and Saraf, S. (2022). Deployment of 5G Core for 5G Private Networks. In 2022 International Conference on Industry 4.0 Technology (I4Tech).

Mendes de Souza, L., de Andrade da Silva, P. A., dos Santos Neto, A. A., Forcelli Silva, I., and Maciel Jr., P. D. (2025). Impacto do Posicionamento da UPF na Borda sobre a Qualidade de Serviço em Redes 5G Privadas. In Anais do XLIII Simpósio Brasileiro de Telecomunicações e Processamento de Sinais (SBrT 2025), Natal, RN, Brasil.

Nguyen, T.-T., Yeom, Y.-J., Kim, T., Park, D.-H., and Kim, S. (2020). Horizontal Pod Autoscaling in Kubernetes for Elastic Container Orchestration. Sensors, 20(16).

Strinati, E. C. et al. (2020). Beyond 5G Private Networks: the 5G CONNI Perspective. In 2020 IEEE Globecom Workshops (GC Wkshps), pages 1–6.

Veeck, C., Barbosa, M., and Dias, K. (2025). Reagir ou Antecipar? Uma Comparação entre HPA e ML para Balanceamento de Carga. In Anais do XLIII Simpósio Brasileiro de Telecomunicações e Processamento de Sinais (SBrT 2025), Natal, RN, Brasil.

Yeh, S.-P., Bhattacharya, S., Sharma, R., and Moustafa, H. (2024). Deep Learning for Intelligent and Automated Network Slicing in 5G Open RAN (ORAN) Deployment. IEEE Open Journal of the Communications Society, 5:64–70.