Skip to main navigation menu Skip to main content Skip to site footer

Vol. 33 No. 69 (2024)
July-September 2024: Open Science at the Service of Engineering

Papers

Performance Analysis of Access and Mobility Management Function On a 5G Core Based On CPU Usage Predictions

https://doi.org/10.19053/uptc.01211129.v33.n69.2024.18057

Published 2024-08-31

  • Wilmar-Yesid Campo-Muñoz
    • ,
  • Jhon-Alexander Amaya-Suárez
    • ,
  • Juan-Camilo Caviedes-Valencia

Wilmar-Yesid Campo-Muñoz
University of Quindío image/svg+xml

Jhon-Alexander Amaya-Suárez
University of Quindío image/svg+xml

Juan-Camilo Caviedes-Valencia
Universidad Nacional de Colombia image/svg+xml

Abstract

The increasing number of mobile devices and the growing demand for services lead to an increase in the access requests per second to the Access and Mobility Management Function (AMF) of the control plane in a Fifth Generation (5G) mobile network. It causes congestion of the function and affects the overall network performance. Therefore, this paper proposes a self-scaling mechanism for the AMF in a 5G core by CPU usage predictions using the Long Short-Term Memory (LSTM) machine learning (ML) technique. The mechanism predicts the percentage of CPU usage in the pod containing the AMF and establishes scaling policies that determine the necessary number of AMF pods. The performance of the AMF is evaluated through success rate, loss rate, and latency of access requests per second in three scenarios: a reactive one with scaling based on current CPU thresholds, a predictive one using CPU predictions, and another using both the scaling policies and the LSTM technique. With the previous scenarios, the AMF is scaled reactively and predictively. Results show that the scaling policies and the ML algorithm significantly improve the performance of the function in terms of success rate and loss rate of access requests per second. An efficient self-scaling of the AMF is achieved, which contributes both to the optimization of computational resources and to improving the availability of the 5G mobile network.

Keywords

AMF, CPU, scaling policies, self-scaling

XML PDF

References

  1. Ericsson, Explore the Ericsson Mobility Report, 2024. https://www.ericsson.com/en/reports-andpapers/mobility-report/reports/june-2024
  2. I. Alam et al., “A Survey of Network Virtualization Techniques for Internet of Things Using SDN and NFV,” ACM Computing Surveys, vol. 53, no. 2, e337944, 2020. https://doi.org/10.1145/3379444
  3. J. L. Chavez-Picon, W. Y. Campo-Muñoz, G. E. Chanchí-Golondrino. “Arquitectura para implementación de servicios de video sobre redes móviles mediante redes definidas por software y segmentación de red,” Revista Colombiana de Tecnologías de Avanzada (RCTA), vol. 2, no. 42, e2651. https://doi.org/10.24054/rcta.v2i42.2651
  4. A. Chouman, D. M. Manias, A. Shami, “A Reliable AMF Scaling and Load Balancing Framework for 5G Core Networks,” in International Wireless Communications and Mobile Computing (IWCMC), Marrakesh, Morocco, 2023, pp. 252-257. https://doi.org/10.1109/IWCMC58020.2023.10182447
  5. H. Atarashi, M. Iwamura, S. Nagata, T. Nakamura, A. Toskala, “5G Targets and Standardization,” in 5G Technoly 3GPP Evolution to 5G-Advanced, pp. 13-26, 2024.
  6. A. Toskala, M. Poikselkä, “5G Architecture,” in 5G Technoly 3GPP Evolution to 5G-Advanced, pp. 67-86, 2024.
  7. S. Christakis, N. Makris, T. Korakis, S. Fdida, “On the Automated Scaling of User Plane Function for 5G: An Experimental Evaluation,” in Joint European Conference on Networks and Communications & 6G Summit (EuCNC/6G Summit), Belgium, 2024, pp. 979-984. https://doi.org/10.1109/EuCNC/6GSummit60053.2024.10597110
  8. C. Rotter, T. Van Do, “A Queueing Model for Threshold-Based Scaling of UPF Instances in 5G Core,” IEEE Access, vol. 9, pp. 81443-81453, 2021. https://doi.org/10.1109/ACCESS.2021.3085955
  9. T. Lorido-Botran, J. Miguel-Alonso, J. A. Lozano, “A Review of Auto-scaling Techniques for Elastic Applications in Cloud Environments,” Journal of Grid Computing., vol. 12, no. 4, pp. 559-592, 2014. https://doi.org/10.1007/s10723-014-9314-7
  10. J. C. Valencia, “Modelo predictivo para la asignación elástica de recursos sobre entornos NFV/SDN basados en OpenStack,” Grade Thesis, Universidad Nacional de Colombia, Bogotá, Colombia, 2021. https://repositorio.unal.edu.co/handle/unal/79636
  11. I. Alawe, A. Ksentini, Y. Hadjadj-Aoul, P. Bertin, “Improving Traffic Forecasting for 5G Core Network Scalability: A Machine Learning Approach,” IEEE Network, vol. 32, no. 6, pp. 42-49, 2018. https://doi.org/10.1109/MNET.2018.1800104
  12. I. Alawe, A. Ksentini, Y. Hadjadj-Aoul, P. Bertin, A. Kerbellec, “On evaluating different trends for virtualized and SDN-ready mobile network,” in IEEE 6th International Conference in Cloud Networking, 2017. https://doi.org/10.1109/CloudNet.2017.8071534
  13. M. A. Alam, S. Khatibi, “CPU resource usage analysis for downlink PDCP processing in CRAN,” in IEEE International Symposium on Personal, Indoor and Mobile Radio Communications, 2020. https://doi.org/10.1109/PIMRC48278.2020.9217294
  14. H. D. Trinh, L. Giupponi, P. Dini, “Mobile Traffic Prediction from Raw Data Using LSTM Networks,” IEEE International Symposium on Personal, Indoor and Mobile Radio Communications, 2018, pp. 1827-1832. https://doi.org/10.1109/PIMRC.2018.8581000
  15. L. Nashold, R. Krishnan, Using LSTM and SARIMA Models to Forecast Cluster CPU Usage, 2020. https://api.semanticscholar.org/CorpusID:219711129
  16. H. Ge, Y. Huo, Z. Wang, P. Xie, T. Wei, “VNF Instance Dynamic Scaling Strategy Based on LSTM,” Advances in Intelligent Systems and Computing, vol. 1274, pp. 335-343, 2021. https://doi.org/10.1007/978-981-15-8462-6_39

Downloads

Download data is not yet available.