f Improvement of 5G Core Network Performance using Network Slicing and Deep Reinforcement Learning
FOREX Press I. J. of Electrical & Electronics Research
Support Open Access
  • Home/
  • IJEER-120222

Research Article |

Improvement of 5G Core Network Performance using Network Slicing and Deep Reinforcement Learning

Author(s): Fred Otieno Okello*, Vitalice Oduol, Ciira Maina and Antonio Apiyo

Published In : International Journal of Electrical and Electronics Research (IJEER)        Volume 12, Issue 2

Publisher : FOREX Publication

Published : 30 May 2024

e-ISSN : 2347-470X

Page(s) : 493-502

DOI: https://doi.org/10.37391/IJEER.120222

Abstract

Users have increasingly been having more use cases for the network while expecting the best Quality of Service (QoS) and Quality of Experience (QoE). The Fifth Generation of mobile telecommunications technology (5G) network had promised to satisfy most of the expectations and network slicing had been introduced in 5G to be able to satisfy various use cases. However, creating slices in a real-life environment with just the resources required while having optimized QoS has been a challenge. This has necessitated more intelligence to be required in the network and machine learning (ML) has been used recently to add the intelligence and ensure zero-touch automation. This research addresses the open question of creating slices to satisfy various use cases based on their QoS requirements, managing, and orchestrating them optimally with minimal resources while allowing the isolation of services by introducing a Deep reinforcement Machine Learning (DRL) algorithm. This research first evaluates the previous work done in improving QoS in the 5G core. 5G architecture is simulated by following the ETSI NFV MANO (European Telecommunications Standards Institute for Network Function Virtualization Management and Orchestration) framework and uses Open5G in 5G core, UERANISM for RAN, Openstack for Virtual Infrastructure Manager (VIM), and Tacker for Virtual Network Function Management and orchestration (VNFMO). The research simulates network slicing at the User Plane Function (UPF) level and evaluates how it has improved QoS. The network slicing function is automated by following ETSI Closed Loop Architecture and using Deep Reinforcement Learning (DRL) by modeling the problem as a Markov Decision Problem (MDP). Throughput is the Reward for the actions of the DRL agent. Comparison is done on the impact of slicing on throughput and compares models that have not been sliced, the ones that have been sliced and combined to work together, and models with slices that have been assigned more bandwidth. Sliced networks have better throughput than the ones not sliced. If more slices are load-balanced the throughput is increased. Deep Reinforcement Learning has managed to achieve the dynamic assigning of slices to compensate for declining throughput.

Keywords: 5G, 5G Architecture, ETSI NFV MANO, Network slicing, QoS, Reinforcement learning, User plane functions.




Fred Otieno Okello*, Department of Electrical Engineering, Pan Africa University Institute for Basic Sciences, Technology, and Innovation (PAUSTI), Juja, Kenya; Email: kogsokello@gmail.com

Vitalice Oduol, Department of Electrical and Information Engineering, University of Nairobi of Nairobi, Nairobi, Kenya

Ciira Maina, Centre for Data Science and Artificial Intelligence, Dedan Kimathi University of Technology, Nyeri, Kenya

Antonio Apiyo, Nokia Mobile Networks, Wroclaw, Poland

    [1] ITU International Library. Setting the scene for 5g: Opportunities and challenges. Report, 2018. URL http://handle.itu.int/11.1002/pub/811d7a5f-en.
    [2] A. Platek, J. You, and R. Pandey. AI-Powered 5G Operations. Episode 2, Ericsson Podcast Series, 2021. URL https://www.ericsson.com/en/ai/ai-operations-podcast/ai-powered-5g-Operations.
    [3] C. Ssengozi, P. Kogeda, and T. Olwal. A survey of deep reinforcement learning application in 5g and beyond network slicing and virtualization. Array, 14:100142, 2022. URL https://doi.org/10.1016/j.array.2022.100142. [CrossRef]
    [4] 3GPP TS 23.501 V16.4.0. System architecture for the 5G System (5GS). Release 16, 2020.
    [5] Q. Ye, W. Zhuang, S. Zhang, A. Jin, X. Shen, and X. Li. Dynamic radio resource slicing for a two-tier heterogeneous wireless network. IEEE Trans Veh Technol, 67(10):9896, 2019. [CrossRef]
    [6] G. Zhous, L. Zhao, K. Liang, and G. Zhen. Utility analysis of radio access network slicing. IEEE Trans Veh Technol, 67(10):99, 2019.
    [7] H. Yang, T. So, and Y. Xu. Chapter 12 - 5G Network Slicing, pages 621–639. Elsevier, 2022. ISBN 9780323910606. [CrossRef]
    [8] I. Levya-Pupo, C. Cervel, and A. Llorens-Carrodeguas. Optimal placement of user plane functions in 5g networks. Wired/Wireless Internet Communications, 2019. URL https://api.semanticscholar.org/CorpusID:202550252. [CrossRef]
    [9] I. Alawe, A. Ksentini, Y. Hadjadj-Aoul, and P. Bertin. Improving traffic forecasting for 5g core network scalability: A machine learning approach. IEEE Network, 32(6):42–49, 2018. [CrossRef]
    [10] P. D. Bojovi´c, T. Malbaˇsi´c, D. Vujoˇsevi´c, G. Marti´c, and Z. Bojovi´c. Dynamic QoS management for a flexible 5g/6g network core: A step toward a higher programmability. Sensors, 22(8):2849, 2022. URL https://doi.org/10.3390/s22082849. [CrossRef]
    [11] J. Moysen and L. Giupponi. From 4g to 5g: Self organized network management meets machine learning. Computer Communications, 129:248–268, 2018.
    [12] H. T. Nguyen, T. Van Do, and C. Rotter. Scaling upf instances in 5g/6g core with deep reinforcement learning. IEEE Access, 9:165892–165906, 2021. URL https://doi.org/10.1109/access.2021.3135315. [CrossRef]
    [13] P. et al. Rost. Mobile network architecture evolution toward 5g. IEEE Communications Magazine, 54(5):84–91, 2016. doi: https://doi.org/10.1109/MCOM.2016.7470940. [CrossRef]
    [14] N. Van Giang and Y. H. Kim. Slicing the next mobile packet core network. In 2020 11th International Symposium on Wireless Communications Systems (ISWCS), pages 901–904, 2020. [CrossRef]
    [15] Q. Ye, J. Li, K. Qu, W. Zhuang, X. S. Shen, and X. Li. End-to-end quality of service in 5g networks: Examining the effectiveness of a network slicing framework. IEEE Vehicular Technology Magazine, 13(2):65–74, 2018. [CrossRef]
    [16] H. Wei, Z. Zhang, and B. Fan. Network slice access selection scheme in 5g. In 2017 IEEE 2nd Information Technology, Networking, Electronic and Automation Control Conference (ITNEC), pages 352–356, 2017. [CrossRef]
    [17] O. Sallent, J. Perez-Romero, R. Ferrus, and R. Agusti. Radio access network slicing from a radio resource management perspective. IEEE Wirel. Commun., 24(5):166–174, 2017. URL https://doi.org/10.1109/MWC.2017 .1600220WC. [CrossRef]
    [18] C. Tsai, F. Lin, and H. Tanaka. Evaluation of 5g core slicing on user plane function. Communications and Network, 13:79–92, 2019. [CrossRef]
    [19] H. Yang, T. So, and Y. Xu. Chapter 12 - 5G Network Slicing, pages 621–639. Elsevier, 2022. ISBN 9780323910606. doi: 10.1016/B978-0-323-91060-6.00012. [CrossRef]
    [20] ETSI GS NFV 001 099 v2.1.1, URL https://www.etsi.org/deliver/etsi_gs/nfv/001_099/006/02.01.01_60/gs_nf v006v020101p.pdf.
    [21] ETSI GS ZSM 001 099 v1.1.1, URL https://www.etsi.org/deliver/etsi_gs/ZSM/001_099/00901/01.01.01_60/g s_ZSM00901v010101p.pdf.
    [22] K. Muppavaram, S. Govathoti, D. Kamidi, and T. Bhaskar. Exploring the generations: A comparative study of mobile technology from 1g to 5g. International Journal of Electronics and Communication Engineering, 10(7): 54–62, 2023. [CrossRef]
    [23] R. et al. Li. Deep reinforcement learning for resource management in network slicing. IEEE Access, 6:74429–74441, 2018. doi: 10.1109/ACCESS.2018.2881964. [CrossRef]
    [24] B. S. Teja and V. M. John. Generations of wireless mobile networks: An overview. In Proceedings of International Conference on Deep Learning, Computing, and Intelligence. Springer, 2022.
    [25] ITU. Framework of the imt-2020 network. Technical Report Y.May, ITU-T, 2018.
    [26] P. Subedi, A. Alsadoon, and P. W. C. Rasad. Network slicing: A next-generation 5g perspective. J Wireless Com Network, 102, 2021. URL https://doi.org/10.1186/s13638-021-01983. [CrossRef]
    [27] V. M. Alevizaki, A. I. Manolopoulos, M. Anastasopoulos, and A. Tzanakaki. Dynamic user plane function allocation in 5g networks enabled by optical network nodes. In 2021 European Conference on Optical Communication (ECOC), pages 1–4, 2021. [CrossRef]
    [28] K. Godfrey, S. Joan, G. Juanluis, Y. Haipeng, and Z. Peiying. A reinforcement learning-based approach for 5g network slicing across multiple domains. In 15th International Conference on Network and Service Management, 2019. [CrossRef]
    [29] H. T. Nguyen, T. Van Do, and C. Rotter. Scaling upf instances in 5g/6g core with deep reinforcement learning. IEEE Access, 9:165892–165906, 2021. doi: https://doi.org/10.1109/access.2021.3135315. [CrossRef]
    [30] X. Chen, Z. Li, Y. Zhang, R. Long, H. Yu, X. Du, and M. Guizani. Reinforcement learning-based QoS/QoE-aware service function chaining in software-driven 5g slices. [CrossRef]
    [31] C. Zhang, P. Patras, and H. Haddadi. Deep learning in mobile and wireless networking: A survey. IEEE Communications Surveys (&) Tutorials, 21(3):2224–2287, 2019. doi: 10.1109/COMST.2019.2904897. [CrossRef]

Fred Otieno Okello, Vitalice Oduol, Ciira Maina and Antonio Apiyo (2024), Improvement of 5G Core Network Performance using Network Slicing and Deep Reinforcement Learning. IJEER 12(2), 493-502. DOI: 10.37391/IJEER.120222.