International journal of advanced smart convergence

The Institute of Internet, Broadcasting and Communication (한국인터넷방송통신학회)
권호 표지
DOI QR코드

DOI QR Code

A reinforcement learning-based network path planning scheme for SDN in multi-access edge computing

  • MinJung Kim (Department of Computer Software, Hanyang University) ;
  • Ducsun Lim (Department of Computer Software, Hanyang University)
  • Received : 2024.04.05
  • Accepted : 2024.04.16
  • Published : 2024.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

With an increase in the relevance of next-generation integrated networking environments, the need to effectively utilize advanced networking techniques also increases. Specifically, integrating Software-Defined Networking (SDN) with Multi-access Edge Computing (MEC) is critical for enhancing network flexibility and addressing challenges such as security vulnerabilities and complex network management. SDN enhances operational flexibility by separating the control and data planes, introducing management complexities. This paper proposes a reinforcement learning-based network path optimization strategy within SDN environments to maximize performance, minimize latency, and optimize resource usage in MEC settings. The proposed Enhanced Proximal Policy Optimization (PPO)-based scheme effectively selects optimal routing paths in dynamic conditions, reducing average delay times to about 60 ms and lowering energy consumption. As the proposed method outperforms conventional schemes, it poses significant practical applications.

Keywords

Acknowledgement

This work was partially supported by the Institute of Information & Communications Technology Planning & Evaluation (IITP) grant funded by the Korean government (MSIT) (No.2020-0-01373, Artificial Intelligence Graduate School Program (Hanyang University)) and the research fund of Hanyang University (HY-2024).

References

  1. H. Kim and N. Feamster, Improving Network Management with Software Defined Networking, IEEE Communications Magazine, Vol. 51, No. 2, pp. 114-119, 2013. DOI: https://doi.org/10.7236/JIIBC.2017.17.2.233 
  2. L. Aarikka-Stenroos and P. Ritala, Network Management in the Era of Ecosystems: Systematic Review and Management Framework, Industrial Marketing Management, Vol. 67, pp. 23-36, 2017. DOI: https://doi.org/10.1016/j.indmarman.2017.08.010 
  3. M. Ndiaye, G. P. Hancke, and A. M. Abu-Mahfouz, Software Defined Networking for Improved Wireless Sensor Network Management: A Survey, Sensors, Vol. 17, No. 5, 1031, 2017. DOI: https://doi.org/10.3390/s17051031 
  4. D. Lim et al., DRL-OS: A Deep Reinforcement Learning-based Offloading Scheduler in Mobile Edge Computing, Sensors, Vol. 22, no. 23, pp. 9212, 2022. DOI: https://doi.org/10.3390/s22239212 
  5. T. Taleb et al., On Multi-access Edge Computing: A Survey of the Emerging 5G Network Edge Cloud Architecture and Orchestration, IEEE Communications Surveys & Tutorials, Vol. 19, No. 3, pp. 1657-1681, 2017. DOI: https://doi.org/10.1109/COMST.2017.2705720. 
  6. L. Yang, and X. Zheng. 6G: A Survey on Technologies, Scenarios, Challenges, and the Related Issues. Journal of Industrial Information Integration 19 (2020): 100158. DOI: https://doi.org/10.1016/j.jii.2020.100158 
  7. Y. Lu and X. Zheng, 6G: A Survey on Technologies, Scenarios, Challenges, and the Related Issues, Journal of Industrial Information Integration, Vol. 19, 100158, 2020. DOI: 10.1109/JIOT.2022.315767 
  8. Y. Zuo et al., Learning-based Network Path Planning for Traffic Engineering, Future Generation Computer Systems, Vol. 92, pp. 59-67, 2019. DOI: https://doi.org/10.1016/j.future.2018.09.043 
  9. O. S. Oubbati et al., SEARCH: An SDN-Enabled Approach for Vehicle Path-Planning, IEEE Transactions on Vehicular Technology, Vol. 69, No. 12, pp. 14523-14536, 2020. DOI: 10.1109/TVT.2020.3043306 
  10. D. Lim and I. Joe, A DRL-Based Task Offloading Scheme for Server Decision-Making in Multi-Access Edge Computing, Electronics, Vol. 12, no. 18, pp. 3882, 2023. DOI: https://doi.org/10.3390/electronics12183882 
  11. D. Lim and D. Lim, Deep Reinforcement Learning-Based Task Offloading in Multi-access Edge Computing for Marine IoT, in Proc. Computational Methods in Systems and Software, Cham: Springer International Publishing, pp. 233-244, 2023. DOI: 10.1007/978-3-031-53549-9_23 
  12. M. H. Alsharif et al., Sixth Generation (6G) Wireless Networks: Vision, Research Activities, Challenges and Potential Solutions, Symmetry, Vol. 12, No. 4, 676, 2020. DOI: https://doi.org/10.3390/sym12040676 
  13. S. Zhang and D. Zhu, Towards Artificial Intelligence Enabled 6G: State of the Art, Challenges, and Opportunities, Computer Networks, Vol. 183, 107556, 2020. DOI: https://doi.org/10.1016/j.comnet.2020.107556 
  14. G. Dulac-Arnold et al., Challenges of Real-World Reinforcement Learning: Definitions, Benchmarks and Analysis, Machine Learning, Vol. 110, No. 9, pp. 2419-2468, 2021. DOI: https://doi.org/10.48550/arXiv.1904.12901 
  15. D. Yong et al., Joint Optimization of Multi-User Partial Offloading Strategy and Resource Allocation Strategy in D2DEnabled MEC, Sensors, Vol. 23, No. 5, 2565, 2023. DOI: https://doi.org/10.3390/s23052565