Dynamic Path Selection in SDN Based on Reinforcement Learning and Link Utilization
DOI:
https://doi.org/10.4108/ew.12999Keywords:
Reinforcement Learning, Link utilization, Path selection optimization, Software-defined networking, Graph convolutional networkAbstract
INTRODUCTION: The development of modern power systems imposes stringent requirements on communication networks, including highly dynamic loads, low latency, and high reliability. Although recent Software-Defined Networking routing, link-utilization-aware scheduling, and reinforcement learning-based methods improve path optimization, challenges remain in bottleneck-link perception, congestion feedback, and stable decision-making under dynamic traffic conditions.
OBJECTIVES: To counteract problems like delayed response times and inadequate congestion identification in conventional path selection algorithms owing to dynamic link modifications, this research paper presents a path selection model that combines bottleneck link usage and reinforcement learning.
METHODS: Under the Software-Defined Networking control architecture, the proposed model incorporates link utilization, Graph Convolutional Network structures, and Gated Recurrent Units, while introducing a deep reinforcement learning algorithm to optimize routing strategies.
RESULTS: Experimental results demonstrate that under a 60 Mbit/s load, the proposed method achieves a throughput of 57 Mbit/s, maintains the minimum transmission delay within 0.043 s, and yields a link utilization rate of 89%. In experiments carried out to evaluate dynamic decision-making, the approach for choosing paths adopted by the model averages convergence at the 15th round, resulting in an error rate of 4.2%, minimal load balancing at 0.23, and median latency time in real-time decisions of only 31 ms, which is better than other models.
CONCLUSION: These results demonstrate that the model achieves superior state awareness and adaptive routing performance in multi-source heterogeneous networks. The model also exhibits good performance in terms of congestion control and path optimization and hence can be used effectively for intelligent routing in next-generation power communication networks.
Downloads
References
[1] Logeshwaran J, Shanmugasundaram RN, Lloret J. Load based dynamic channel allocation model to enhance the performance of device-to-device communication in WPAN. Wireless Netw. 2024;30(4):2477-2509. DOI:10.1007/s11276-024-03680-x.
[2] Wei W, Fu L, Gu H, Zhang Y, Zou T, Wang C, Wang N. GRL-PS: Graph embedding-based DRL approach for adaptive path selection. IEEE Trans Netw Serv Manag. 2023;20(3):2639-2651. DOI:10.1109/TNSM.2023.3240396.
[3] Veisi F, Montavont J, Theoleyre F. Enabling centralized scheduling using software defined networking in industrial wireless sensor networks. IEEE Internet Things J. 2023;10(23):20675-20685. DOI:10.1109/JIOT.2023.3302994.
[4] Mehraban S, Yadav RK. Traffic engineering and quality of service in hybrid software defined networks. China Commun. 2024;21(2):96-121. DOI:10.23919/JCC.fa.2022-0860.202402.
[5] Liu CL, Huang TH. Dynamic job-shop scheduling problems using graph neural network and deep reinforcement learning. IEEE Trans Syst Man Cybern Syst. 2023;53(11):6836-6848. DOI:10.1109/TSMC.2023.3287655.
[6] Ye X, Yu Y, Fu L. Deep reinforcement learning based link adaptation technique for LTE/NR systems. IEEE Trans Veh Technol. 2023;72(6):7364-7379. DOI:10.1109/TVT.2023.3236791.
[7] He Q, Wang Y, Wang X, Xu W, Li F, Yang K, Ma L. Routing optimization with deep reinforcement learning in knowledge defined networking. IEEE Trans Mob Comput. 2024;23(2):1444-1455. DOI:10.1109/TMC.2023.3235446.
[8] Li D, Zhang Z, Alizadeh B, Zhang Z, Duffield N, Meyer MA, Behzadan AH. A reinforcement learning-based routing algorithm for large street networks. Int J Geogr Inf Sci. 2024;38(2):183-215. DOI:10.1080/13658816.2023.2279975.
[9] He J, Cheng N, Yin Z, Zhou C, Zhou H, Quan W, Lin XH. Service-oriented network resource orchestration in space-air-ground integrated network. IEEE Trans Veh Technol. 2024;73(1):1162-1174. DOI:10.1109/TVT.2023.3301676.
[10] Yang L, Liang J, Wang R, Liu X, De Sanctis M, Burleigh SC, Zhao K. A study of Licklider transmission protocol in deep-space communications in presence of link disruptions. IEEE Trans Aerosp Electron Syst. 2023;59(5):6179-6191. DOI:10.1109/TAES.2023.3273523.
[11] Taha M. An efficient software defined network controller based routing adaptation for enhancing QoE of multimedia streaming service. Multimed Tools Appl. 2023;82(22):33865-33888. DOI:10.1007/s11042-023-14938-5.
[12] Ritzkal R, Suhadi S, Amalia R, Afrianto Y, Triawan A, Syafrial S, Fatimah F. K-nearest neighbor algorithm analysis for path determination in network simulation using software defined network. Bull Electr Eng Inform. 2023;12(4):2388-2400. DOI:10.11591/eei.v12i4.4868.
[13] Zheng H, Guo J, Zhou Q, Peng Y, Chen Y. Application of improved ant colony algorithm in load balancing of software-defined networks. J Supercomput. 2023;79(7):7438-7460. DOI:10.1007/s11227-022-04957-8.
[14] Wu C, Zhang Y, Li N, Rezaeipanah A. An intelligent fuzzy-based routing algorithm for video conferencing service provisioning in software defined networking. Telecommun Syst. 2024;87(4):887-898. DOI:10.1007/s11235-023-01044-y.
[15] Ye Z, Sun G, Guizani M. ILBPS: An integrated optimization approach based on adaptive load-balancing and heuristic path selection in SDN. IEEE Internet Things J. 2024;11(4):6144-6157. DOI:10.1109/JIOT.2023.3309832.
[16] Rafid M, Ghafoor H, Koo I. An SVM-based optimal-controller selection and path selection protocol for heterogeneous communications in SDVNs. IEEE Trans Intell Transp Syst. 2024;25(5):3828-3842. DOI:10.1109/TITS.2023.3326651.
[17] Liu Y, Huo L, Zhang X, Wu J. A multi-objective resource pre-allocation scheme using SDN for intelligent transportation system. IEEE Trans Intell Transp Syst. 2024;25(1):571-586. DOI:10.1109/TITS.2023.3310978.
[18] Sheng Z, Wen S, Feng ZK, Shi K, Huang T. A novel residual gated recurrent unit framework for runoff forecasting. IEEE Internet Things J. 2023;10(14):12736-12748. DOI:10.1109/JIOT.2023.3254051.
[19] Prabha R, Senthil GA, Bharathi GP, Sridevi S. Hybrid multipath routing cluster head prediction based on SDN-enabled IoT and heterogeneous context-aware graph convolution network. Peer-to-Peer Netw Appl. 2024;17(4):2016-2030. DOI:10.1007/s12083-024-01685-z.
[20] Huang L, Ye M, Xue X, Wang Y, Qiu H, Deng X. Intelligent routing method based on Dueling DQN reinforcement learning and network traffic state prediction in SDN. Wireless Netw. 2024;30(5):4507-4525. DOI:10.1007/s11276-022-03066-x.c
Additional Files
Published
Issue
Section
License
Copyright (c) 2026 Ying Zeng, Xingnan Li, Yuben Bao, Guangyu Hu, Jikai Hong, Fan Zha
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This is an open-access article distributed under the terms of the Creative Commons Attribution CC BY 4.0 license, which permits unlimited use, distribution, and reproduction in any medium so long as the original work is properly cited.
