Enhancing Routing Performance in Software-Defined Networks through the Random Forest Algorithm
DOI:
https://doi.org/10.29304/jqcsm.2025.17.42579Keywords:
Random Forest Algorithm,, Data Traffic Management,, Quality of Service (QoS).Abstract
Computer networks are growing fast in both their size and the number of applications that use them. Because of that, managing the flow of data has become more difficult than before. Software-Defined Networking (SDN) makes it possible to manage and monitor the network from one place. SDN relies on three main principles: the separation of the control plane from the data plane, centralized control of the whole network, and providing a global programmable view of network states. These features allow SDN controllers to make dynamic and intelligent routing decisions. However, the controller still deals with a very large amount of traffic data. In the last few years, researchers started to use Machine Learning (ML) methods to handle this data and make routing decisions more efficient. In this study, the Random Forest method was used within an SDN setup to classify and predict traffic patterns. The experiments showed that the model accuracy ranged from about 0.85 to 0.94 in selecting routes. It also helped lower the average delay by nearly 30 to 35 percent compared with OSPF and kept the system stable even when the traffic load changed.
Downloads
References
L. Mhamdi, A. Ben Abdallah, H. Otrok, “Securing SDN: Hybrid autoencoder-random forest for intrusion detection in SDN,” Computers & Security, vol. 105, p. 102467, 2024. [Online]. Available:
https://www.sciencedirect.com/science/article/pii/S1084804524000456 M. Hammad, “Enhancing Network Intrusion Recovery in SDN: A Random Forest Based Approach,” Journal of Network and Systems Management, 2023. [Online]. Available: https://www.tandfonline.com/doi/full/10.1080/25765299.2023.2261219
A. O. Salau and M. M. Beyene, “Software defined networking based network traffic classification using machine learning techniques,” Scientific Reports, vol. 14, p. 20060, 2024. [Online]. Available: https://www.nature.com/articles/s41598-024-70983-6 Nature+1
F. Aktas, et al., “AI-enabled routing in next generation networks: A survey,” Computer Networks, vol. 240, p. 110122, 2025. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S111001682500122X [5] R. H. Serag, “Software Defined Network Traffic Classification for QoS Enhancements,” Springer / Journal (or related), 2025. [Online]. Available: via link Springer “Software Defined Network Traffic Classification for QoS” SpringerLink
Mesfin T. Alemu and Abdisa L. Dinku, “Optimizing SDN Traffic Routing Using Graph Neural Networks and AI Techniques,” MJCRR Journal, 2025. [Online]. Available: https://aspjournals.org/Journals/index.php/mjcrr/article/view/1270 aspjournals.org
Mohamed S. Sawah, Hela Elmannai, Alaa A. El-Bary, Kh. Lotfy, Osama E. Sheta, “Distributed denial of service (DDoS) classification based on random forest model with backward elimination algorithm and grid search algorithm,” Scientific Reports, vol. 15, Article 19063, 2025. [Online]. Available: https://www.nature.com/articles/s41598-025-03868-x Nature
“Traffic classification in SDN-based IoT network using two-level fused network with self-adaptive manta ray foraging,” Scientific Reports, 2025. [Online]. Available: https://www.nature.com/articles/s41598-024-84775-5 Nature
“A Hybrid Learning Approach for Predicting SDN Link States,” (2025). [Online]. Available: InspireHEP listing. inspirehep.net
K. Muheden et al., “A Review of Machine Learning Techniques in Software Defined Networks,” in ITM Conferences (ICACS 2024), 2024. [PDF]. Available: ITM Conferences PDF. itm-conferences.org
S. Nyaramneni et al., “Advanced Ensemble Machine Learning Models to Predict Internet Traffic,” Procedia / Elsevier / Journal 2023.
Karar Talal Hamzah, “Optimizing Software-Defined Networking (SDN) Performance Through Machine Learning-Based Traffic Management,” Journal of Al-Qadisiyah for Computer Science and Mathematics, vol. 17, no. 2, 2025. [Online]. DOI:10.29304/jqcsm.2025.17.22193 ResearchGate
B. Y. Yu, G. Yang, C. Yoo, Comprehensive Prediction Models of Traffic Control for SDN Controllers, 2018 4th IEEE Conference on Network Software and Workshops, NetSoft 2018 (NetSoft) (2018) 415–423. doi:10.1109/NETSOFT.2018.8460111.
Y. Wang, D. Jiang, L. Huo, Y. Zhao, On reconstruction and prediction of network traffic in software-defined networking, Proceedings – IEEE International Conference on Industrial Internet Cloud, ICII 2019 (ICII) (2019) 98–102. doi:10.1109/ICII.2019.00029.
J. Xie, F. Richard Yu, T. Huang, R. Xie, J. Liu, C. Wang, Y. Liu, A survey of machine learning techniques applied to software defined networking (SDN): Research issues and challenges, IEEE Communications Surveys and Tutorials 21 (1) (2019) 393–430. doi:10.1109/COMST.2018.2866942.
A. R. Mohammed, S. A. Mohammed, S. Shirmohammadi, Machine Learning and Deep Learning Based on Traffic Classification and Prediction in Software Defined Networking, 2019 IEEE International Symposium on Measurements and Networking, M and N 2019 - Proceedings (2019). doi:10.1109/IWMN.2019.8805044.
G. Wassie, J. Ding, and Y. Wondie, “Detecting and Predicting Models for QoS Optimization in SDN,” JOURNAL OF COMPUTER NETWORKS AND COMMUNICATIONS, vol. 2024, Article ID 3073388, 9 pages, 2024. doi: 10.1155/2024/3073388.
A. D. İpek, M. Cicioğlu, and A. Çalhan, “AIRSDN: AI based routing in software-defined networks for multimedia traffic transmission,” COMPUTER COMMUNICATIONS, vol. 240, p. 108222, Aug. 2025. doi: 10.1016/j.comcom.2025.108222.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Samah Fakhri Aziz
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
