MUET logo

A Comparative Analysis of Software-Defined Networking (SDN) Security Policies With and Without Reinforcement Learning Automation

Authors

  • Syed Shabeeb Raza

    WeUno Technologies, Karachi, Pakistan
    Author

  • Muhammad Imran Saleem

    Sir Syed University of Engineering & Technology, Karachi, Pakistan
    Author

  • Hassan Ahmed Khan

    Iqra University, Karachi, Pakistan
    Author

  • Shaheena Noor

    Sir Syed University of Engineering & Technology, Karachi, Pakistan
    Author

  • Ali Yousuf Khan

    Sir Syed University of Engineering & Technology, Karachi, Pakistan
    Author

  • Eman Razzaq

    Sir Syed University of Engineering & Technology, Karachi, Pakistan
    Author

DOI:

https://doi.org/10.22581/0413

Keywords:

Policy Automation , Network Security, Artificial Intelligence, Dynamic policy management , Software-Defined Networking (SDN), Reinforcement Learning (RL)

Abstract

Software-Defined Networking (SDN) has changed the way networks are built in modern days by separating the control and data planes which thus made it possible to have centralized programmability and flexibility. Although these security mechanisms have developed, SDN security management still depends on static or manually configured policies which are not sufficient anymore for the dynamic and sophisticated cyber threats. AI, especially, Reinforcement Learning (RL), has now become a reliable option to automate SDN security policies and thus allow quick adaptive response to changing threats. In this article, a complete theoretical analysis has been conducted where SDN security policy management through RL-based dynamic automation is juxtaposed against traditional methods. By combining recent studies outcomes, the current work delineates the pros, cons, and practical applicability of both methods. A proposal of a conceptual framework for the implementation of RL into SDN controllers is made which would subsequently help to connect the present gaps and guide future research in both academic and industrial sectors. The paper wraps up with the identification of research challenges, posing of questions that need to be answered, and giving suggestions for the further development of automated, intelligent SDN security architectures

Downloads

References

[1] N. McKeown et al., “OpenFlow: Enabling Innovation in Campus Networks,” ACM SIGCOMM Computer Communication Review, vol. 38, no. 2, pp. 69–74, Apr. 2008.

[2] M. Jammal, T. Singh, A. Shami, R. Asal, and Y. Li, “Software Defined Networking: State of the Art and Research Challenges,” Computer Networks, vol. 72, pp. 74–98, Oct. 2014.

[3] L. Cui, F. R. Yu, Q. Yan, and Z. Han, “When Big Data Meets Software-Defined Networking: SDN, Fog and Cloud Computing,” IEEE Network, vol. 30, no. 1, pp. 58–65, Jan.–Feb. 2016.

[4] A. Lara, A. Kolasani, and B. Ramamurthy, “Network Innovation Using OpenFlow: A Survey,” IEEE Communications Surveys & Tutorials, vol. 16, no. 1, pp. 493–512, 1st Quarter 2014.

[5] P. Porras, S. Shin, V. Yegneswaran, M. Fong, M. Tyson, and G. Gu, “A Security Enforcement Kernel for OpenFlow Networks,” in Proceedings of the First Workshop on Hot Topics in Software Defined Networks (HotSDN), Helsinki, Finland, 2012, pp. 121–126.

[6] S. Scott-Hayward, S. Natarajan, and S. Sezer, “A Survey of Security in Software Defined Networks,” IEEE Communications Surveys & Tutorials, vol. 18, no. 1, pp. 623–654, 1st Quarter 2016.

[7] M. H. H. Tabrizi and K. Salah, “SDN Security: A Survey on Issues, Challenges and Open Research Directions,” IEEE Communications Surveys & Tutorials, vol. 21, no. 3, pp. 2687–2712, 2019.

[8] S. Scott-Hayward, G. O'Callaghan, and S. Sezer, “SDN Security: A Survey,” in Proc. IEEE SDN for Future Networks and Services (SDN4FNS), Trento, Italy, 2013, pp. 1–7, doi: 10.1109/SDN4FNS.2013.670255.

[9] M. Khondoker, D. Zymbler, and R. Vogt, “Survey on SDN Based Network Intrusion Detection System Using Machine Learning Approaches,” in Proceedings of the 2021 International Conference on Networked Systems (NetSys), pp. 1–5.

[10] Faezi, S., Shirmarz, A. A Comprehensive Survey on Machine Learning using in Software Defined Networks (SDN). Hum-Cent Intell Syst 3, 312–343 (2023). doi.org/10.1007/s44230-023-00025-3.

[11] Q. H. Mahmoud, B. H. Al-Husainy, A. Al-Ghobari, and S. M. Taha, “A systematic literature review on machine learning and deep learning approaches for detecting DDoS attacks in SDN,” Sensors, vol. 23, no. 9, Art. no. 4441, 2023, doi: 10.3390/s23094441.

[12] M. A. L. Razib, D. Javeed, M. T. Khan, R. Alkanhel, and M. S. A. Muthanna, “Cyber threats detection in smart environments using SDN-enabled DNN-LSTM hybrid framework,” IEEE Access, vol. 10, pp. 53015–53026, 2022, doi: 10.1109/ACCESS.2022.3174322.

[13] G. Kumar and H. Alqahtani, “Machine learning techniques for intrusion detection systems in SDN—Recent advances, challenges and future directions,” Comput. Model. Eng. Sci., vol. 134, no. 1, pp. 89–119, Aug. 2022, doi: 10.32604/cmes.2022.020724.

[14] M. Latah and L. Toker, “Artificial Intelligence Enabled Software Defined Networking: A Comprehensive Overview,” arXiv preprint arXiv:1803.06818, Mar. 2018.

[15] R. Doriguzzi‑Corin and D. Siracusa, “FLAD: Adaptive Federated Learning for DDoS Attack Detection,” arXiv preprint arXiv:2205.06661, May 2022.

[16] Y. Han, B. I. P. Rubinstein, T. Abraham, T. Alpcan, O. De Vel, S. Erfani, D. Hubczenko, C. Leckie, and P. Montague, “Reinforcement Learning for Autonomous Defence in Software‑Defined Networking,” arXiv preprint arXiv:1808.05770, Aug. 201.

[17] N. Harris and S. Khorsandroo, “DDT: A Reinforcement Learning Approach to Dynamic Flow Timeout Assignment in Software Defined Networks,” J. Netw. Syst. Manage., vol. 32, Art. 35, 2024, doi: 10.1007/s10922-024-09815-x.

[18] Y. K. Shen and C. Zhang, “Predictive mobility and cost‑aware flow placement in SDN‑based IoT networks: a Q‑learning approach,” J. Cloud Comput., vol. 13, Art. 26, Jan. 2024, doi: 10.1186/s13677-024-00589-w.

[19] M. AL-Naday, V. Dobre, M. Reed, et al., “Federated deep Q-learning networks for service-based anomaly detection and classification in edge-to-cloud ecosystems,” Ann. Telecommun., vol. 79, pp. 165–178, 2024, doi: 10.1007/s12243-023-00977-4.

[20] Y. Qing, S. Liu, J. Song, H. Wang, and M. Song, “A survey on explainable reinforcement learning: Concepts, algorithms, challenges,” arXiv preprint arXiv:2211.06665, Nov. 2022.

[21] Y. L. Khaleel, M. A. Habeeb, A. S. Albahri, T. Al‑Quraishi, O. S. Albahri, and A. H. Alamoodi, “Network and cybersecurity applications of defense in adversarial attacks: A state‑of‑the‑art using machine learning and deep learning methods,” J. Intell. Syst., vol. 33, no. 1, Art. 20240153, Aug. 2024, doi: 10.1515/jisys-2024-0153.

[22] I. Panitsas, A. Mudvari, and L. Tassiulas, “Constrained reinforcement learning for adaptive controller synchronization in distributed SDN,” arXiv preprint arXiv:2403.08775, Jan. 2024.

[23] Tianfang, Y., & Liu, H. (2021). STCC: A SDN‑oriented TCP congestion control mechanism for datacenter network. IET Networks, 10(2), 59–69. https://doi.org/10.1049/ntw2.12005.

[24] M. Jenabzadeh, V. Ayatollahitafti, M. Mollakhalili Meybodi, et al., “VNR_LBP: A New Approach to Congestion Control Using Virtualization and Switch Migration in SDN,” Wireless Pers. Commun., vol. 139, pp. 733–757, 2024, doi: 10.1007/s11277-024-11492-7.

[25] J. Arevalo-Herrera, J. Camargo Mendoza, J. I. Martínez Torre, et al., “Assessing SDN Controller Vulnerabilities: A Survey on Attack Typologies, Detection Mechanisms, Controller Selection, and Dataset Application in Machine Learning,” Wireless Pers. Commun., vol. 140, pp. 739–775, 2025, doi: 10.1007/s11277-025-11748-w.

[26] Y. Chen, L. Wang, and H. Zhou, “BI‑TE: Achieving bandwidth‑indistinguishable traffic engineering via differential privacy in multi‑domain SDN,” Front. Comput. Sci., 2024, doi: 10.1007/s11704-024-40551-2..

[27] X. Xu, F. Wu, M. Bilal, J. Bhattacharyya, et al., “XRL‑SHAP‑Cache: an explainable reinforcement learning approach for intelligent edge service caching in content delivery networks,” Sci. China Inf. Sci., vol. 67, Art. 170303, Jun. 2024, doi: 10.1007/s11432-023-3987-y.

[28] A. K. Alnaim, “Adaptive Zero Trust Policy Management Framework in 5G Networks,” Mathematics, vol. 13, Art. 1501, 2025, doi: 10.3390/math13091501..

[29] L. Borchjes, C. Nyirenda, and L. Leenen, “Adversarial deep reinforcement learning for cyber security in software defined networks,” arXiv preprint arXiv:2308.04909, Aug. 2023. arxiv.org/abs/2308.04909.

[30] M. Q. Hamdan, H. Lee, D. Triantafyllopoulou, et al., “Recent Advances in Machine Learning for Network Automation in O‑RAN,” Sensors, vol. 23, no. 21, Art. 8792, 2023, doi: 10.3390/s23218792..

[31] A. S. Tosun, J. M. Arco Rodríguez, R. Doriguzzi‑Corin, and V. G. Vassilakis, “SDN as a defence mechanism: A comprehensive survey,” Int. J. Inf. Secur., vol. 23, pp. 141–185, 2024..

[32] Lee, S. Kim, and H. Park, “A flexible SDN‑based framework for slow‑rate DDoS attack detection and mitigation using reinforcement learning,” Electronics, vol. 14, no. 5, Art. 995, Feb. 2025.

[33] H. Kheddar, D. W. Dawoud, A. I. Awad, Y. Himeur and M. K. Khan, "Reinforcement-Learning-Based Intrusion Detection in Communication Networks: A Review," in IEEE Communications Surveys & Tutorials, vol. 27, no. 4, pp. 2420-2469, Aug. 2025, doi: 10.1109/COMST.2024.3484491

[34] Gao, D., Guo, C., Zhang, Y., Ji, W., Lv, Z., Li, Z., Zhang, K. and Lin, R. (2024), Risk-Aware SDN Defense Framework Against Anti-Honeypot Attacks Using Safe Reinforcement Learning. Int J Network Mgmt, 34: e2297. https://doi.org/10.1002/nem.2297

[35] W. Zhou, D. Zhang, H. Wang, J. Li and M. Jiang, "A Meta-Reinforcement Learning-Based Poisoning Attack Framework Against Federated Learning," in IEEE Access, vol. 13, pp. 28628-28644, 2025, doi: 10.1109/ACCESS.2025.3538891.

Published

2026-04-01

Issue

Vol. 45 No. 2 (2026): April Issue

Section

Articles

License

Copyright (c) 2026 Mehran University Research Journal of Engineering and Technology

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite

A Comparative Analysis of Software-Defined Networking (SDN) Security Policies With and Without Reinforcement Learning Automation. (2026). Mehran University Research Journal of Engineering and Technology, 45(2), 19-36. https://doi.org/10.22581/0413

Similar Articles

21-30 of 81

You may also start an advanced similarity search for this article.