Intelligent Optimization of OSPF Path Selection Using Machine Learning Models for Adaptive Network Routing

Rebeen Rebwar Hama Amin

doi:10.24017/science.2025.2.3

Authors

Rebeen Rebwar Hama Amin Network Department, Computer Science Institute, Sulaimani Polytechnic University, Sulaymaniyah, Iraq https://orcid.org/0000-0002-9847-5543

Abstract

At the core of enterprise networks lies routing protocols that make forwarding decisions based on a set of rules and metrics. One of the most popular and widely used routing protocols is the Open Shortest Path First (OSPF). Traditional OSPF calculates the cost of the route primarily based on interface bandwidth, without considering real-time factors such as latency, congestion, or link stability. These calculations are static and can lead to deficiencies in adapting to unstable network conditions. This study proposes the integration of multiple machine learning (ML) models and techniques to enhance OSPF routing decisions. Four important ML functions namely traffic forecast, anomaly detection, failure prediction, and dynamic cost optimization—have been used to improve OSPF performance. ML methods such as Random Forest and XGBoost are used to predict and assign costs in traffic utilization and real-time performance assessments. AutoRegressive Integrated Moving Average models and Long Short-Term Memory are applied to enable traffic predictions and route adjustments before potential congestions. Furthermore, link and node failure are common in network routing. Random Forest and logistic regression models are employed to predict these. The simulation took place in Graphical Network Simulator-3 using Cisco routers and Linux servers to allow thorough testing before and after applying the ML models. The results and findings have shown that the integration of ML models reroutes the traffic to enhance latency and throughput by approximately 30%. The findings demonstrate the upside of ML-enhanced OSPF routing as a versatile and scalable solution for high-demand networks.

Keywords:

Machine Learning, OSPF, SDN, Routing Protocols

References

G. Bernárdez et al., “MAGNNETO: A Graph Neural Network-Based Multi-Agent System for Traffic Engineering.” IEEE Transactions on Cognitive Communications and Networking, vol. 9, no. 2, pp. 494–506, 10 Jan. 2023 . https://doi.org/10.1109/tccn.2023.3235719 DOI: https://doi.org/10.1109/TCCN.2023.3235719

B. Al-Musawi and P. Branch, “Identifying OSPF Anomalies Using Recurrence Quantification Analysis,” arXiv (Cor-nell University), Jan. 2018. https://doi.org/10.48550/arxiv.1805.08087

H. Saini, and A. K. Garg. “Impact of Mathematical Optimization on OSPF Routing in WDM Optical Networks”, in: H. Malik, S., Srivastava, Y. Sood and A. Ahmad (eds), Applications of Artificial Intelligence Techniques in Engineer-ing . Advances in Intelligent Systems and Computing, vol 697, pp 201-208. Springer, Singapore. https://doi.org/10.1007/978-981-13-1822-1_19 DOI: https://doi.org/10.1007/978-981-13-1822-1_19

R. Etengu et al. “Deep Learning-Assisted Traffic Prediction in Hybrid SDN/OSPF Backbone Networks.” NOMS 2022-2022 IEEE/IFIP Network Operations and Management Symposium, 25 Apr. 2022, pp. 1–6. https://doi.org/10.1109/NOMS54207.2022.9789868 DOI: https://doi.org/10.1109/NOMS54207.2022.9789868

A. Ikpe and I. Ekanem, “Engineering Wired Network Performance Enhancement in a Route Redistributed Simula-tion Based Systems”, Big Data and Computing Visions, vol, 4, no. 1, pp. 31-48, 2024. https://doi.org/10.22105/bdcv.2024.464144.1181

W. Jiang et al., “Graph Neural Networks for Routing Optimization: Challenges and Opportunities,” Sustainability, vol. 16, no. 21, p. 9239, Oct. 2024. https://doi.org/10.3390/su16219239 DOI: https://doi.org/10.3390/su16219239

X. Li, J. Li, J. Zhou, and J. Liu, “Towards Robust Routing: Enabling Long-Range Perception with the Power of Graph Transformers and Deep Reinforcement Learning in Software-Defined Networks,” Electronics, vol. 14, no. 3, p. 476, Jan. 2025. https://doi.org/10.3390/electronics14030476 DOI: https://doi.org/10.3390/electronics14030476

M. Usama, et al. “Unsupervised Machine Learning for Networking: Techniques, Applications and Research Chal-lenges.” IEEE Access, vol. 7, pp. 65579–65615, 2019. https://doi.org/10.1109/access.2019.2916648 DOI: https://doi.org/10.1109/ACCESS.2019.2916648

Q. Zhou, and D. Pezaros. “A Prediction-Based Model for Consistent Adaptive Routing in Back-Bone Networks at Extreme Situations.” Electronics, vol. 9, no. 12, pp. 2146–2146, 15 Dec. 2020. https://doi.org/10.3390/electronics9122146 DOI: https://doi.org/10.3390/electronics9122146

D. Szostak, A. Włodarczyk and K. Walkowiak , “Machine Learning Classification and Regression Approaches for Optical Network Traffic Prediction.” Electronics, vol. 10, no. 13, p. 1578, 30 June 2021. https://doi.org/10.3390/electronics10131578 DOI: https://doi.org/10.3390/electronics10131578

J. Zhang, R. Gardner and I. Vukotic., “Anomaly Detection in Wide Area Network Meshes Using Two Machine Learning Algorithms.” Future Generation Computer Systems, vol. 93, pp. 418–426, Apr. 2019. https://doi.org/10.1016/j.future.2018.07.023 DOI: https://doi.org/10.1016/j.future.2018.07.023

K. Fotiadou, et al., “Network Traffic Anomaly Detection via Deep Learning.” Information, vol. 12, no. 5, p. 215, 19 May 2021.https://doi.org/10.3390/info12050215 DOI: https://doi.org/10.3390/info12050215

I. Fosić, et al. “Anomaly Detection in NetFlow Network Traffic Using Supervised Machine Learning Algorithms.” Journal of Industrial Information Integration, vol. 33, p. 100466, 1 June 2023. https://doi.org/10.1016/j.jii.2023.100466 DOI: https://doi.org/10.1016/j.jii.2023.100466

J. Papán et al., “The New Label Bit Repair Fast Reroute Mechanism,” IEEE Access, vol.12, pp. 46487 – 46503, 2024. https://doi.org/10.1109/access.2024.3379150 DOI: https://doi.org/10.1109/ACCESS.2024.3379150

J. Chen et al., “Dynamic routing optimization in software-defined networking based on a metaheuristic algorithm,” Journal Of Cloud Computing, vol. 13 p.41, Feb. 2024. https://doi.org/10.1186/s13677-024-00603-1 DOI: https://doi.org/10.1186/s13677-024-00603-1

M. Goyal et al. “Improving Convergence Speed and Scalability in OSPF: A Survey.” IEEE Communications Surveys & Tutorials, vol. 14, no. 2, pp. 443–463, 2012. https://doi.org/10.1109/surv.2011.011411.00065 DOI: https://doi.org/10.1109/SURV.2011.011411.00065

W. Wei et al., “Energy-Aware Traffic Engineering in Hybrid SDN/IP Backbone Networks.” Journal of Communica-tions and Networks, vol. 18, no. 4, pp. 559–566, Aug. 2016/ https://doi.org/10.1109/jcn.2016.000079. DOI: https://doi.org/10.1109/JCN.2016.000079

M. Caria and A. Jukan. “Link Capacity Planning for Fault Tolerant Operation in Hybrid SDN/OSPF Networks.” 2015 IEEE Global Communications Conference (GLOBECOM), 1 Dec. 2016, pp. 1–6. https://doi.org/10.1109/glocom.2016.7841957 DOI: https://doi.org/10.1109/GLOCOM.2016.7841957

M. Caria et al., “Divide and Conquer: Partitioning OSPF Networks with SDN,” 2015 IFIP/IEEE International Sym-posium on Integrated Network Management (IM), Ottawa, ON, Canada, 2015, pp. 467-474, https://doi.org/10.1109/inm.2015.7140324 DOI: https://doi.org/10.1109/INM.2015.7140324

R. Amin et al., “A survey on machine learning techniques for routing optimization in SDN,” IEEE Access, vol. 9, pp. 104582–104611, 2021. https://doi.org/10.1109/access.2021.3099092 DOI: https://doi.org/10.1109/ACCESS.2021.3099092

A. Abrol, P. M. Mohan, and T. Truong-Huu, “A Deep Reinforcement Learning Approach for Adaptive Traffic Rout-ing in Next-gen Networks,” arXiv.org, Feb. 2024, https://doi.org/10.48550/arxiv.2402.04515 DOI: https://doi.org/10.1109/ICC51166.2024.10622726

S. Mahajan, R. Harikrishnan, and K. Kotecha, “Adaptive Routing in Wireless Mesh Networks Using Hybrid Rein-forcement Learning Algorithm,” IEEE Access, vol. 10, pp. 107961–107979, 2022. https://doi.org/10.1109/ACCESS.2022.3210993 DOI: https://doi.org/10.1109/ACCESS.2022.3210993

C. Pan et al., “Inverse Coupled Simulated Annealing for Enhanced OSPF Convergence in IoT Networks,” Electron-ics, vol. 13, no. 22, pp. 4332–4332, Nov. 2024. doi: https://doi.org/10.3390/electronics13224332 DOI: https://doi.org/10.3390/electronics13224332

C. V. Murudkar and R. D. Gitlin, “Optimal-Capacity, Shortest Path Routing in Self-Organizing 5G Networks using Machine Learning,” Wireless and Microwave Technology Conference, pp. 1–5, Apr. 2019. https://doi.org/10.1109/WAMICON.2019.8765434 DOI: https://doi.org/10.1109/WAMICON.2019.8765434

P. Tshakwanda, S. T. Arzo, and M. Devetsikiotis, “Advancing 6G Network Performance: AI/ML Framework for Proactive Management and Dynamic Optimal Routing”, IEEE Open Journal of the Computer Society, vol 5, pp.303-314, 2024. https://doi.org/10.1109/ojcs.2024.3398540 DOI: https://doi.org/10.1109/OJCS.2024.3398540

S. Çoğay, M. Akkoç and G. Secinti, "ML-Assisted Dynamic Multi-Path Routing for Enhanced QoS," 2024 IEEE 29th International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (CAMAD), Athens, Greece, 2024, pp. 1-6, https://doi.org/10.1109/CAMAD62243.2024.10942960 DOI: https://doi.org/10.1109/CAMAD62243.2024.10942960