Enhancing Traffic Engineering with AI: Comparative Analysis of Mpls, Sd-WaN, and SRv6

Modern networks must manage dynamic traffic driven by 5G, IoT, and cloud services. Traditional traffic en- gineering (TE) technologies such as static routing cannot react in real time, leading to congestion and degraded performance. Predictive and adaptive capabilities come through artificial in- telligence (AI) to overcome these shortcomings.
This article compares three classic TE technologies: Segment Routing over IPv6 (SRv6), SoftwareDefined Wide Area Network- ing (SD-WAN), and Multiprotocol Label Switching (MPLS). Each has unique trade-offs: MPLS provides deterministic QoS at a high cost and limited flexibility; SD-WAN provides cost-effective flexibility but does not provide guaranteed QoS; SRv6 makes source routing programmable at the cost of header overhead and scalability demands. To address these drawbacks, we present a TE framework based on AI that leverages predictive analytics for predicting flows and RL to provide adaptive path selection choices. The model was evaluated with simulated enterprise-scale topologies supporting composite traffic mixtures of voice, video, and data. Outcomes demonstrate that AI-driven TE significantly reduces latency and packet loss while improving throughput and cost savings over static TE controls. Predictive rerouting, in particular, achieved double-digit latency savings, while RL dynamically distributed load between MPLS, SD-WAN, and SRv6 paths.
These findings confirm that AI-based TE enhances perfor- mance, scalability, and flexibility and is a suitable solution for future heterogeneous and high-traffic networks.

Modern networks must manage dynamic

1. T. Tian et al., “Traffic engineering in partially deployed seg- ment routing over IPv6 network with deep reinforcement learn- ing,” IEEE/ACM Trans. Netw., vol. 28, no. 3, pp. 1573–1586, 2020, doi:10.1109/TNET.2020.2987866. [Google Scholar] [Crossref]

2. A. Botta et al., “Adaptive overlay selection at the SD-WAN edges: A reinforcement learning approach with networked agents,” Computer Net- works, vol. 243, Art. 110310, 2024, doi:10.1016/j.comnet.2024.110310. [Google Scholar] [Crossref]

3. X. Pei et al., “Enabling efficient routing for traffic engineering in SDN with deep reinforcement learning,” Computer Networks, vol. 241, Art. 110220, 2024, doi:10.1016/j.comnet.2024.110220. [Google Scholar] [Crossref]

4. M. Masood et al., “Enhanced optimisation of MPLS network traf- fic using a novel adjustable Bat algorithm with loudness op- timizer,” Results in Engineering, vol. 20, Art. 104774, 2025, doi:10.1016/j.rineng.2025.104774. [Google Scholar] [Crossref]

5. D. Wu and L. Cui, “A comprehensive survey on Segment Routing Traffic Engineering,” Digital Commun. Networks, vol. 9, no. 4, pp. 990–1008, 2023, doi:10.1016/j.dcan.2022.02.006. [Google Scholar] [Crossref]

6. M. A. Ouamri et al., “A comprehensive survey on software-defined wide area network (SD-WAN): principles, opportunities and future chal- lenges,” J. Supercomputing, vol. 81, Art. 291, 2025, doi:10.1007/s11227- 024-06718-1. [Google Scholar] [Crossref]

7. I. Grgurevic et al., “Analysis of MPLS and SD-WAN network per- formances using GNS3,” in Future Access Enablers for Ubiqui- tous and Intelligent Infrastructures, LNCS 12703, 2021, pp. 77–90, doi:10.1007/978-3-030-78459-1 6. [Google Scholar] [Crossref]

8. L. Borgianni et al., “From MPLS to SD-WAN to ensure QoS and QoE in cloud-based applications,” in IEEE NetSoft, 2023, pp. 366–369, doi:10.1109/NetSoft57336.2023.10175470. [Google Scholar] [Crossref]

9. Q. M. Alam et al., “Towards AI/ML-driven network traffic engineering,” in Proc. 4th Int. Conf. AI-ML Systems (AI-MLSys), 2024 (to appear 2025), doi:10.1145/3703412.3703436. [Google Scholar] [Crossref]

10. S. Troia et al., “On deep reinforcement learning for traffic engineering in SD-WAN,” IEEE J. Sel. Areas Commun., vol. 39, no. 7, pp. 1972–1985, 2021, doi:10.1109/JSAC.2020.3041385. [Google Scholar] [Crossref]

11. J. Lu et al., “Graph-based reinforcement learning for software-defined networking traffic engineering,” J. King Saud Univ. – Comput. Inf. Sci., vol. 37, Art. 119, 2025, doi:10.1007/s44443-025-00133-z. [Google Scholar] [Crossref]

12. R. Kablaoui et al., “Network traffic prediction by learning time series as images,” Eng. Sci. Technol. Int. J., vol. 36, Art. 101754, 2024, doi:10.1016/j.jestch.2024.101754. [Google Scholar] [Crossref]

13. M. J. F. Alenazi, “An effective deep-Q learning scheme for QoS improvement in physical layer of software-defined net- works,” Physical Communication, vol. 61, Art. 102387, 2024, doi:10.1016/j.phycom.2024.102387. [Google Scholar] [Crossref]

14. Y. Zheng et al., “Flow-by-flow traffic matrix prediction methods: achiev- ing accurate, adaptable, low cost results,” Computer Commun., vol. 194, pp. 348–361, 2022, doi:10.1016/j.comcom.2022.07.052. [Google Scholar] [Crossref]

15. Y. Yang, “A network traffic forecasting method based on SA-optimized ARIMA-BP neural network,” Computer Networks, vol. 193, Art. 108102, 2021, doi:10.1016/j.comnet.2021.108102. [Google Scholar] [Crossref]

16. F. Aktas et al., “AI-enabled routing in next generation networks: A survey,” Alexandria Eng. J., vol. 120, no. 3, pp. 449–474, 2025, doi:10.1016/j.aej.2025.01.095. [Google Scholar] [Crossref]

17. X. Wang et al., “Traffic Engineering Optimization in Hybrid Software- Defined Networks: A mixed integer nonlinear programming model and heuristic algorithm,” Int. J. Network Management, vol. 35, no. 3, 2025, doi:10.1002/nem.70017. [Google Scholar] [Crossref]

18. S. M. S. Bukhari et al., “Network traffic prediction: using AI to predict and manage traffic in high-demand IT networks,” Policy Res. J., vol. 2, no. 4, p. 1706, 2024. [Google Scholar] [Crossref]

19. M. Gupta and P. Kumar, “Traffic optimization in SD-WAN using AI and segment routing,” Internet of Things J., vol. 10, no. 1, pp. 1–15, 2023, doi:10.1016/j.iot.2023.100789. [Google Scholar] [Crossref]

20. R. Kołakowski et al., “Hierarchical Traffic Engineering in 3D Networks Using QoS-Aware [Google Scholar] [Crossref]

21. Graph-Based Deep Reinforcement Learning,” Electronics, vol. 14, no. 5, Art. 1045, 2025, doi:10.3390/electronics14051045. [Google Scholar] [Crossref]

22. D. Aureli et al., “Intelligent Link Load Control in a Segment Routing network via Deep Reinforcement Learning,” in ICIN, 2022, doi: (ICIN). [Google Scholar] [Crossref]

23. A. Abdelsalam et al., “SRPerf: a Performance Evaluation Frame- work for IPv6 Segment Routing,” IEEE TNSM, Dec. 2020, doi:10.1109/TNSM.2020.3030084. [Google Scholar] [Crossref]

24. A. Abdelsalam et al., “Pushing Network Programmability to the limits with SRv6 uSIDs and P4,” in EuroP4, 2020. [Google Scholar] [Crossref]

25. C. Scarpitta et al., “High performance delay monitoring for SRv6-based SD-WANs,” IEEE TNSM, 2023, doi:10.1109/TNSM.2023.3300151. [Google Scholar] [Crossref]

26. M. A. Habib et al., “Traffic Steering for 5G Multi-RAT Deployments using Deep Reinforcement Learning,” arXiv preprint arXiv:2301.05316, 2023. [Google Scholar] [Crossref]

27. J. Lu et al., “Graph-based reinforcement learning for software**-defined networking traffic engineering,” J. King Saud Univ. – Comput. Inf. Sci., 2025, doi:10.1007/s44443025-00133-z. [Google Scholar] [Crossref]

28. R. Kołakowski et al., “Hierarchical Traffic Engineering in 3D Net- works Using QoSAware Graph-Based DRL,” Electronics, 2025, doi:10.3390/electronics14051045. [Google Scholar] [Crossref]

• Assessment of the Role of Artificial Intelligence in Repositioning TVET for Economic Development in Nigeria
• Teachers’ Use of Assure Model Instructional Design on Learners’ Problem Solving Efficacy in Secondary Schools in Bungoma County, Kenya
• “E-Booksan Ang Kaalaman”: Development, Validation, and Utilization of Electronic Book in Academic Performance of Grade 9 Students in Social Studies
• Analyzing EFL University Students’ Academic Speaking Skills Through Self-Recorded Video Presentation
• Major Findings of The Study on Total Quality Management in Teachers’ Education Institutions (TEIs) In Assam – An Evaluative Study