COMBINING GRAPH-BASED MODEL AND EVOLUTIONARY ALGORITHM FOR SOLVING PARETO-OPTIMAL ROUTING PROBLEMS

Abstract

This paper presents a mathematical model for traffic management in communication networks based on multi-criteria optimization. The model is built on network graphs and considers Quality of Service (QoS) indicators — such as delay, throughput, and reliability — as independent optimization objectives. It incorporates AI-driven techniques, including reinforcement learning and graph neural networks, to enable adaptive routing control. The model is implemented and simulated in Python under both baseline and failure scenarios. A Pareto-optimal framework is used to develop an efficient decision-making algorithm for complex network environments. The results demonstrate the model’s stability and high adaptability to changes in network topology.

Keywords

References

1. Kleinrock L. Queueing Systems. Volume 2: Computer Applications. Wiley, 1976.
2. Li X., Floudas C. A. Multiobjective optimization problems with equilibrium constraints // Journal of Optimization Theory and Applications. – 2006.
3. Ahuja R. K., Magnanti T. L., Orlin J. B. Network flows: theory, algorithms, and applications. Prentice Hall, 1993.
4. Marler R. T., Arora J. S. Survey of multi - objective optimization methods for engineering // Structural and Multidisciplinary Optimization. – 2004.
5. Deb K. Multi - objective optimization using evolutionary algorithms. John Wiley & Sons, 2001.
6. Sutton R. S., Barto A. G. Reinforcement Learning: An Introduction. MIT Press, 2018.
7. Bäck T. Evolutionary algorithms in theory and practice. Oxford University Press, 1996.
8. Alsabaan M., Naik K., Goel N., Nayak A. Real - time traffic routing using intelligent transportation systems // IEEE Transactions on Intelligent Transportation Systems, 2013.
9. Zhou J. et al. Graph neural networks: A review of methods and applications // AI Open. – 2020.
10. Attar R. et al. Multipath routing for QoS - aware traffic engineering in MPLS networks // Scientific Research Publishing, 2017.
11. Wu Z. et al. A comprehensive survey on graph neural networks // IEEE Transactions on Neural Networks and Learning Systems, 2020.
12. Liu Y. et al. Multi - objective genetic algorithm for routing optimization // PLOS ONE, 2019.
13. Mirzaeva M. Study of Neural Networks in Telecommunication Systems // Conference Proceedings, 2021.