DEVELOPMENT OF A MULTI-AGENT SYSTEM FOR DYNAMIC SDN CONTROL
Article Sidebar
Main Article Content
Abstract
Relevance. Currently, the volume of transmitted information and the quality requirements for its transmission are increasing. Recently, Software-Defined Networking (SDN) technology has been gaining popularity; however, challenges arise related to the uncertainty of the SDN network state and its elements, as well as the integration of various data streams that have different quality delivery requirements. Therefore, the task of utilizing an intelligent multi-agent system (MAS) for managing SDN networks becomes relevant. The object of research is the process of managing SDN networks. The subject of the research is models and methods for managing SDN networks. The purpose of this paper is to develop a model for the interaction of intelligent agents to ensure the effective functioning of multi-agent systems (MAS) in dynamic management of SDN. Research results. Using the analytical framework of probabilistic temporal graphs, mathematical models have been developed for two options for coordinating agents in the dynamic management of SDN networks: a system with a coordinating agent and a self-regulating MAS. Based on the analysis of the obtained probabilistic temporal characteristics of various coordination options, it has been established that self-regulating MAS are advisable in situations where agents have sufficient knowledge to solve the overwhelming majority of emerging tasks, where these solutions are highly likely to be correct, the number of agents in the system is small, and there is a high probability of effective control over the decisions made.
Article Details
References
Zhong, Qin and Zhang, Zhaohui (2023), “Traffic Load Balancing and Routing Optimization Algorithms in Sdn-Driven Networks”, Available at SSRN: https://ssrn.com/abstract=4576872 or http://dx.doi.org/10.2139/ssrn.4576872
Tache, M. D., Păscuțoiu, O., and Borcoci, E. (2024), “Optimization Algorithms in SDN: Routing, Load Balancing, and Delay Optimization”, Applied Sciences, vol. 14(14), article number: 5967, doi: https://doi.org/10.3390/app14145967
Guo, A., and Yuan, C. (2021), “Network Intelligent Control and Traffic Optimization Based on SDN and Artificial Intelligence”, Electronics, vol. 10(6), article number: 700, doi: https://doi.org/10.3390/electronics10060700
Hussain, M., Shah, N., Amin, R., Alshamrani, S. S., Alotaibi, A., and Raza, S. M. (2022), “Software-Defined Networking: Categories, Analysis, and Future Directions”, Sensors, vol. 22(15), article number: 5551, doi:
https://doi.org/10.3390/s22155551
Arzo, S. T., Akhavan, Z., Esmaeili, M., Devetsikiotis, M., and Granelli, F. (2022), “Multi-agent-based traffic prediction and traffic classification for autonomic network management systems”, Future Internet, vol. 14(8), article number: 230. doi: https://doi.org/10.3390/fi14080230
Arzo, S. T., Bassoli, R., and Granelli, F. (2021), “Multi-agent based autonomic network management architecture”, IEEE Transactions on Network and Service Management, vol. 18(2), pp. 1092–1106, doi: https://doi.org/10.1109/TNSM.2021.3059752
Goteti, D. and Reddy V. K. (2025), “AI-driven routing pipeline in SDN: Federated and multi-agent control”, Frontiers in Artificial Intelligence, article number: 1685155. doi: https://doi.org/10.3389/frai.2025.1685155
Yuan, T., da Rocha Neto, W., Rothenberg, C. E., Obraczka, K., Barakat, C., and Turletti, T. (2021), “Dynamic controller assignment in SDN through multi-agent deep reinforcement learning”, IEEE Transactions on Network and Service Management, vol. 18(2), pp. 1230–1244. doi: https://doi.org/10.1109/TNSM.2020.3047765
Kunz, T. and Muthukumar, K. (2017), “Comparing OpenFlow and NETCONF when interconnecting data centers”, Proc. Int. Conf. on Network Protocols (ICNP), 2017-October, 8117598, doi: https://doi.org/10.1109/ICNP.2017.8117598
Kalinin, Y., Koliesnik, I., Kuchuk, H., Kuchuk, N., Polyashenko, S. and Medvid, M. (2025), “Principles of Diagnostics of Complex Systems using Structural Automaton Algebra and Taking into Account Signal Time Coordination”, 2025 IEEE 6th Khpi Week on Advanced Technology (Khpiweek 2025), doi: https://doi.org/10.1109/KhPIWeek61436.2025.11288711
Aryan, R., Yazidi, A., Bouhoula, A. and Engelstad, P.E. (2025), “A formal technique for automatic resolution of OpenFlow anomalies”, International Journal of Information Security, vol. 24(4), 181, doi: https://doi.org/10.1007/s10207-025-01035-x
Rezanov, B., and Kuchuk, H. (2023), “Model of elemental data flow distribution in the Internet of Things supporting Fog platform”, Innovative Technologies and Scientific Solutions for Industries, vol. 2023(3), pp. 88–97, doi: https://doi.org/10.30837/ITSSI.2023.25.088
Mozhaev, O., Kuchuk, H., Kuchuk, N., Mykhailo, M. and Lohvynenko, M. (2017), “Multiservice network security metric”, 2nd International Conference on Advanced Information and Communication Technologies, AICT 2017 – Proceedings, pp. 133–136, doi: https://doi.org/10.1109/AIACT.2017.8020083
Kuchuk, H., Kalinin, Y., Dotsenko, N., Chumachenko, I. and Pakhomov, Y. (2024), “Decomposition of integrated high-density IoT data flow”, Advanced Information Systems, vol. 8, no. 3, pp. 77–84, doi: https://doi.org/10.20998/2522-9052.2024.3.09
Li, G., Wang, X., & Zhang, Z. (2019), “SDN-based load balancing scheme for multi-controller deployment”, IEEE Access, 7, 39612–39622. doi: https://doi.org/10.1109/ACCESS.2019.2906683
Kuchuk, N., Kashkevich, S., Radchenko, V., Andrusenko, Y. and Kuchuk, H. (2024), “Applying edge computing in the execution IoT operative transactions”, Advanced Information Systems, vol. 8, no. 4, pp. 49–59, doi: https://doi.org/10.20998/2522-9052.2024.4.07
Agarwal, S., Kodialam, M., & Lakshman, T. V. (2016), “Multi-controller based software-defined networking: A survey”, Computer Networks, 103, 122–135. doi: https://doi.org/10.1016/j.comnet.2016.04.015