Future Architecture of Knowledge-Defined Networking (KDN)

In this paper, the concept and architecture of Knowledge-Defined Networking (KDN) are explored as a new paradigm of network management that integrates artificial intelligence and machine learning to enable intelligent and adaptive network behavior. The relevance of the research is driven by the limitations of traditional and Software-Defined Networking (SDN) systems in the face of modern challenges such as exponential traffic growth, dynamic conditions, and rising operational costs. KDN introduces a knowledge plane that optimizes resource allocation, automates decision-making, and enhances security in real-time. Despite the fact that today the SDN (Software-Defined Network) technology is very popular, in which the centralized control function allows to review all processes occurring in the network. At the time, its appearance really turned out to be a breakthrough, and now some experts are inclined to believe that the next stage of network evolution will be the Knowledge-Defined Network - a network defined by knowledge, operating on the basis of machine learning algorithms. Routing, resource allocation, network function virtualization (NFV), service function chaining (Service Function Chaining, SFC), anomaly detection, network load analysis - all these points can be taken on by KDN. The study aims to examine the structural and functional features of KDN and analyze the interaction of its five logical planes ‒ data, control, monitoring, knowledge, and applications ‒ to achieve a high degree of automation and adaptability.The research methods include literature analysis, conceptual modeling, and a comparative evaluation of KDN and SDN architectures. The results. The study analyzed the architecture of KDN, comprising five logical planes: data, control, monitoring, knowledge, and applications. The findings demonstrate that integrating the knowledge plane significantly enhances automation and adaptability within the network. The novelty of this work lies in being one of the first attempts to conduct a systematic analysis of the Knowledge-Defined Networking (KDN) concept in the context of Russian-language scientific literature. The research addresses an existing gap in domestic science, offering a unique perspective on KDN capabilities considering local conditions and applications. The theoretical significance of the work lies in establishing a foundation for the study and integration of machine learning methods into network management systems.