Метод оптимізації розподілу трафіку в багаторівневих SDN- мережах для зниження затримки доставки пакетів

Abstract

The thesis examines the process of traffic distribution management and quality of service assurance in multi-level software-defined networks (SDN). The aim of the research was to develop a comprehensive optimization method aimed at minimizing packet delivery delays and providing QoS guarantees. The research methods used included system analysis, graph theory for topology modeling, mathematical optimization methods, and simulation modeling in Mininet and AnyLogic environments to verify the proposed solutions. The results confirmed the effectiveness of combining policy-based dynamic routing (iPBR) and hierarchical queueing (HTB) for stabilizing data transmission time metrics. The novelty of the research lies in the improvement of resource allocation algorithms in multi-level SDN structures, which allows adaptive changes to traffic routes depending on the current network load. The practical significance of the results obtained lies in the possibility of their implementation in the design of data centers, the development of software for Linux-based switching equipment, and the modernization of Internet providers' traffic management systems.The thesis examines the process of traffic distribution management and quality of service assurance in multi-level software-defined networks (SDN). The aim of the research was to develop a comprehensive optimization method aimed at minimizing packet delivery delays and providing QoS guarantees. The research methods used included system analysis, graph theory for topology modeling, mathematical optimization methods, and simulation modeling in Mininet and AnyLogic environments to verify the proposed solutions. The results confirmed the effectiveness of combining policy-based dynamic routing (iPBR) and hierarchical queueing (HTB) for stabilizing data transmission time metrics. The novelty of the research lies in the improvement of resource allocation algorithms in multi-level SDN structures, which allows adaptive changes to traffic routes depending on the current network load. The practical significance of the results obtained lies in the possibility of their implementation in the design of data centers, the development of software for Linux-based switching equipment, and the modernization of Internet providers' traffic management systems.