Research on SDN traffic anomaly detection technology based on knowledge graph
Suyang Li, Xiaojun Bai, Shenhang Wang · 2023
SDN (Software Defined Networking) is a novel network architecture that allows for flexible configuration and centralized control of resources. However, it also presents new fault problems, particularly in high data volumes and complex topologies where traditional anomaly detection algorithms often need to be revised. To address this issue, we propose a knowledge graph-based approach to SDN fault detection. By leveraging the interpretability and expressiveness of knowledge graphs and the SDN controller’s global information, we construct and continuously update a knowledge graph that enables real-time monitoring and analysis of the network state. Finally, we detect and diagnose the abnormal conditions in the network through graph inference. The experimental results indicate that the knowledge graph-based SDN fault detection algorithm demonstrates high accuracy and efficiency, effectively enhancing SDN networks’ operational stability and security.