Research on SDN traffic anomaly detection technology based on knowledge graph

Suyang Li; Xiaojun Bai; Shenhang Wang

doi:10.1117/12.3009456

16 October 2023 Research on SDN traffic anomaly detection technology based on knowledge graph

Suyang Li, Xiaojun Bai, Shenhang Wang

Proceedings Volume 12803, Fifth International Conference on Artificial Intelligence and Computer Science (AICS 2023); 128033L (2023) https://doi.org/10.1117/12.3009456
Event: 2023 5th International Conference on Artificial Intelligence and Computer Science (AICS 2023), 2023, Wuhan, China

Abstract

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.

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Suyang Li, Xiaojun Bai, and Shenhang Wang "Research on SDN traffic anomaly detection technology based on knowledge graph", Proc. SPIE 12803, Fifth International Conference on Artificial Intelligence and Computer Science (AICS 2023), 128033L (16 October 2023); https://doi.org/10.1117/12.3009456

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available