Deep Reinforcement Learning Based Fast Anomaly Detection and Localization for Programmable Networks

Peng Zhan, Guangyi Qin, Xingxin Qian, Xiong Wang, Jing Ren, Zirui Zhuang, Shizhong Xu

Abstract

The fast anomaly detection and localization is essential for network management, however, it is also very challenging for the current networks due to the lack of flexible control and telemetry capabilities. Fortunately, the maturity of Deep Reinforcement Learning (DRL) and programmable networking technologies could shed a light on realizing fast and intelligent anomaly detection and localization. In the paper, we design a fast anomaly detection and localization system for programmable networks by leveraging the in-band network telemetry and flexible control capabilities of programmable networks. Based on the system, we propose a DRL-based abnormal link detection and localization algorithm. It can iteratively infer abnormal links based on the ingress-to-egress performance metrics of flows and the one-hop performance metrics of the flows on the already identified abnormal links. The simulation results show that our proposals can detect and localize link anomalies in a matter of seconds to tens of seconds with low network telemetry overhead.
BibTeX
@inproceedings{zhan2023deep,
  author = {Peng Zhan and Guangyi Qin and Xingxin Qian and Xiong Wang and Jing Ren and Zirui Zhuang and Shizhong Xu},
  title = {{Deep Reinforcement Learning Based Fast Anomaly Detection and Localization for Programmable Networks}},
  booktitle = {ICC},
  year = {2023},
  doi = {10.1109/icc45041.2023.10278843},
}

Loading related content...

Figure