
Research Article
Research on Network Fault Detection and Diagnosis Based on Deep Q Learning
@INPROCEEDINGS{10.1007/978-3-030-69072-4_43, author={Peipei Zhang and Mingxiao Wu and Xiaorong Zhu}, title={Research on Network Fault Detection and Diagnosis Based on Deep Q Learning}, proceedings={Wireless and Satellite Systems. 11th EAI International Conference, WiSATS 2020, Nanjing, China, September 17-18, 2020, Proceedings, Part II}, proceedings_a={WISATS PART 2}, year={2021}, month={2}, keywords={Heterogeneous wireless networks Deep Q learning Fault diagnosis Fault prediction}, doi={10.1007/978-3-030-69072-4_43} }
- Peipei Zhang
Mingxiao Wu
Xiaorong Zhu
Year: 2021
Research on Network Fault Detection and Diagnosis Based on Deep Q Learning
WISATS PART 2
Springer
DOI: 10.1007/978-3-030-69072-4_43
Abstract
In order to improve the efficiency and quality of service of the network, network convergence and the development of heterogeneous network have became inevitable. It is a challenge to detect and diagnose the various network faults efficiently in the complex network environment. To solve this problem, a network fault detection and diagnosis algorithm based on deep Q-learning is proposed. Combining deep learning and reinforcement learning model to classify network faults, we can classify some obvious network states via using less features, and filter irrelevant or redundant features at the same time. Results show that the algorithm can use less features to achieve higher classification accuracy, and the accuracy can reach 96.7%.