Classification For Multiple Power Quality Disturbances Based On Deep Forest
45TH ANNUAL CONFERENCE OF THE IEEE INDUSTRIAL ELECTRONICS SOCIETY (IECON 2019)(2019)
摘要
In order to solve the problem of power quality disturbance which is increasingly prominent in smart power grid, a method of power quality disturbance classification based on Deep Forest( gcForest) was proposed. Firstly, disturbance feature are automatically extracted from the original dataset of power quality disturbance waveforms by the Multi-Grained Scanning and the feature representation of the original dataset is obtained. Secondly, the depth feature is acquired by the Cascade Forest. Finally, Cascade Forest procedure will be repeated till convergence of validation performance to achieve power quality disturbance classification. In addition, the robustness of the proposed method is verified by using different sampling frequency and adding noise to the data. The results indicate that the method proposed can accurately identify 9 types of power quality disturbances including 2 complex disturbances, and have good anti-noise capability.
更多查看译文
关键词
power quality disturbance, feature extraction, disturbance identification, Cascade Forest, Multi-Grained Scanning
AI 理解论文
溯源树
样例
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要