Identification of Voltage Sag Source in Distribution Network Based on BAS-SVM
Voltage sag is a kind of power quality problem. In order to improve the identification accuracy of different voltage sag disturbance sources, a voltage sag source identification method based on beetle antennae search (BAS) and support vector machine (SVM) is proposed. In this paper, the improved S-t...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
State Grid Energy Research Institute
2022-05-01
|
| Series: | Zhongguo dianli |
| Subjects: | |
| Online Access: | https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202003138 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Voltage sag is a kind of power quality problem. In order to improve the identification accuracy of different voltage sag disturbance sources, a voltage sag source identification method based on beetle antennae search (BAS) and support vector machine (SVM) is proposed. In this paper, the improved S-transform is applied to the time-frequency reversible analysis of voltage sag signal, and the related amplitude curve and 16 characteristic indexes are extracted. The penalty factor and kernel function parameters of SVM are optimized by BAS, and a BAS-SVM classifier is constructed. The extracted characteristic index data is normalized and divided into training sample set and test sample set by 5-fold cross validation, which are input into the new classifier to realize the recognition of different types of voltage sag sources in distribution network. Finally, the simulation results show that the classifier has better classification effect. |
|---|---|
| ISSN: | 1004-9649 |