Low-Frequency Oscillation Pattern Recognition Based on Wavelet Packet and SVM
| Autor: | Anle Li, Hui Xiao, Xu He, Ping Liu, Hui He, Hongmang Hu |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Computer science
business.industry Network packet 020209 energy Pattern recognition 02 engineering and technology Wavelet packet decomposition Support vector machine Electric power system ComputingMethodologies_PATTERNRECOGNITION Wavelet Principal component analysis 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Artificial intelligence Low-frequency oscillation business Eigenvalues and eigenvectors |
| Zdroj: | 2019 IEEE 3rd Conference on Energy Internet and Energy System Integration (EI2). |
| DOI: | 10.1109/ei247390.2019.9061841 |
| Popis: | Traditional low-frequency oscillation mode identification methods have complex calculation processes and poor real-time performance, which make it difficult to meet the computational requirements of pattern classification of low-frequency oscillation in complex power system. Based on wavelet packet and support vector machine (SVM), a more simple and convenient method of identification and classification is proposed in this paper. The low-frequency oscillation signal is selected as the research object, and the wavelet packet decomposition of the signal in different modes is used to extract the energy eigenvector samples in this method. To achieve low-frequency oscillation mode identification classification, the principal component analysis (PCA) is used to reduce the energy eigenvectors and construct the SVM pattern recognition classifier. The simulation results show that this method can realize the classification of low-frequency oscillation modes in power system more quickly and accurately. The method proposed in this paper has good application prospects. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|