A Load Modeling Method Based on Machine Learning
| Autor: | Rui-Peng Diao, Yi-Long Li, Chao-Liang Wang, Wei-Liu, Chi-Jiang, Chen-Hui Zhou, Qing-Juan Wang, Xiao-Qiong Huang, Lei Song, Chun-Guang Lu, Yi Ding |
|---|---|
| Rok vydání: | 2021 |
| Předmět: | |
| Zdroj: | Journal of Physics: Conference Series. 2087:012076 |
| ISSN: | 1742-6596 1742-6588 |
| Popis: | More and more high-power impact loads in the power grid are put into use. When the power is impacted, these loads will cause the power grid bus voltage fluctuations and reduce the power quality. Therefore, in order to accurately analyze the changes in the power system, it is particularly important to establish a reasonable impact load model. This paper takes the impact load data generated by the CT machine during exposure as an example to analyze the characteristics of the impact load. Based on the active power characteristics of the impact load, machine learning methods (such as support vector machines and long and short-term memory networks) are introduced into the impact load modeling, and the power waveform change law of the impact load is accurately established by this method. Finally, the effectiveness of the method is verified by simulation. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|