Real-Time Load Identification by Active Power Feature Extraction and Switching Detection

With the intelligent development of the power system, load identification becomes an important task. A noninvasive household load identification method is proposed in this paper, which can be used to detect the load switching moments and identify the types of loads. A calculation method of feature value is proposed based on active power. A template method is proposed to detect the jumping of the feature curve, which can determine the load switching moments robustly and accurately. The types of loads can be identified by a threshold value method. The results show that the method can accurately determine the load switching moments and identify the types of loads, and it also has good robustness.