Consumers’ Phase Identification in Low Voltage Station Area Based on Wavelet Analysis of Consumption Data

When balancing the three-phase load in the low-voltage station area, it is necessary to identify and adjust the phase of some users. Due to the reality that power company only stores the users' power consumption data, this paper proposed a method to extract the data features through the wavelet analysis of the electric consumption data. The features are extracted in both three phases end and the consumer end at the same time, and the similarity analysis is carried out with the features to identify the user mounting phase. Based on the real data of a low voltage station in S Province, the daily power data of each phase of distribution transformer is generated by fitting, and then the above method is applied to the phase identification of all consumers in the station area, and the recognition accuracy is close to 60%. Finally, the factors that affect the accuracy of phase identification are analyzed, and it is concluded that the fitting accuracy of each phase electric consumption data and the sampling period of consumers’ quantity data will affect the accuracy of phase identification.