Improving correlation-based consumer phase identification for incomplete data

With the roll-out of smart meters, data-driven methods based on smart meter data have become an important technical direction for consumer phase identification in low-voltage distribution network (LVDN). However, as a result of poor communication quality, human error, electricity theft and other reasons, the obtained power consumption data of consumers is incomplete and cannot fully reflect the power consumption of LVDN, which affects the recognition performance of the existing consumer phase identification methods. Under this background, this paper proposes a consumer phase identification algorithm based on the correlation characteristics to improve the accuracy of consumer phase identification with incomplete data. Firstly, the correlation characteristics among consumers and that between consumers and three-phase buses on the low voltage side of distribution transformer are deduced. Then, a preliminary phase identification method is proposed according to the correlation characteristics between consumers and three-phase buses on the low voltage side of distribution transformer. Finally, the correlation characteristics among consumers are used to correct the preliminary identification results. The proposed algorithm is applied on a real-world LVDN in Guangdong, China. The comparison analysis between the proposed method and other published methods are also investigated. The results indicate that the proposed method effectively increases the consumer phase identification accuracy compared with the published methods when the obtained power consumption data of consumers is incomplete.