Non-Functional Electrical Scene Extraction Method Considering Spatiotemporal Correlation

In recent years, the power grid structure and load type have undergone profound changes, and the requirements for power quality have gradually increased, and the characteristics of user-side load, including reactive power and power factors, have also changed. Therefore, in order to better optimize reactive power allocation, this paper proposes a method to extract inactive power scenes considering temporal and spatial correlation, and conducts experiments based on the operation data of three transformers in a certain area of Shanghai. The results show that the proposed algorithm based on LE-GMM for extracting the typical day scene of inactive electricity considering the temporal and spatial correlation has a good ability to fit the actual operation scene.