Abstract Heterogeneous data collected by a variety of measurement devices in the distribution network constitute the data source for state estimation. Depth identification of measurement data is the primary task to improve the accuracy of state estimation. In this paper, an identification and correction method for bad data in measured data is proposed. The method firstly uses primary identification based on new information sequence and density-based spatial clustering of applications with noise (DBSCAN) method, and then performs secondary identification according to the time inertia of measured data. Finally, the modified long-short term memory (LSTM) algorithm is used to correct the abnormal data. A simulation platform is built to verify the effectiveness of the proposed method.
ZHANG Shuo,WU Lizhen. Distribution network state estimation considering bad data identification and correction[J]. Electrical Engineering, 2022, 23(11): 1-5.
2022, Vol. 23 
