Data Prediction and Real-time State Estimation of Distribution Network

Abstract

With the improvement of real-time measurement technology in distribution network, the data collected by power dispatching department is explosively growing. As a result, the real-time detection and analysis of the operation status of distribution network is facing new challenges. In this paper, a prediction model based on the combination of fuzzy c-means (FCM) algorithm and BP neural network is proposed to describe the range of future distribution network operation data. The purpose of this work is to provide a reference range for real-time operation state analysis. Then, considering the problem of massive measurement data in distribution network, a robust state estimation method based on exponential function weighted least squares (EFWLS) is proposed, which has better accuracy and efficiency than traditional weighted least squares (WLS) method. Finally, the accuracy of the prediction model is verified by comparing the predicted data with the real data, and the advantages of the proposed state estimation method are verified by comparing the results of different methods.