Research On Recognition And Compensation Method Of Abnormal Data In Electric Energy Measurement

With the rapid development of the smart grid and the comprehensive construction of the ubiquitous power grid,power system automation plays an increasingly important role in the grid.In order to collect accurate power data,ensure the safe operation of the power grid and improve the efficiency of the power supply system,promote the digital and intelligent development of the power system,it is of great significance to identify and correct the abnormal data of electric energy measurement.The main research content of this article:First,the k-means++ clustering algorithm is used to train and extract the statistical characteristics of the user's energy metering load data,and the elbow method is used to solve the problem of k-value determination in the clustering algorithm.According to the clustering results,the user load data of each category and the characteristics of user data of each category are obtained,which lays a foundation for the identification and compensation of abnormal data in energy measurement.Secondly,the BP neural network algorithm is used to identify abnormal data,and the extracted user load data features are used to train the BP neural network.Since the BP neural network has the problem of initial weights and thresholds,this paper uses genetics Algorithm optimization.Through the trained GA-BP neural network model,the user load data is judged and the abnormal type is determined.Finally,for different types of abnormal electricity data,the wavelet neural network algorithm and the compensation method based on the user's characteristic data are used to modify,respectively,to achieve the purpose of electricity metering user data compensation.The simulation method is used in this paper to verify the feasibility and effectiveness of the proposed method for identifying and compensating the abnormal data of electric energy measurement.