Research on Anomaly Detection Method for electro-data

In order to overcome the problem of low computational efficiency caused by data mining anomaly detection method and insensitivity to abnormal data with clustered characteristics, a new anomaly detection method for electro-data is proposed, this method uses an electric anomaly detection model based on SCiForest algorithm to test whether the user's electricity consumption data is abnormal or not, and combines with daily load curve data for verification. The result shows that the method can not only effectively detect scattered anomalies, but also detect the clustered anomalies. In the detection scenario of electricity consumption data with clustered characteristics, the method is more effective in testing whether the user's electricity consumption data is abnormal or not.