Distribution area line loss detection method and device based on feature selection and machine learning

The invention discloses a transformer area line loss detection method and device based on feature selection and machine learning, and the method comprises the steps: S01, extracting original electrical feature indexes from a historical data sample of a transformer area, and constructing an electrical feature index set; s02, clustering the data in the electrical characteristic index training set, and calculating the correlation degree between each electrical characteristic index and the line loss rate; s03, selecting a final electrical characteristic index subset from the electrical characteristic index set according to a clustering processing result and a correlation degree result; and S04, inputting the electrical characteristic index subset into a machine learning training model for training to obtain a transformer area line loss detection model so as to realize transformer area line loss detection. The method has the advantages of being simple in implementation method, low in cost, capable of giving consid