Research on Abnormal Power Consumption Detection Technology Based on Decision Tree and Improved SVM

The main purpose of abnormal power consumption detection for power users is to maintain the legitimate rights and interests of normal users, improve the economic benefits of power grid companies, and thereby reduce non-technical losses (NTL). In order to realize the rational use of user-side data and improve the efficiency of power audit, this article proposes an improved SVM power theft detection model based on decision tree. First of all, to address the problem of less electricity stealing data, this article combines convolutional neural networks (CNN) and generative adversarial networks (GAN) for data generation, and uses the powerful feature extraction function of CNN to extract the features of different stealing methods to guide GAN. Then the improved support vector machine (SVM) model based on decision tree (DT) detects user data. When classifying, it combines SVM and KNN for classification, which solves the point of SVM near the decision plane. For the problem of low classification accuracy, simulation experiments finally verified the effectiveness of the proposed model.