The safe operation of smart substation is an important guarantee to ensure the stability of power supply. Aiming at the problems of substation data anomaly identification caused by large amount of substation data, complex data and high dimension, a smart substation anomaly data detection method based on K-means-SVM is proposed in this paper. Firstly, the unlabeled substation data is transformed into labeled data by K-means method, and then the unsupervised classification results provided by K-means are used as the training data of SVM. After SVM training, use the trained plane to test the two types of data obtained by K-means clustering, use the accurate data predicted by SVM to retrain the SVM segmentation plane, and iteratively update the SVM segmentation plane according to this method until the error number of SVM prediction data is not changed. This method can effectively improve the accuracy and efficiency of substation abnormal data identification, so as to improve the operation and maintenance safety and equipment maintenance ability.
|