A Grey Wolf Algorithm Optimized SVM Method for Voltage Sag Identification in Distribution Systems

For the voltage sag caused by short-circuit fault, transformer switching and induction motor starting in distribution network, an optimized support vector machine method based on Gray Wolf algorithm is proposed for voltage sag identification. The empirical mode decomposition method is used to analyze the voltage sag signal, obtain an inherent mode function set (IMFs), and calculate the energy entropy of each order IMF as the eigenvector. In order to solve the problem that the traditional support vector machine is easy to fall into local optimization in the process of optimization, a method of optimizing the penalty factor and kernel function parameters of support vector machine (SVM) through gray wolf algorithm (GWO) is proposed, a GWO-SVM classifier is constructed, and then the extracted feature vector is input into the GWO-SVM classifier to train and recognize the samples, So as to realize the automatic classification and identification of different types of voltage sag sources. The simulation results show the effectiveness of the extracted feature vector and GWO-SVM classifier. Compared with other five traditional methods, it is verified that it has fast speed and high precision.