Prediction of Line Loss Rate in Power Supply Area Based on Grey Wolf Algorithm Optimized Support Vector Machine

Abstract

in order to comprehensively and accurately evaluate the line loss level in power supply area, a line loss prediction method based on Gray Wolf algorithm and improved support vector machine is proposed. Through massive station data, 3 electrical indicators are determined, and finally the best electrical characteristic index system is determined. Secondly, the prediction performance of the improved model is calculated and analyzed by using the fivefold cross validation method. The gray wolf algorithm is used to improve the support vector machine method for learning and prediction. The convergence and prediction accuracy of this method are compared. The traditional support vector machine is analyzed and the optimal network structure is determined. The problem of low accuracy of line loss rate prediction caused is solved. In this paper, an example of a certain area is simulated and analyzed. The results show that the improved support vector machine model based on Gray Wolf algorithm is a better prediction model.