Calculating theoretical line losses based on improved minimum enclosing ball vector machine

Abstract

In order to overcome the low accuracy defect of the traditional theoretical line losses calculation method in distribution system, an intelligent calculation method based on improved minimum enclosing ball vector machine (MEBVM) is proposed. In this intelligent calculation method, the theoretical line losses calculation is abstracted into multiple regression analysis. All kinds of line losses impact factors have been as inputs, and the theoretical line losses calculation result has been as outputs. In this intelligent calculation method, to solve the multiple regression analysis by improved MEBVM, a large number of lines data that whose theoretical line losses were known, is constructed into a sample set that is trained by improved MEBVM, and then the fitting function of multiple regression analysis that is as the training result, is obtained. The fitting function is used to calculate the unknown line losses. In improved MEBVM training process, to enhance the calculation accuracy of improved MEBVM, the optimal training parameters of improved MEBVM are dynamic searched by particle swarm optimization algorithm (PSO). Finally, the experiment indicates the effectiveness of intelligent theoretical line losses calculation method based on improved MEBVM Compared with the traditions, the intelligent calculation method has better performance in calculating accuracy.