Voltage Deviation Forecasting with Improved BP Neural Network
Yong Zhang, Chen Fang, Wang Zhifang, Xiu Yang · 2018
This paper presents an accurate model to forecast voltage deviation with improved BP neural network, which concerns with the meteorological factors. The proposed method is a combination of PCA dimension reduction, AP clustering and BP neural network. In this paper, the PCA is used to reduce the dimension of the input data, and the AP clustering is employed to classify input data into clusters. Finally a forecast of voltage deviation is made by using BP neural network. The proposed method is successfully applied to real data. A comparison is made between the proposed method and the other methods. The practical application results proved that the mean absolute percentage error(MAPE) of the proposed method is 3.06%,and the probability of the relative error less than 3% is 54.17%,which are obviously better than that of the other methods.