基于GA-RBF神经网络的电力系统短期负荷预测

针对短期负荷预测问题,提出了一种遗传算法-径向基函数(GA-RBF)神经网络负荷预测方法,解决传统径向基函数(RBF)神经网络预测中难以确定最佳隐藏层数问题,以提高预测的准确性。首先分析了GA算法模型和RBF神经网络模型;然后利用GA算法与RBF模型结合得到GA-RBF负荷预测模型;最后利用仿真工具对所建模型进行训练和预测。结果表明,与传统方法相比,其平均绝对百分误差值降低了4. 7%,证明了该方法的精确性和有效性。

Short-term Load Prediction of Power System Based on GARBF Neural Network

A genetic algorithm-radial basis function (GA-RBF) neural network load prediction method is proposed to solve the problem of the difficulty in determining the optimal number of hidden layers in traditional radial basis function (RBF) neural network prediction so as to improve the accuracy of prediction.Firstly,GA algorithm model and RBF neural network model are analyzed.Then GA-RBF load forecasting model is obtained by combining GA algorithm with RBF model.Finally,the model is trained and predicted using simulation tools.The result shows that the average absolute percentage error (MAPE) is reduced by 4.7% compared with the traditional method,which proves the accuracy and effectiveness of this method.