摘要
为了提高预测的精度,将神经网络组合预测模型应用于能源消费总量预测中,通过建立RBF、ELM、BP神经网络预测模型,用熵值法确定组合预测模型的加权系数,建立神经网络组合预测模型.利用安徽省统计年鉴获得的1991～2007年安徽省能源消费总量进行检验仿真,结果表明组合预测模型的误差较小,精度较高,预测结果更接近于实际情况.
To improve the accuracy of the forecast, the combination of neural network prediction model is used to predict the total energy consumption. Through the establishment of RBF, ELM and BP neural network prediction model , the combination of entropy prediction model is used to determine the weighting coefficients and establish neural network combination prediction model. Through the Statistical Yearbook of Anhui Province during 1991-2007, total energy consumption in Anhui Province is simulated in test. The results show that the combination of the forecast model owns small errors, high accuracy and prediction outcome is closer to the actual situation.
出处
《湖南工程学院学报（自然科学版）》
2009年第4期59-61,71,共4页
Journal of Hunan Institute of Engineering(Natural Science Edition)
