摘要
提出了采用EEMD与动态神经网络络相结合的混合模型进行电力系统短期负荷预测的方法。首先运用EEMD将非平稳的负荷序列分解,然后根据分解后各分量的特点构造不同的动态神经网络对各分量分别进行预测,最后对各分量预测结果采用BP网络进行重构得到最终预测结果。仿真结果表明基于该方法的电力系统短期负荷预测具有较高的精度。
This paper proposes a hybrid model based on Ensemble Empirical Mode Decomposition(EEMD), dynamic neural network and BP nature network as a short-term load forecasting model.At first,based on EMD the load series is decomposed into different lots of calm series;then according to the feature of decomposed components,different dynamic neural network model is established;finally,using the BP network,to reconstruct the forecasted signals of the components and abstain the ultimate forecasting result.Simulink results show that the proposed forecasting method possesses accuracy.
出处
《东北电力大学学报》
2009年第6期20-26,共7页
Journal of Northeast Electric Power University
关键词
短期负荷预测
经验模态分解
动态神经网络
重构
short-term Load Forecasting
Empirical Mode Decomposition(EMD)
dynamic neural network
reconfiguration