摘要
利用改进的主成分分析(MPCA)方法对径向基函数神经网络输入空间进行重构,在降低输入空间维数的同时克服了传统主成分分析法的缺点,缩小了网络的结构,达到了提高网络泛化能力的目的。通过某省实例验证了该方法的有效性。
The method which reconstruct the original input space of radial basic function neural network by modified principal component analysis （MPCA）, can not only gready reduce dimension of new phase space but also overcome the shortcoming of traditional principal component analysis. This method can simplify its network structure as well as enhance the network＇ s generalization performance. The effectiveness of the proposed algorithm is verified by the practical data of a certain provincial power network.
出处
《华北电力大学学报（自然科学版）》
CAS
北大核心
2007年第3期77-79,84,共4页
Journal of North China Electric Power University：Natural Science Edition
基金
国家自然科学基金资助项目(5007707)
关键词
主成分分析
径向基函数
人工神经网络
负荷预测
电力系统
principal component analysis
radial basic function （RBF）
artificial neural network （ANN）
load forecasting
power system
