电网技术2011，Vol.35Issue(9)：128-132,5.
基于主成分分析与人工神经网络的风电功率预测
Prediction of Wind Power Based on Principal Component Analysis and Artificial Neural Network
摘要
Abstract
A wind power prediction model based on integration of principal component analysis (PCA) with back-propagation (BP) neural network is proposed. The PCA is used to preprocess original multi-dimensional input variables and principal components of input variables are chosen as the input of BP neural network, by this way either the dimensions of input variables can be reduced or correlativity among input variables can be eliminated, thus both convergence and stability of neural network can be improved. Simulation results show that the accuracy of wind power prediction by the proposed PCA-BP model is better than that by common neural network models and the proposed model possesses better generalization performance.关键词
风电功率预测/主成分分析/前馈神经网络/泛化性能Key words
wind power prediction/principal component analysis/back-propagation (BP) neural network/generalization performance分类
信息技术与安全科学引用本文复制引用
周松林,茆美琴,苏建徽..基于主成分分析与人工神经网络的风电功率预测[J].电网技术,2011,35(9):128-132,5.基金项目
国家重点基础研究发展计划项目(973项目)(2009CB219708). （973项目）
