基于主成分分析与前向反馈传播神经网络的风电场输出功率预测

Forecasting of Wind Farm Generation Output Based on Principal Component Analysis and Back Propagation Neural Network

为了解决单一的传统预测方法在风电场输出功率预测中存在的问题,提出了基于主成分前向反馈神经网络的预测方法。首先采用K-S方法对样本进行选取;然后用主成分分析法提取样本有效信息,求解出主成分,构建神经网络模型进行输出功率预测。结果表明,主成分分析后的神经网络模型消除了输入因子的相关性并简化了网络结构,使网络加速收敛。实例验证,与单一的神经网络模型相比,预测精度有所提高,为风电场输出功率预测提供了一种有效的方法。

To remedy the defects existing in the forecasting of wind farm generation output by tranditional singular forecasting method, a forecasting method based on principal component analylsis （PCA） and back propagation neural netwrok （BPNN） is proposed. Firstly, the samples are chosen by K-S method; then the effective information in the chosen samples is extracted by PCA and the principal components are solved; and then the BPNN is constructed to forecast the wind farm generation output. Calculation results show that after the processing by PCA the correlativity among input factors in BPNN model is eliminated as well as the structure of the BPNN is simplified, thus the BPNN converges faster. The forecasting results by the proposed method is more precise than those by singular neural netwrok model.