基于多变量相空间重构和RBF神经网络的光伏功率预测方法

针对光伏功率单变量预测方法的不足,设计了一种新型光伏功率多变量相空间重构预测方法。首先,基于相关性分析,选取实际光伏电站的历史光伏功率和气象因素时间序列组成多变量时间序列;然后,利用C-C法和虚假邻近点(false nearest neighbors,FNN)法重构光伏功率预测的多变量相空间,并以小数据法识别其混沌特性;最后,结合径向基函数(radial basis function,RBF)神经网络强大的非线性拟合能力,建立了基于多变量相空间重构和RBF神经网络的光伏功率预测模型。算例分析表明,相较于单变量预测方法,所提出的多变量相空间重构预测方法性能更加优越。

Power prediction method of photovoltaic generation based on multivariablephase space reconstruction and RBF neural network

In view of the shortcomings of the single variable prediction method of photovoltaic (PV) power, a new multivariable phasespace reconstruction prediction method of PV power is designed. Firstly, based on the correlation analysis, the historical PV power andmeteorological factors time series of the actual PV power plant are selected to form multivariate time series. Then, the multivariablephase space of PV power prediction is reconstructed by C-C method and false nearest neighbors ( FNN) method, and its chaoticcharacteristics are identified by small data method. Finally, combined with the powerful nonlinear fitting ability of radial basis function(RBF) neural network, a PV power prediction model based on multivariate phase space reconstruction and RBF neural network isestablished. The example analysis shows that the proposed multivariate phase space reconstruction prediction method has betterperformance than the single variable prediction method.