基于小波变换和神经网络的光伏功率预测

Photovoltaic output power prediction approach based on wavelet transform and neural network

提出了一种小波分解(Wavelet Transform,WT)和径向基函数神经网络(RBFNN)相结合的预测方法,并引入理论太阳辐照量、温度和相对湿度数据来预测未来24 h光伏电站的输出功率。小波分解能有效地表征光伏电站输出功率时间序列的局部特征,人工智能方法可以捕捉到光伏发电中的非线性特性。预测结果表明,采用该方法预测光伏电站输出功率,能有效地提高预测精度。

A method combining wavelet transform（WT） and radial basis function neural network（RBFNN） is proposed to forecast output power of the next day by incorporating data of solar radiation,temperature and relative humidity. In this method, WT can effectively describe the local characteristics of the PV power output time series; neural network can capture the nonlinear characteristics of photovoltaic power generation. The results show that the method can effectively improve the predictive accuracy of PV station output power.