基于天气类型聚类识别的光伏系统短期无辐照度发电预测模型研究

Short-term PV Generation System Forecasting Model Without Irradiation Based on Weather Type Clustering

现有光伏发电量预测模型大多以太阳辐照度作为必要的输入,然而,由于当前国内太阳辐射站点仍较稀少且预报能力较低,因此此类预报方法难于实施。利用距离分析方法分析光伏发电量与气象因素间的相关性,确定以气温和湿度作为预报输入因子,建立反传播(back propagation,BP)神经网络的无辐照度发电量短期预报模型。此外,为适应天气突变,采用自组织特征映射(self-organizing feature map,SOM)由云量预报信息对天气类型聚类识别,继而对各天气类型采用相应的预测网络,避免了单神经网络的过拟合问题。通过与含辐照度输入及无天气聚类识别的预测模型做交叉对比实验,预测结果表明,天气类型聚类识别能显著提高预测精度,无辐照度光伏发电量短期预测模型有较高的精度和50%湿度抗扰动性。

Most of photovoltaic（PV） generation forecasting models need to take solar irradiance as their input parameters.However,they were difficult to implement in China due to insufficient solar radiation stations available and poor performance of forecasting.After investigating the correlation among PV generation and several meteorological elements through distance analysis,a back propagation（BP） neural network forecasting model was proposed whose input parameters were ambient temperature and humility.Furthermore,in order to adapt sudden weather changes,the future weather type was recognized from forecasted cloud cover by using self-organizing feature map（SOM）.Then,PV power generation in each weather type could be forecasted from its corresponding forecast network.Therefore,the over fitting issue of single network model could be addressed.Comparison experiments were made as opposed to the forecasting model with radiation observation and the one without weather type classification.The experimental results indicate that weather type clustering can significantly improve the precision of power prediction,and that the short-term forecasting model without irradiance with high precision can withstand 50% disturbance with humidity.