一种光伏短期出力区间预测方法

A PHOTOVOLTAIC SYSTEM SHORT-TERM POWER INTERVAL FORECASTING METHOD

该文建立基于相似日模糊信息粒化和Elman神经网络的光伏短期出力区间预测模型。首先对原始序列进行相似日的选取,然后将提取的样本利用模糊信息粒化进行处理,确定预测区间的上下界,并结合Elman神经网络分别预测,构建区间预测模型。仿真结果表明,所提出的区间预测方法具有较高的预测精度和实用价值。

At present,the prediction of PV output power usually adopts point predicting model.For the strong randomness and volatility of the PV output power,the interval forecast method is more meaningfully.In this paper,an interval forecast model for PV short-term out put power based on similar day fuzzy information granulation and FIG-Elman is proposed.Firstly,the similar days are selected from the original sequence,and then the data are decomposed into the upper and lower bounds of the prediction interval by fuzzy information granulation.At last,the Elman neural network is used to forecast the upper and the lower bounds,respectively.Finally,an interval prediction model is established by combining Elman.The interval forecasting method is built.Simulation results show that the proposed method has higher prediction accuracy and the practical value.