利用相似日小波变换和多层感知机的短期光伏功率预测

A short-term photovoltaic power prediction method using similar day wavelet transform and multilayer perceptron

为了提高光伏功率预测的准确性和可靠性,基于相似日小波变换和多层感知机建立智能光伏功率预测模型;将小波变换的多分辨率特点和多层感知机的非线性拟合能力结合起来,以有效地提高预报的可靠性.首先,选取相似日数据并归一化,并用小波变换对数据进行预处理;其次,训练多层感知机模型学习气象因素与光伏功率之间的映射关系;最后,基于沙漠知识澳大利亚太阳能中心实际大型数据集进行对比实验.实验结果中的技能得分表明,本预测模型相较于其他对比模型,在预测准确性和可靠性方面具有更好的性能.

In order to improve the accuracy and reliability of photovoltaic power prediction,this paper establishes a smart photovoltaic power prediction model based on similar day wavelet transform and multilayer perceptron,which combines the multi-resolution characteristics of wavelet transform and the nonlinear fitting ability of multilayer perceptron.It effectively improves the reliability of forecasting.First,select the data of similar day and normalize,and then use wavelet transform to preprocess the data.Secondly,the multilayer perceptron is trained to learn the mapping relationship between meteorological factors and photovoltaic power.Finally,the experimental results based on the actual large-scale data set of Desert Knowledge Australia Solar Centre(DKASC)show that the prediction model proposed in this paper has better performance in terms of prediction accuracy and reliability than other comparison models.