基于PCA-Elman神经网络的短期PV/T组件温度预测

Short-term PV/T component temperature prediction based on PCA-Elman neural network

为了进一步提高光伏/光热一体化(PV/T)系统中PV/T组件温度的预测精度,使得PV/T系统能够根据PV/T组件温度的波动情况提前准确地做出控制决策,以优化控制效果,文章在分析PV/T组件温度与气象因素的相关性以及相邻时间序列温度自相关性的基础上,采用主成分分析法对原始输入样本数据进行预处理,并提取该样本数据的主成分,然后结合反馈型Elman神经网络理论,建立动态预测模型。研究结果表明,相对于未提取主成分的神经网络模型,提取主成分的神经网络模型的预测精度更高,泛化性能更强。

： In order to further improve the prediction accuracy of PV/T module temperature In photovoltaic-thermal （PV/T） system, making the PvYr system controller run forward according to fluctuation condition of module temperature to optimize control effect, this paper presents a new method. Based on the analysis of the correlation between PV/T module temperature and meteorological factors and the correlation between adjacent PVYr module temperatures, the principal component analysis method is used to preprocess the original input sample data to extract the main component. Then combined with the feedback Elman neural network theory, the simulation results show that the proposed method makes the prediction accuracy of the network model higher and the generalization performance is stronger than that of the neural network without the main component extraction.