基于模型辨识的BP神经网络在光伏系统MPPT中的应用

Application of BP Neural Network Based on Model Identification in Photovoltaic System MPPT

摘要:

光伏电池作为光伏发电系统的重要组成部分,研究其模型的准确性并对其最大功率点进行预测与跟踪,对于光伏发电效率的提高具有重大意义;首先根据光伏电池的内部结构和伏安特性建立其数学模型,并对所建立的模型进行参数辨识,进而得到模型输出与测量信息偏差最小的参数值,验证模型的准确和有效性;根据模型所反映的规律,将温度和光照强度作为输入变量,最大功率点对应的电压作为输出变量,构建了用于MPPT的神经网络模型;神经网络经训练后对最大功率点电压进行预测与跟踪,结果表明构建的神经网络具有良好的适应性。

Abstract:

Photovoltaic cell is an important part of photovoltaic power generation system. It is of great significance to study the accurate model of photovoltaic cell and to predict and track the MPP (maximum power point). Firstly, according to the internal structure and the I-V characteristics of photovoltaic cell, the mathematical model is established. The parameters of the model can be identified by searching the minimum deviations between outputs of the identified model and actual measurement information, and the accuracy and validity of the model can be verified. According to the law of the PV model, the temperature and illumination are considered as the input variables, and the corresponding voltage of MPP is used as the output variables, a neural network model for MPPT is constructed. The neural network is trained to predict and track the voltage of MPP. The results show that the neural network has good adaptability.