一种利用多层感知机和I-V特性的光伏组件建模方法

为了提高光伏组件模型的准确度和可靠性，本文提出了一种利用多层感知机和不同工况下实测的I-V特性曲线数据集的建模新方法。首先，使用双线性插值法对实测I-V曲线进行重采样，以提高I-V曲线上数据点分布的均匀性；进而使用基于温度-辐照度的网格采样法对数据集进行下采样，降低数据冗余度。其次，提出一种基于多层感知机神经网络的光伏组件模型，并基于预处理的I-V曲线数据集，使用Adam算法训练该模型。最后，采用美国国家可再生能源实验室提供的实测I-V特性曲线数据集，验证和测试了所提出的建模方法，并与支持向量机、梯度提升决策树等机器学习算法进行对比。实验结果证明，所提出的建模方法具有最高的精度和泛化性能。

A photovoltaic module modeling method using multilayer perceptron and I-V characteristics

In order to improve the accuracy and reliability of the photovoltaic module models, this paper proposes a new modeling method based on the multilayer perceptron and I-V characteristic curves dataset measured under different working conditions. Firstly, bilinear interpolation method is used for resampling the measured I-V curve to improve the uniformity of the distribution of data points on the I-V curve, and then the dataset was down-sampled by temperature-irradiance grid sampling method to reduce the data redundancy. Secondly, a new photovoltaic module model based on multilayer perceptron neural network is proposed. Based on the pre-processed I-V curve data set, the Adam algorithm is used to train the model. Finally, the proposed modeling method is validated and tested using the public I-V characteristic curve dataset provided by the National Renewable Energy Laboratory of the United States, and compared with machine learning algorithms such as support vector machine and gradient boosting decision tree. Experimental results show that the proposed modeling method has the highest precision and generalization performance.