基于一种改进的BP神经网络光伏电池建模

由于光伏电池具有高度非线性特性，难以建模，而传统的数学模型难以满足光伏控制系统设计和应用的要求。该文利用神经网络具有逼近任意复杂非线性函数的能力，将神经网络技术应用到光伏阵的建模中，避开了该模块内部的复杂性。模型以太阳能日照、温度以及负载电压作为神经网络辨识模型的输入量，光伏阵输出电流为输出量，采用改进型BP算法，建立了光伏电池的动态响应模型，然后预测了最大功率点。文中给出模型的结构，训练步骤和仿真结果。仿真结果表明，方法可行，建立的模型精度较高，从而为设计光伏实时控制系统奠定了基础。

Modeling of Photovoltaic-Array Based on Improved BP Neural Networks Identification

For the serious complexity of photovoltaic array(PV),modeling of it is very difficult and the existing models are too complicated to be applied to designing and controlling the system,especially to on-line controlling.In this paper,we try to establish a voltage and current model of PV array by using neural networks identification technique.The temperature,radiation and voltage of the solar cells are taken as the input and the current as the output of the neural networks model.In this way,we can avoid the internal complexity of PV module.The 595 groups experimental data are used,and the structure and the novel BP algorithm of neural networks identification system are given.The validity and accuracy of the model are proved by the simulation results.The neural networks modeling makes it possible to design on-line controller of PV system.