基于模型辨识与BP神经网络的光伏MPPT方法

A Photovoltaic MPPT Method Based on Model Identification and BP Neural Network

光伏阵列是光伏发电系统的重要组成部分,研究其准确模型并对最大功率点进行跟踪与预测,对光伏发电效率的提高具有重大意义。针对光伏阵列中二极管品质因数以及串联电阻阻值等参数难以直接准确测量的问题,采用光伏阵列在多种工作状况下的实际测量信息对其数学模型进行参数辨识,使辨识后的模型与实际对象相一致。为了对最大功率点进行实时地预测,构造了一种BP神经网络模型。采用辨识后的准确模型产生测试数据,提取光照强度、光伏电池板温度以及最大功率点对应的输出电压等信息,用于BP神经网络的训练。最后将训练好的BP神经网络模型用于光伏发电系统的最大功率点跟踪(MPPT)。结果表明,该方法极大地提高了MPPT的实时性和高效性。

Photovoltaic array is an important part of photovoltaic power generation system. It is of great significance to improve the efficiency of photovoltaic power generation through studying its accurate model and predicting and tracking the maximum power point(MPP). It is difficult to directly and accurately measure the parameters, such as the diode quality factor and the value of the series resistance in photovoltaic array. The actual measurement information of photovoltaic array under various working conditions is used to identify the parameters of its mathematical model, so as to make the identified model consistent with the actual processes. In order to predict the MPP in real time, a BP neural network model is constructed. The identified accurate model is used to generate test data, and the information such as the intensity of illumination, the temperature of photovoltaic panel and the output voltage corresponding to MPP are extracted for training the BP neural network. Finally, the trained BP neural network is applied to the maximum power point tracking(MPPT) of the photovoltaic power generation system. The results show that this method greatly improves the real-time performance and efficiency of MPPT.