一种新的光伏发电预测模型的设计

A Model Design for the Forecasting of Photovoltaic System Power Generation Power

为了对光伏发电的输出功率进行预测,本文分析光伏发电的影响因素,提出了一种基于太阳辐射功率曲线匹配的预测模型。该模型将历史数据按时段进行分解,查找与当前时段太阳辐射功率曲线最为匹配的数据,以此构建并训练BP神经网络,来预测未来3个小时内的太阳辐射功率,能够较好的实现预测目标。实验结果表明,该模型有较高的精度,可对电网调度起到重要的指导作用。

To predict the power of photovoltaic power generation, we analyzed the factors of photovoltaic power generation and proposed a method of predicting photovohaic power generation power based on the curve matching of solar radiation. By decomposing the historical data, searching the solar radiation curve, using the BP neural network, this method could predict photovoltaic power generation power within the next three hours and have a good performance. Experimental results show that this model can have a small forecasting error, which means that it＇s important in electric network management.