Determination Method of Insolation Prediction With Fuzzy and Applying Neural Network for Long-Term Ahead PV Power Output Correction
Determination Method of Insolation Prediction With Fuzzy and Applying Neural Network for Long-Term Ahead PV Power Output Correction
复制标题
DOI：
10.1109/tste.2013.2246591
复制
发表时间：
2013-03
影响因子：
8.8
通讯作者：
A. Yona;T. Senjyu;T. Funabashi;Chul-Hwan Kim
中科院分区：
文献类型：
--
作者：
A. Yona;T. Senjyu;T. Funabashi;Chul-Hwan Kim
近年来，太阳能等替代能源的引入是可想而知的。然而，日照并不是恒定的，光伏系统的输出会受到气象条件的影响。为了尽可能准确地预测光伏系统的功率输出，需要一种太阳辐射估算方法。利用气象预报数据、模糊理论和神经网络(NN)，提出了一种基于提前24小时日照预报的光伏系统功率预测方法。如果没有选择合适的训练数据，神经网络的训练过程往往是不稳定的。所提出的神经网络应用技术是通过基于模糊理论的功率输出数据和天气预报数据来训练的。由于模糊模型决定了日照预测数据，因此神经网络将平滑地训练功率输出。通过计算机仿真比较了两种方法的预测能力，验证了该方法的有效性。
In recent years, introduction of an alternative energy source such as solar energy is expected. However, insolation is not constant and the output of a photovoltaic (PV) system is influenced by meteorological conditions. In order to predict the power output for PV systems as accurately as possible, an insolation estimation method is required. This paper proposes the power output forecasting of a PV system based on insolation forecasting at 24 hours ahead by using weather reported data, fuzzy theory, and neural network (NN). If the suitable training data is not selected, the training process of NN tends to be unstable. The proposed technique for application of NN is trained by power output data based on fuzzy theory and weather reported data. Since the fuzzy model determines the insolation forecast data, NN will train the power output smoothly. The validity of the proposed method is confirmed by comparing the forecasting abilities on the computer simulations.