标题:
光伏电站输出功率的主因隐藏型RBFNN预测方法RBFNN Based Photovoltaic Power Prediction Method with Hiding of Main Influencing Factor
作者:
文明, 李刚强, 江辉, 彭建春
关键字:
光伏电站, 功率预测, 气象, 马氏距离, 径向基神经网络Photovoltaic Power Station, Power Prediction, Meteorology, Mahalanobis Distance, RBFNN
期刊名称:
《Smart Grid》, Vol.6 No.4, 2016-08-25
摘要:
提出了一种光伏电站功率的主因隐藏型径向基神经网络(RBFNN)预测方法。先合理隐去影响光伏电站功率的主要气象因素“太阳辐射强度”，建立RBFNN预测模型。再按与预测时点气象因素记录的马氏距离从历史记录中筛选出相似样本集，对RBFNN模型进行学习训练。运用训练好的RBFNN实现短期光伏电站功率的预测。这种方法不仅合理隐去了预测中难以获取的地面太阳辐射强度、使光伏功率预测易于实现，而且运用马氏距离筛选样本、改进了预测精度。仿真结果验证了本文方法的有效性。
A radial basis function neural network (RBFNN) based photovoltaic power prediction method with hiding of main influencing factor is proposed in this paper. Firstly, the main influencing factor of solar radiation intensity on photovoltaic power is hidden rationally, and RBFNN based photovoltaic power prediction model is built. Then the similar samples are screened out from historical records of meteorological factors according to their Mahalanobis distances from the record of meteorological factors of the prediction time point, which are used to train the RBFNN model. At last, the trained RBFNN is used to predict the output power of the photovoltaic power station. The proposed method hides rationally the ground solar radiation intensity that is difficult to obtain and has important influence on photovoltaic power in the prediction, which makes photovoltaic power prediction easy to implement. In addition, the screening of similar samples by Mahalanobis distance improves the accuracy of photovoltaic power prediction. Simulation results show the effectiveness of the proposed method.