期刊名称：IOP Conference Series: Earth and Environmental Science
印刷版ISSN：1755-1307
电子版ISSN：1755-1315
出版年度：2019
卷号：227
期号：2
页码：022032
DOI：10.1088/1755-1315/227/2/022032
出版社：IOP Publishing
摘要：Intermittence and fluctuation natures of photovoltaic (PV) solar energy pose great challenge on the grid stability and power scheduling. PV power forecasting is an effective measure to alleviate the issue. This study presents an improved model for forecasting one-day-ahead hourly PV power generation using Numerical Weather Prediction (NWP) and historical data, which is based on Radial Basis Function (RBF) neural network and similar day method. Firstly, historical similar days of the same weather type are selected according to the correlation of meteorological data. Secondly, the RBF neural network based forecasting model is trained using the historical data of similar days. Finally, the model is used to forecast the power generation using the NWP data of the forecast day. Experimental results show that the proposed method is accurate and reliable.
