A short-term photovoltaic power forecasting model based on a radial basis function neural network and similar days. Issue 2 (February 2019)

• Record Type: Journal Article
• Authors: Xu, Zhenlei; Chen, Zhicong; Zhou, Haifang; Wu, Lijun; Lin, Peijie; Cheng, Shuying
• Is Part Of: IOP conference series. Volume 227:Issue 2(2019)
• Publication Date: 2019-02
• Subjects: Earth sciences -- Periodicals; Environmental sciences -- Congresses; Environmental sciences -- Periodicals; 550.5
• DOI: 10.1088/1755-1315/227/2/022032
• Languages: English
• ISSNs: 1755-1307

Abstract

Abstract: 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.