Hybrid method for short‐term photovoltaic power forecasting based on deep convolutional neural network. Issue 20 (18th September 2018)

• Record Type: Journal Article
• Authors: Zang, Haixiang; Cheng, Lilin; Ding, Tao; Cheung, Kwok W.; Liang, Zhi; Wei, Zhinong; Sun, Guoqiang
• Is Part Of: IET generation, transmission & distribution. Volume 12:Issue 20(2018)
• Page Start: 4557
• Page End: 4567
• Publication Date: 2018-09-18
• Subjects: load forecasting -- time series -- power engineering computing -- neural nets -- photovoltaic power systems; hourly timescales -- commonly used methods -- hybrid method -- short‐term photovoltaic power forecasting -- deep convolutional neural network -- photovoltaic electric power -- rising energy demands -- inexhaustible renewable energy -- solar radiation -- grid‐connected PV systems -- CNN -- short‐term PV power forecasting -- different frequency components -- historical time series -- variational mode decomposition -- VMD -- convolution kernels -- hybrid model; Electric power production -- Periodicals; Electric power transmission -- Periodicals; Electric power distribution -- Periodicals; 621.3105
• DOI: 10.1049/iet-gtd.2018.5847
• Languages: English
• ISSNs: 1751-8687

Abstract

Abstract : Photovoltaic (PV) electric power has been widely employed to satisfy rising energy demands because inexhaustible renewable energy is environmentally friendly. In order to mitigate the impact caused by the uncertainty of solar radiation in grid‐connected PV systems, a hybrid method based on a deep convolutional neural network (CNN) is introduced for short‐term PV power forecasting. In the proposed method, different frequency components are first decomposed from the historical time series of PV power through variational mode decomposition (VMD). Then, they are constructed into a two‐dimensional data form with correlations in both daily and hourly timescales that can be extracted by convolution kernels. Moreover, the time series of residue from VMD is refined into advanced features by a CNN, which could reduce the data size and be easier for further model training along with meteorological elements. The hybrid model has been verified by forecasting the output power of PV arrays with diverse capacities in various hourly timescales, which demonstrates its superiority over commonly used methods.