Abstract
With the integration of photovoltaic (PV) power into an electrical network, the complexity of the grid management is increasing because of intermittent and fluctuation nature of solar energy. Solar irradiance forecasting is essential to facilitate planning and managing electricity generation and distribution in smart grid cyber-physical system (CPS). The performance of existing short-term forecasting methods is far from satisfactory due to a lack of reliable and fast time-frequency model for continuous-time solar irradiance data. To address this problem, this paper proposes a new method, Elman Neural Network (ENN) driven Wavelet Transform (WT-ENN), for hourly solar irradiance forecasting. Firstly, the solar irradiance series was decomposed into a set of constitutive series using wavelet transform. Secondly, the new wavelet coefficients were predicted by ENNs in every sub-series with the best network structure and parameters. Thirdly, Wavelet reconstruction will predict next hour solar irradiance through the aggregation of outputs of the ensemble of ENNs. Finally, the forecasting performance was evaluated using two large real-world solar irradiance datasets. Experiment results show that the new WT–ENN model outperforms a large number of alternative methods and an average forecast skill of 0.7590 over the persistence model. Thus, it is concluded that the proposed approach can significantly improve the forecasting accuracy and reliability.
Highlights
Because of the challenges of climate change, environmental pollution, and energy insecurity, the market penetration of renewable energy sources is growing rapidly
I=1 Yi − Y i where the N is the number of testing instances, Yi is the prediction of the models and Yi is the measured irradiance mean
The results show that our wavelet transform (WT)-Elman neural network (ENN) method has superior prediction performance in sunny days
Summary
Because of the challenges of climate change, environmental pollution, and energy insecurity, the market penetration of renewable energy sources is growing rapidly. Mohammadi et al [23] proposed a hybrid model that combines the SVM and the Wavelet Transform (WT) algorithm to predict horizontal global solar radiation. We proposed a novel WT-ENN approach that hybridizes wavelet transform (WT) and Elman neural network (ENN) to forecast solar irradiance. The experiment results show that the proposed WT-ENN model has superior performance and can effectively improve the prediction accuracy These indicate that the accurate forecasting hourly solar irradiance using only historical irradiance without other meteorological parameters is possible. The main contributions of this study are as follows: 1) This study improves the performance of ENN models by using WT for the original data and, subsequently, develops an improved WT-ANN hybrid model for solar irradiance forecasting.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
