A point and interval forecasting of solar irradiance using different decomposition based hybrid models

For the regulation and operation of electrical systems, a reliable and precise prediction of solar irradiation is extremely beneficial. Therefore, this paper deals with the issue of accurate and reliable estimation of solar irradiance by developing and investigating the different standalone and hybrid forecasting models. Eleven different models: Feedforward neural network (FFNN), long short term memory (LSTM), gated recurrent unit (GRU), Bidirectional long short term memory (BDLSTM), BDLSTM with empirical mode decomposition (EMD), ensemble empirical mode decomposition (EEMD), complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), variational mode decomposition (VMD), wavelet transform (WT) and wavelet packet decomposition (WPD) are developed for point and interval forecasting of solar global horizontal irradiance (GHI) on hour ahead basis for two Indian locations. The autocorrelation function ((ACF) and partial autocorrelation function (PACF) are used as statistical measurement to select the optimal lags of the input lags of deep learning (DL) predictors. Likewise, the grid search algorithm is used to select the optimum value of hyperparameters of the predictor. To evaluate the model’s performance, root mean square error (RMSE) and mean absolute error (MAE) for point forecast whereas; prediction interval nominal confidence (PINC), average coverage error (ACE) and prediction interval average width (PIAW) for the interval forecast are calculate for annual and seasonal datasets. From the study, the WPD based model achieved the minimum annual RMSE (11.35 W/m 2 & 10.49 W/m 2 ) and MAE (6.04 W/m 2 & 6.41W/m 2 ). Likewise, at confidence interval (CI) = 99%, the PICP, ACE and PIAW achieved by WPD are ranges from 80.66–81.27, 19.92–21.03, 17.71–18.33 respectively.