Nine novel ensemble models for solar radiation forecasting in Indian cities based on VMD and DWT integration with the machine and deep learning algorithms

Abstract

This paper focuses on integrating two popular signal processing techniques, i.e., variational mode decomposition (VMD) and discrete wavelet transform (DWT), with deep learning (DL) and machine learning (ML) algorithms to come up with nine novel ensemble models for solar radiation forecasting. For these ensemble models, we considered five DL algorithms that include gated recurrent units (GRU), long short-term memory (LSTM), bidirectional long short-term memory (BiLSTM), convolutional neural network (CNN), and deep neural network (DNN); two ML algorithms that include artificial neural network (ANN) and support vector regression (SVR). The proposed nine models were tested for seven Indian cities, namely Delhi, Chennai, Hyderabad, Nagpur, Patna, Trivandrum, and Bhubaneshwar. We used root mean square error (RMSE), mean absolute error (MAE), and coefficient-of-determination (R2) metrics for understanding the performance. Observed that the DL-based VMD integration had generated considerably promising results compared to DWT integration. Out of the nine models, VMD-integrated GRU gave the most optimum results for all the cities with RMSE (0.82-1.22), MAE (0.54-1.02), and R2 (0.83-0.93). It's because GRU employs fewer training parameters, which requires less memory and functions faster than any other algorithm. Overall, this study helps Indian cities to forecast solar radiation more effectively with advanced ML and DL algorithms and scope for applying these models elsewhere around the world.