Hybrid Explainable SRNN-LSTM Architecture for Irradiance, Temperature and Wind Speed Forecasting

Abstract Sustainable Energy alternatives such as Solar Energy, Wind Energy are the best alternatives to the harmful Non-Renewable energy sources like fossil fuels. With the increasing investment made in the Sustainable Energy alternatives, forecasting of Energy production from the farms plays a crucial in the structured design of Energy farms and for integrated smart grid management. In this research, we propose SRNN-LSTM hybrid models for univariate solar irradiance forecasting, multivariate temperature forecasting and univariate forecasting of Wind Speed. The proposed models are evaluated based on RMSE, MAE, r2 score and Index of Agreement error metrics. The SRNN16LSTM16 hybrid models achieves the best performance with r2 score of 0.97 for Solar Irradiance forecasting and SRNN8LSTM8 hybrid model achieves the best performance with the r2 Score of 0.989 and RMSE of 0.122 for Wind Speed forecasting. We have also proposed a simple approach to derive the prediction intervals based on the Median of the residual values. The higher values of PICP error metric indicate that the proposed models are efficient and perform better than the state-of-the-art models used in the forecasting frameworks. We have also performed the Model Analysis using Explainable Artificial Intelligence tools such as LIME and ELI5 to analyze the importance of features in the model development process, generating and analyzing local explanations.