Explainable AI models for short-term renewable energy forecasting under uncertainty
Reliable short-term PV forecasting is essential to ensure the reliability of energy management based on renewable sources, but the lack of interpretability of deep learning models and the environmental uncertainty still prevent their operation. In this research, an uncertainty-aware transformer framework is proposed which is explainable when forecasting the short-term PV power under dynamically changing environmental conditions. It introduces a framework which combines a Temporal Fusion Transformer (TFT), quantile-based uncertainty estimation, dual explainability mechanism based on attention analysis, and SHAP based feature attribution. The measurements from a real solar system having capacity of 1.005 kW were taken at the site of Sitapura, Jaipur, India and were synchronously matched with the POWER meteorological measurements taken by NASA. The framework was tested on the baseline models of ARIMA, LSTM and CNN-LSTM. These experimental results showed that the approach achieved better forecasting results compared to all the baseline approaches with RMSE of 0.067, MAE of 0.051 and MAPE of 4.38%. The probabilistic forecasting module was able to attain a Prediction Interval Coverage Probability (PICP) of 94.8% and narrow interval width, thus demonstrating good uncertainty estimation abilities. Irradiance and PV output of the past were found to be the most important factors for forecasting in this explainability analysis. The proposed framework is based on the transformer model, probabilistic forecasting, and then explains the renewable energy forecasting system in the entire system for photovoltaic uncertainty-aware and interpretable prediction.