Grid physics-informed and time-adaptive stacked learning for real-time electricity price forecasting: a short-term to mid-term approach

Key Points

• Forecasting electricity prices using a novel machine learning method improves predictive accuracy.
• The stacked learning model incorporates grid physics-informed techniques, resulting in consistent performance improvements.
• Observational analysis combines historical pricing data with time-adaptive learning for enhanced forecasting models.
• Highlights the potential for real-time applications in dynamic electricity markets, indicating further testing is needed.