<ul><li>Team GEB's solution ranked 3rd in trading, 4th in forecasting, and 1st among student teams in the IEEE Hybrid Energy Forecasting and Trading Competition 2024 (HEFTCom2024).</li><li>The solution involves a stacking-based approach for wind power forecasts, an online solar post-processing model for the online test set, a probabilistic aggregation method for accurate quantile forecasts of hybrid generation, and a stochastic trading strategy to maximize trading revenue considering uncertainties in electricity prices.</li><li>The paper also discusses the potential of end-to-end learning to improve trading revenue by adjusting forecast error distributions and provides detailed case studies validating these methods.</li><li>All methods mentioned in the solution have accompanying code available for reproduction and further research in both industry and academia.</li></ul>

A Hybrid Strategy for Aggregated Probabilistic Forecasting and Energy Trading in HEFTCom2024

Discover more