In modern power systems with increasing renewable energy integration, electricity price forecasting has become increasingly vital for system planning. This study focuses on Türkiye’s Day-Ahead Market (DAM) prices by utilizing a probabilistic machine learning model to improve short-term price prediction. A Quantile Gradient Boosting Regressor (GBR) was trained using hourly data obtained from the EPİAŞ transparency platform covering the period between 2022 and 2025. By estimating market-clearing prices, the model allows for capturing both the central tendency and the uncertainty of prices.The model includes time stamp data as hour and day, as well as electricity generation resources and past prices. Quantitatively, the model achieved an RMSE of 434.82 TRY/MWh, a CRPS of 194.98 TRY/MWh, and a PICP of 0.74 for the 80% prediction interval. The results show that the proposed approach provides high-performance prediction intervals when compared with traditional single-point models. This probabilistic model could be used for decision-making in energy markets, as well as for the scheduling of renewable integrated storage systems within renewable energy systems.
Kübra Nur Akpınar (Mon,) studied this question.