ML-based bidding price prediction for pay-as-bid ancillary services markets: An application to the German control reserve market

The increasing integration of renewable energy sources has led to greater volatility and unpredictability in electricity generation, posing challenges to grid stability. Ancillary service markets, such as the German control reserve market, allow industrial consumers and producers to offer flexibility in their power consumption or generation, contributing to grid stability while earning additional income. However, many participants use simple bidding strategies that may not maximize their revenues. This paper presents a methodology for forecasting bidding prices in pay-as-bid ancillary service markets, focusing on the German control reserve market. We evaluate various machine learning models, including Support Vector Regression, Decision Trees, and k-Nearest Neighbors, and compare their performance against benchmark models. To address the asymmetry in the revenue function of pay-as-bid markets, we introduce an offset adjustment technique that enhances the practical applicability of the forecasting models. Our analysis demonstrates that the proposed approach improves potential revenues by 37.79% to 74.44% compared to baseline models. When analyzing the relationship between the model forecasting errors and the revenue, a negative correlation is measured for three markets; according to the results, a reduction of 1€ /MW model price forecasting error (MAE) statistically leads to a yearly revenue increase between 483 €/MW and 3631 €/MW. The proposed methodology enables industrial participants to optimize their bidding strategies, leading to increased earnings and contributing to the efficiency and stability of the electrical grid. • A method for pay-as-bid price prediction in balancing markets has been developed. • ML-Models achieved up to 74.44 % more revenue wrt. baselines. • Offset adjustment for revenue optimization in pay-as-bid markets is introduced. • SVR and XGBRegressor are identified as the most effective forecasting models. • The influence of forecasting errors on revenue outcomes is analyzed.