Wind farm control reduces power imbalance costs by tailoring clear strategies
Value-oriented policy distillation for interpretable wind farm power control
Artificial Intelligence
Summary
Balancing electricity supply and demand is hard for wind farms because prices can change unpredictably. The paper shows how a new method uses simple, understandable models to control wind farm power in a way that lowers costs and helps keep the power system stable. The method combines expert knowledge with a special way of learning from data, making the decisions easy to explain and trust. Tests with real wind farm and grid data show it can cut imbalance costs by over 80%, doing better than other standard approaches.
What this means in practice
- •For wind farm operators: Use transparent control models that reduce imbalance compensation costs while supporting system stability under uncertain electricity prices.
- •For energy grid managers: Adopt interpretable wind generation controls to anticipate imbalance prices and improve grid balance without relying on black-box AI methods.
Tested on one dataset.
Authors
Max Bruninx, Timothy Verstraeten, Jan Decuyper, Ann Nowé, Jan Helsen
Abstract
Wind farm power control can help the system maintain balance and avoid blackouts. In Europe, this can be achieved through implicit balancing, where a wind farm adjusts its power setpoint in anticipation of the imbalance price using information published by the Transmission System Operator. Thereby, the wind farm helps restore system balance while also reducing its own imbalance costs resulting from forecast errors. However, implicit balancing is a challenging problem since the settlement price is unknown in advance and can be impacted by the pursued control strategy. Reinforcement learning methods could help to solve this problem, but lack the interpretability needed to be deployed on real wind farms. Therefore, we propose a policy distillation framework using explainable boosting machines (EBMs), a variant of generalized additive models, to obtain a transparent control policy. To increase the value captured by the EBM model, we introduce a value-oriented perspective to policy distillation inspired by research in the field of energy forecasting. Furthermore, we suggest to include expert knowledge during model design, such that the control strategy is also justifiable to stakeholders. Using real data of the Belgian grid and an offshore wind farm, we find that our value-oriented and expert-based controller can reduce imbalance costs by 82%, while outperforming a price threshold controller as well as a policy distillation baseline using decision trees.