Secondary control activation analysed and predicted with explainable AI

The transition to a renewable energy system poses challenges for power grid operation and stability. Secondary control is key in restoring the power system to its reference following a disturbance. Underestimating the necessary control capacity may require emergency measures, such as load shedding. Hence, a solid understanding of the emerging risks and the driving factors of control is needed. In this contribution, we establish an explainable machine learning model for the activation of secondary control power in Germany. Training gradient boosted trees, we obtain an accurate description of control activation. Using SHapely Additive exPlanation (SHAP) values, we investigate the dependency between control activation and external features such as the generation mix, forecasting errors, and electricity market data. Thereby, our analysis reveals drivers that lead to high reserve requirements in the German power system. Our transparent approach, utilizing open data and making machine learning models interpretable, opens new scientific discovery avenues.

[1]  Dominik Jost,et al.  Dynamic dimensioning of frequency restoration reserve capacity based on quantile regression , 2015, 2015 12th International Conference on the European Energy Market (EEM).

[2]  Robbie Morrison,et al.  Energy system modeling: Public transparency, scientific reproducibility, and open development , 2018 .

[3]  Dirk Witthaut,et al.  Exploring deterministic frequency deviations with explainable AI , 2021, 2021 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm).

[4]  Anthony Papavasiliou,et al.  Dynamic dimensioning approach for operating reserves: Proof of concept in Belgium , 2019, Energy Policy.

[5]  Dirk Uwe Sauer,et al.  Automatic frequency restoration reserve market prediction: Methodology and comparison of various approaches , 2020, Applied Energy.

[6]  E. Welfonder,et al.  High frequency deviations within the European Power System: Origins and proposals for improvement , 2009, 2009 IEEE/PES Power Systems Conference and Exposition.

[7]  Yonghua Song,et al.  Artificial intelligence in sustainable energy industry: Status Quo, challenges and opportunities , 2021, Journal of Cleaner Production.

[8]  Reinhard Haas,et al.  Machine learning analysis for a flexibility energy approach towards renewable energy integration with dynamic forecasting of electricity balancing power , 2017, 2017 14th International Conference on the European Energy Market (EEM).

[9]  Tie-Yan Liu,et al.  LightGBM: A Highly Efficient Gradient Boosting Decision Tree , 2017, NIPS.

[10]  Lion Hirth,et al.  Short-term electricity trading for system balancing: An empirical analysis of the role of intraday trading in balancing Germany's electricity system , 2019, Renewable and Sustainable Energy Reviews.

[11]  Scott M. Lundberg,et al.  Consistent Individualized Feature Attribution for Tree Ensembles , 2018, ArXiv.

[12]  Lion Hirth,et al.  The ENTSO-E Transparency Platform – A review of Europe’s most ambitious electricity data platform , 2018, Applied Energy.

[13]  Christoph Weber,et al.  Impacts of Dynamic Probabilistic Reserve Sizing Techniques on Reserve Requirements and System Costs , 2015, IEEE Transactions on Sustainable Energy.

[14]  Robert Tibshirani,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition , 2001, Springer Series in Statistics.

[15]  Hugh Chen,et al.  From local explanations to global understanding with explainable AI for trees , 2020, Nature Machine Intelligence.

[16]  Scott Otterson,et al.  Dynamic sizing of automatic and manual frequency restoration reserves for different product lengths , 2016, 2016 13th International Conference on the European Energy Market (EEM).

[17]  Francisco Herrera,et al.  Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI , 2020, Inf. Fusion.

[18]  Hendrik Lens,et al.  Impact of Current Market Developments in Europe on Deterministic Grid Frequency Deviations and Frequency Restauration Reserve Demand , 2018, 2018 15th International Conference on the European Energy Market (EEM).

[19]  Dirk Witthaut,et al.  Revealing drivers and risks for power grid frequency stability with explainable AI , 2021, Patterns.