English

Revealing drivers and risks for power grid frequency stability with explainable AI

Systems and Control 2022-01-07 v2 Systems and Control Data Analysis, Statistics and Probability

Abstract

Stable operation of the electrical power system requires the power grid frequency to stay within strict operational limits. With millions of consumers and thousands of generators connected to a power grid, detailed human-build models can no longer capture the full dynamics of this complex system. Modern machine learning algorithms provide a powerful alternative for system modelling and prediction, but the intrinsic black-box character of many models impedes scientific insights and poses severe security risks. Here, we show how eXplainable AI (XAI) alleviates these problems by revealing critical dependencies and influences on the power grid frequency. We accurately predict frequency stability indicators (such as RoCoF and Nadir) for three major European synchronous areas and identify key features that determine the power grid stability. Load ramps, specific generation ramps but also prices and forecast errors are central to understand and stabilize the power grid.

Keywords

Cite

@article{arxiv.2106.04341,
  title  = {Revealing drivers and risks for power grid frequency stability with explainable AI},
  author = {Johannes Kruse and Benjamin Schäfer and Dirk Witthaut},
  journal= {arXiv preprint arXiv:2106.04341},
  year   = {2022}
}

Comments

26 pages, 19 figures; updated comments; this is the initially submitted version, for the final version see journal link

R2 v1 2026-06-24T02:57:32.275Z