loading page

Evaluating Machine Learning Models for the Fast Identification of Contingency Cases
  • Florian Schaefer,
  • Jan-Hendrik Menke,
  • Martin Braun
Florian Schaefer
University of Kassel
Author Profile
Jan-Hendrik Menke
University of Kassel
Author Profile
Martin Braun
University of Kassel
Author Profile


Fast approximations of power flow results are beneficial in power system planning and live operation. In planning, millions of power flow calculations are necessary if multiple years, different control strategies, or contingency policies are to be considered. In live operation, grid operators must assess if grid states comply with contingency requirements in a short time. In this paper, we compare regression and classification methods to either predict multi-variable results, e.g., bus voltage magnitudes and line loadings, or binary classifications of time steps to identify critical loading situations. We test the methods on three realistic power systems based on time series in 15min and 5min resolution of one year. We compare different machine learning models, such as multilayer perceptrons (MLPs), decision trees, k-nearest neighbors, gradient boosting, and evaluate the required training time and prediction times as well as the prediction errors. We additionally determine the amount of training data needed for each method and show results, including the approximation of untrained curtailment of generation. Regarding the compared methods, we identified the MLPs as most suitable for the task. The MLP-based models can predict critical situations with an accuracy of 97-98% and a very low number of false negative predictions of 0.0-0.64%.

Peer review status:Published

25 Aug 2020Submitted to Applied AI Letters
27 Aug 2020Reviewer(s) Assigned
30 Sep 2020Review(s) Completed, Editorial Evaluation Pending
30 Sep 2020Editorial Decision: Revise Minor
03 Nov 20201st Revision Received
06 Nov 2020Submission Checks Completed
06 Nov 2020Assigned to Editor
09 Nov 2020Reviewer(s) Assigned
23 Nov 2020Review(s) Completed, Editorial Evaluation Pending
23 Nov 2020Editorial Decision: Accept
15 Dec 2020Published in Applied AI Letters. 10.1002/ail2.19