Explainable machine learning : a SHAP value-based approach to locational frequency stability

Tools

Kilembe, Alinane B. and Hamilton, Robert I. and Papadopoulos, Panagiotis N. (2025) Explainable machine learning : a SHAP value-based approach to locational frequency stability. International Journal of Electrical Power and Energy Systems, 170. 110885. ISSN 0142-0615 (https://doi.org/10.1016/j.ijepes.2025.110885)

[thumbnail of Kilembe-etal-IJEPES-2025-Explainable-machine-learning-a-SHAP-value-based-approach]
Preview
 Text. Filename: Kilembe-etal-IJEPES-2025-Explainable-machine-learning-a-SHAP-value-based-approach.pdf
Final Published Version
License: Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 logo
Download (2MB)| Preview

Abstract

The increasing complexity of modern power systems, resulting from the high integration of Converter Interfaced Generation (CIG), challenges the effectiveness of current analytical frequency approaches, leading to instability risks and a diminished understanding of local frequency dynamics. To address this, we propose a Machine Learning (ML)-based technique, utilising Artificial Neural Networks (ANNs) to capture the frequency characteristics of the system at a local level, and SHapley Additive exPlanations (SHAP), an additive feature attribution method, to enhance the understanding of the frequency dynamics. The proposed method further leverages these insights to inform system optimisation models for secure generation dispatch. Validation results from time-domain simulations conducted on a modified version of the IEEE 39-bus network indicate that the proposed method can accurately identify important system variables that shape the local and global frequency stability boundaries, and simple rules can be derived to guide system optimisation for enhanced system security.

ORCID iDs

Kilembe, Alinane B., Hamilton, Robert I. ORCID logoORCID: https://orcid.org/0000-0002-3268-8669 and Papadopoulos, Panagiotis N.;
CORE (COnnecting REpositories)