5th International Conference on Electrical, Computer, Communications and Mechatronics Engineering - ICECCME 2025, Zanzibar (Tanzania). 16-19 October 2025
Summary:
This paper proposes a fast and interpretable framework for frequency-constrained unit commitment (FCUC) using machine-learning (ML) surrogates. Unlike prior studies that rely on proprietary system-frequency-response tools, we use an open-source second-order differential equation (SODE) model to simulate generator outages, generating a 117000 -scenario dataset. Three linear classifiers -Logistic Regression (LR), Linear Discriminant Analysis (LDA), and a log-loss Stochastic-Gradient-Descent model (SGD-Log)-are trained on this dataset and inserted as linear constraints in a mixed-integer UC model to enforce frequency adequacy. The surrogates detect ≥98.8 % of unsafe operating points (≤32 false negatives) while training in only 0.1 s to 2.3 s. Applied to a spring-week case study on the La Palma island system, they uphold a strict -3 Hz nadir limit, achieve average nadirs of -1.23 Hz to -1.31 Hz, compared with -1.41 Hz in the unconstrained base case, and raise weekly cost by no more than 1.3 % above that baseline. Also, in comparison with a first-order differential equation (FODE) model, the SODE-ML formulations solve 40−390× faster (12.2s to 101.4s vs. 4767s) without linearisation assumptions. These results demonstrate that reproducible, SODE-labelled surrogates enable secure and computationally efficient FCUC for low-inertia grids.
Spanish layman's summary:
Este trabajo usa modelos sustitutos de aprendizaje automático, entrenados con simulaciones de frecuencia de segundo orden, para imponer seguridad de frecuencia en la programación de generación de redes insulares de baja inercia, con gran ahorro computacional y bajo sobrecoste.
English layman's summary:
This paper uses machine-learning surrogates trained on second-order frequency-response simulations to enforce frequency security in unit commitment for low-inertia island grids, achieving much faster optimization with only a small cost increase.
Keywords: Frequency-constrained unit commitment (FCUC), machine learning (ML), frequency nadir (FN), second-order differential equation (SODE), mixed-integer linear programming (MILP), renewable energy sources (RES).
DOI: 
https://doi.org/10.1109/ICECCME64568.2025.11277713
Published in: ICECCME 2025: Conference proceedings, pp: 1-6, ISBN: 979-8-3315-3557-5
Publication date: 15-Dec-2025.
Citation:
A.O. Olasoji, D.T.O. Oyedokun, M. Rajabdorri, J.E. Sierra-Aguilar, Ch.E. Okafor, M. Mditshwa, "Frequency-Constrained UC via Second-Order ODEs with ML Surrogates", presented at 5th International Conference on Electrical, Computer, Communications and Mechatronics Engineering - ICECCME 2025, Zanzibar, Tanzania, 16-19 October 2025. In: ICECCME 2025: Conference proceedings, pp. 1-6, doi: 10.1109/ICECCME64568.2025.11277713
IIT-25-410C
