Learning constraint surrogate model for two-stage stochastic unit commitment

Document Type

Article

Publication Date

10-1-2026

Abstract

The increasing penetration of renewable energy sources introduces significant uncertainty in power system operations, making traditional deterministic unit commitment approaches computationally expensive. This paper presents a machine learning surrogate modeling approach designed to reformulate the feasible design space of the two-stage stochastic unit commitment (TSUC) problem, reducing its computational complexity. The proposed method uses a support vector machine (SVM) to construct a surrogate model based on the governing equations of the learner. This model replaces the original 2×|L|×|S| transmission line flow constraints, where |S| is the number of uncertainty scenarios and |L| is the number of transmission lines, with only |S| linear inequality constraints, resulting in a substantial reduction in model size. The approach is theoretically grounded in the polyhedral structure of the feasible region under DC power flow approximation, enabling the transformation of 2×|L| line flow limit constraints into a single linear constraint. The surrogate model is trained using data generated from computationally efficient DC optimal power flow simulations. Simulation results on the IEEE 57-, 118-, and 200-bus systems indicate that the SVM half-space constraints achieve accuracies of 99.72%, 99.88%, and 99.81%, respectively, and reduce TSUC computational time by 46%, 31%, and 29%, respectively, with a negligible increase in generation cost. This shows the effectiveness of the proposed approach for practical power system operations under renewable energy uncertainty.

Publication Source (Journal or Book title)

Electric Power Systems Research

This document is currently not available here.

Share

COinS