Distributionally Robust Unit Commitment Models: Theory and Numerical Results
Forthcoming in Electric Power Systems Research, vol. 263, 113754, 2027
We develop a unified Benders framework to compare stochastic, robust and distributionally robust Unit Commitment models, using difference-of-convex methods to address nonconvex Wasserstein separation problems. Computational efficiency and out-of-sample performance are evaluated across several norms.
Recommended citation: Azéma, M., Leclère, V., van Ackooij, W. (2027). Distributionally Robust Unit Commitment Models: Theory and Numerical Results. Electric Power Systems Research, 263, 113754. https://doi.org/10.1016/j.epsr.2026.113754.
Download Paper