Ensemble Provably Robust Learn-to-Optimize Approach for Security-Constrained Unit Commitment

Security-constrained unit commitment (SCUC) is the basis for power systems and markets operation, which is solved periodically via mixed-integer programming (MIP) with limited input data changes to historical solved instances. This paper proposes an ensemble provably robust learn-to-optimize approach (EPR-L2O) for transforming the MIP-based SCUC into the tractable convex problem with predictable solving time by identifying the integer part of MIP, denoted by unit status integer solution. It formulates the SCUC model for unit status integer solution generation, prunes the generated integer solutions, clusters the units based on their operation status, and proposes the provably robust learning approach to training the unit status integer solution identifiers, which are provably robust against the input adversarial perturbation. After learning, the integer solutions from different identifiers are assembled to identify the integer variables of SCUC. Case study verifies that: 1) EPR-L2O achieves 6.91, 19.71, and 22.14 times acceleration in the 30-bus, 118-bus, and 300-bus systems than the Branch-and-Bound; 2) compared to cross-entropy-based learning, EPR-L2O reduces the MIP gap by 0.031%, 0.21%, and 0.0084% in the 30-bus, 118-bus, and 300-bus systems, indicating its operation economy and robustness.