[2507.09503] Neural Two-Stage Stochastic Optimization for Solving Unit Commitment Problem

Electrical Engineering and Systems Science > Systems and Control arXiv:2507.09503 (eess) This paper has been withdrawn by Zhentong Shao [Submitted on 13 Jul 2025 (v1), last revised 8 Apr 2026 (this version, v2)] Title:Neural Two-Stage Stochastic Optimization for Solving Unit Commitment Problem Authors:Zhentong Shao, Jingtao Qin, Nanpeng Yu View a PDF of the paper titled Neural Two-Stage Stochastic Optimization for Solving Unit Commitment Problem, by Zhentong Shao and Jingtao Qin and Nanpeng Yu No PDF available, click to view other formats Abstract:This paper proposes a neural stochastic optimization method for efficiently solving the two-stage stochastic unit commitment (2S-SUC) problem under high-dimensional uncertainty scenarios. The proposed method approximates the second-stage recourse problem using a deep neural network trained to map commitment decisions and uncertainty features to recourse costs. The trained network is subsequently embedded into the first-stage UC problem as a mixed-integer linear program (MILP), allowing for explicit enforcement of operational constraints while preserving the key uncertainty characteristics. A scenario-embedding network is employed to enable dimensionality reduction and feature aggregation across arbitrary scenario sets, serving as a data-driven scenario reduction mechanism. Numerical experiments on IEEE 5-bus, 30-bus, and 118-bus systems demonstrate that the proposed neural two-stage stochastic optimization method achieves solutio...