Learning-to-solve unit commitment based on few-shot physics-guided spatial-temporal graph convolution network

TL;DR

This paper introduces a few-shot physics-guided spatial-temporal graph convolutional network for rapid unit commitment solving, improving feasibility and efficiency over traditional methods.

Contribution

It presents a novel few-shot learning scheme combined with a tailored STGCN and a straight-through estimator for mixed integer solutions in unit commitment.

Findings

Outperforms mainstream learning methods in UC feasibility

Surpasses traditional solvers in computational efficiency

Effective in handling mixed integer constraints

Abstract

This letter proposes a few-shot physics-guided spatial temporal graph convolutional network (FPG-STGCN) to fast solve unit commitment (UC). Firstly, STGCN is tailored to parameterize UC. Then, few-shot physics-guided learning scheme is proposed. It exploits few typical UC solutions yielded via commercial optimizer to escape from local minimum, and leverages the augmented Lagrangian method for constraint satisfaction. To further enable both feasibility and continuous relaxation for integers in learning process, straight-through estimator for Tanh-Sign composition is proposed to fully differentiate the mixed integer solution space. Case study on the IEEE benchmark justifies that, our method bests mainstream learning ways on UC feasibility, and surpasses traditional solver on efficiency.