.png){kind=icon}
Return
Graph neural network with physics-informed optimization layer for unit commitment and economic dispatch
.png){kind=icon}
OA
AI
DOI：10.1016/j.ijepes.2026.111821.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• A hybrid GNN framework with a decoupled discrete-continuous physics layer. • Iterative PICC strictly enforces the minimum start–stop times and the constraints in continuous dispatch. • Achieves near-optimal cost (+0.0157% gap) versus commercial Gurobi/CPLEX. • Maintains 0% constraint violation rate even under extreme/unseen scenarios and measurement errors. • Accelerates scheduling by orders of magnitude via license-free tensor operations.
Keywords:
Unit commitment
Economic dispatch
Physics-informed neural networks (PINNs)
Graph neural networks
Deep learning
Constrained optimization
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
I
IF:
5
Papers:
666
Citations:
0
Organization
Cited Papers
Forgetting velocity based improved comprehensive learning particle swarm optimization for non-convex economic dispatch problems with valve-point effects and multi-fuel options.png)
ENERGY
ENERGYIF9.4
PREAI
ShareSave
ShareSaveShareSaveShareSaveShareSaveImplementation of coyote optimization algorithm for solving unit commitment problem in power systemsENERGY
ENERGYIF9.4
PREAI
ShareSave
View more