.png){kind=icon}
Return
Dynamic graph learning: A solution for unit commitment problems with topology changes incorporating demand response
.png){kind=icon}
PRE
AI
DOI：10.1016/j.epsr.2026.113711.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Encodes stochastic unit maintenance into temporal graph structures. • Proposes DyGTCN to capture evolving spatiotemporal grid patterns. • Hierarchical SC-DAM dynamically tunes scheduling for feasibility. • Achieves high-accuracy unit state prediction with computational efficiency.
Keywords:
Unit commitment
Topology change
Dynamic graph learning
Deep neural network
Journal
IF:
4.2
Papers:
1.2W
Citations:
2.2W
Organization
Cited Papers
.png){kind=icon}
ShareSaveShareSave
Recursive Learning Based Smart Energy Management With Two-Level Dynamic Pricing Demand Response
PREAI
ShareSave
View more