A trained neural network surrogate for distribution grid voltage constraints is encoded exactly as mixed-integer linear constraints inside optimal power flow, delivering sub-1 V voltage error and faster solves than nonlinear models on networks with PV, EVs, and heat pumps.
Advancements and future directions in the application of machine learning to ac optimal power flow: a critical review
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.SY 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Enhanced Optimal Power Flow Using a Trained Neural Network Surrogate for Distribution Grid Constraints
A trained neural network surrogate for distribution grid voltage constraints is encoded exactly as mixed-integer linear constraints inside optimal power flow, delivering sub-1 V voltage error and faster solves than nonlinear models on networks with PV, EVs, and heat pumps.