SDO uses an ML surrogate to solve a lightweight auxiliary problem that provides warm starts for full-scale NMPC, yielding faster convergence and two orders of magnitude less training data than behavior cloning in a 24-hour pressurized water reactor load-following case.
Learning for casadi: Data-driven models in numerical optimization,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Accelerating Full-Scale Nonlinear Model Predictive Control via Surrogate Dynamics Optimization
SDO uses an ML surrogate to solve a lightweight auxiliary problem that provides warm starts for full-scale NMPC, yielding faster convergence and two orders of magnitude less training data than behavior cloning in a 24-hour pressurized water reactor load-following case.