6 papers
Generating adversarial inputs for a graph neural network model of AC power flow
Robert Parker
This work formulates and solves optimization problems to generate input points that yield high errors between a neural network's predicted AC power flow solution and solutions to t…
MathOptAI.jl: Embed trained machine learning predictors into JuMP models
Oscar Dowson, Robert B Parker, Russel Bent
We present \texttt{MathOptAI.jl}, an open-source Julia library for embedding trained machine learning predictors into a JuMP model. \texttt{MathOptAI.jl} can embed a wide variety o…
Exploiting block triangular submatrices in KKT systems
Robert Parker, Manuel Garcia, Russell Bent
We propose a method for solving Karush-Kuhn-Tucker (KKT) systems that exploits block triangular submatrices by first using a Schur complement decomposition to isolate the block tri…
Variable aggregation for nonlinear optimization problems
Sakshi Naik, Lorenz Biegler, Russell Bent +1
Variable aggregation has been largely studied as an important pre-solve algorithm for optimization of linear and mixed-integer programs. Although some nonlinear solvers and algebra…
Nonlinear Optimization with GPU-Accelerated Neural Network Constraints
Robert Parker, Oscar Dowson, Nicole LoGiudice +2
We propose a reduced-space formulation for optimizing over trained neural networks where the network's outputs and derivatives are evaluated on a GPU. To do this, we treat the neur…
Transient Stability-Constrained OPF: Neural Network Surrogate Models and Pricing Stability
Manuel Garcia, Nicole LoGiudice, Robert Parker +1
A Transient Stability-Constrained Optimal Power Flow (TSC-OPF) problem is proposed that enforces frequency stability constraints using Neural Network (NN) surrogate models. NNs are…