AC-Optimal Power Flow Solutions with Security Constraints from Deep Neural Network Models

Kilwein, Zachary; Boukouvala, Fani; Laird, Carl D.; Castillo, Anya; Blakely, Logan; Eydenberg, Michael; Jalving, Jordan; Lisa, Batsch-Smith,

doi:10.1016/b978-0-323-88506-5.50142-x

Cited by 6 publications

(1 citation statement)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One advantage of our approach is that the classification model can learn the feasibility boundary in the higher dimensional space of the nominal variables instead of learning a single distance metric. We build on our previous work in [28] by introducing (a) a model-based sampling algorithm that can accurately find data points without the need for an iterative "guess and check" procedure, (b) exploring various neural network formulations/facilitated Python implementations, and (c) applying our approach to much larger grid problems with more contingencies.…”

Section: Related Workmentioning

confidence: 99%

Optimization with Neural Network Feasibility Surrogates: Formulations and Application to Security-Constrained Optimal Power Flow

Kilwein,

Jalving,

Eydenberg

et al. 2023

Energies

Self Cite

View full text Add to dashboard Cite

In many areas of constrained optimization, representing all possible constraints that give rise to an accurate feasible region can be difficult and computationally prohibitive for online use. Satisfying feasibility constraints becomes more challenging in high-dimensional, non-convex regimes which are common in engineering applications. A prominent example that is explored in the manuscript is the security-constrained optimal power flow (SCOPF) problem, which minimizes power generation costs, while enforcing system feasibility under contingency failures in the transmission network. In its full form, this problem has been modeled as a nonlinear two-stage stochastic programming problem. In this work, we propose a hybrid structure that incorporates and takes advantage of both a high-fidelity physical model and fast machine learning surrogates. Neural network (NN) models have been shown to classify highly non-linear functions and can be trained offline but require large training sets. In this work, we present how model-guided sampling can efficiently create datasets that are highly informative to a NN classifier for non-convex functions. We show how the resultant NN surrogates can be integrated into a non-linear program as smooth, continuous functions to simultaneously optimize the objective function and enforce feasibility using existing non-linear solvers. Overall, this allows us to optimize instances of the SCOPF problem with an order of magnitude CPU improvement over existing methods.

show abstract

Section: Related Workmentioning

confidence: 99%