Saved in:
Bibliographic Details
Main Authors: Cummins, Michael, Padoan, Alberto, Moffat, Keith, Dorfler, Florian, Lygeros, John
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.06481
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908383797313536
author Cummins, Michael
Padoan, Alberto
Moffat, Keith
Dorfler, Florian
Lygeros, John
author_facet Cummins, Michael
Padoan, Alberto
Moffat, Keith
Dorfler, Florian
Lygeros, John
contents This paper introduces Data-enabled Predictive Control Hyperparameter Tuning via Differentiable Optimization (DeePC-Hunt), a backpropagation-based method for automatic hyperparameter tuning of the DeePC algorithm. The necessity for such a method arises from the importance of hyperparameter selection to achieve satisfactory closed-loop DeePC performance. The standard methods for hyperparameter selection are to either optimize the open-loop performance, or use manual guess-and-check. Optimizing the open-loop performance can result in unacceptable closed-loop behavior, while manual guess-and-check can pose safety challenges. DeePC-Hunt provides an alternative method for hyperparameter tuning which uses an approximate model of the system dynamics and backpropagation to directly optimize hyperparameters for the closed-loop DeePC performance. Numerical simulations demonstrate the effectiveness of DeePC in combination with DeePC-Hunt in a complex stabilization task for a nonlinear system and its superiority over model-based control strategies in terms of robustness to model misspecifications.
format Preprint
id arxiv_https___arxiv_org_abs_2412_06481
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DeePC-Hunt: Data-enabled Predictive Control Hyperparameter Tuning via Differentiable Optimization
Cummins, Michael
Padoan, Alberto
Moffat, Keith
Dorfler, Florian
Lygeros, John
Optimization and Control
This paper introduces Data-enabled Predictive Control Hyperparameter Tuning via Differentiable Optimization (DeePC-Hunt), a backpropagation-based method for automatic hyperparameter tuning of the DeePC algorithm. The necessity for such a method arises from the importance of hyperparameter selection to achieve satisfactory closed-loop DeePC performance. The standard methods for hyperparameter selection are to either optimize the open-loop performance, or use manual guess-and-check. Optimizing the open-loop performance can result in unacceptable closed-loop behavior, while manual guess-and-check can pose safety challenges. DeePC-Hunt provides an alternative method for hyperparameter tuning which uses an approximate model of the system dynamics and backpropagation to directly optimize hyperparameters for the closed-loop DeePC performance. Numerical simulations demonstrate the effectiveness of DeePC in combination with DeePC-Hunt in a complex stabilization task for a nonlinear system and its superiority over model-based control strategies in terms of robustness to model misspecifications.
title DeePC-Hunt: Data-enabled Predictive Control Hyperparameter Tuning via Differentiable Optimization
topic Optimization and Control
url https://arxiv.org/abs/2412.06481