Towards robustness evaluation of models for cyber-physical systems extended abstract

Start Page
106
End Page
109
Citation
27. Workshop Methoden und Beschreibungssprachen zur Modellierung und Verifikation von Schaltungen und Systemen, MBMV 2024
Contribution to Conference
27. Workshop Methoden und Beschreibungssprachen zur Modellierung und Verifikation von Schaltungen und Systemen, MBMV 2024  
Scopus ID
2-s2.0-85192963537
Publisher
VDE VERLAG GMBH
ISBN
978-3-8007-6267-5
This paper presents a novel approach to evaluate robustness of models for Cyber-Physical Systems (CPS). We consider a CPS to be a hybrid system and learn models from data using decision tree regressors. We define robustness as the capability of the learned model to maintain its performance under varying unseen conditions. By systematically incorporating a perturbation process and calculating key statistical measures on the differences in model predictions, our method provides a comprehensive evaluation framework when modeling CPS. This approach enhances our understanding of a model’s robustness in the face of uncertainties, ultimately contributing to the development of more robust models for CPS. We demonstrate the application of our method for a simulated temperature control system.
Subjects
MLE@TUHH
DDC Class
005: Computer Programming, Programs, Data and Security