A Generative Verification Framework on Statistical Stability for Data-Driven Controllers

• Published in: IEEE access Vol. 11; pp. 5267 - 5280
• Main Author: Lee, Suwon
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Adaptive control; Artificial neural networks; Classification; Control systems; Control systems design; Control theory; Controllers; Data-driven analysis; Deep learning; deep neural network; Lyapunov methods; Neural networks; nonlinear controller; nonlinear system verification; Numerical stability; optimal control; performance analysis; Stability analysis; Stability criteria; statistical stability; Support vector machines; variational autoencoder; Verification
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2023.3236917

This study proposes a novel framework for evaluating the stability of data-driven controllers and the concept of statistical stability. The proposed framework can be used when it is challenging to show stability through conventional control theory. The novelty of this paper lies in that it provides a method for scientifically analyzing the stability of data-driven controllers, thereby improving the quality of data-driven controllers. The proposed framework consists of three parts: the generative model, controller optimizer, and verification model. A variational autoencoder is used to classify and randomly generate data, and the generated data are used to train the controller. A support vector machine is used to classify areas where the controller is statistically stable. The statistical stability of an optimal controller designed using a deep neural network structure is analyzed using the proposed framework.