On the use of Data-Driven Cost Function Identification in Parametrized NMPC
This work addresses practitioners in control systems by providing an incremental framework for data-driven NMPC with practical tools.
The paper tackles the feasibility of constrained Nonlinear Model Predictive Control (NMPC) design using data-driven cost function identification, proposing a complete implementation with freely available Python modules and a discussion on deriving control via data-driven modeling.
In this paper, a framework with complete numerical investigation is proposed regarding the feasibility of constrained Nonlinear Model Predictive Control (NMPC) design using Data-Driven model of the cost function. Although the idea is very much in the air, this paper proposes a complete implementation using python modules that are made freely available on a GitHub repository. Moreover, a discussion regarding the different ways of deriving control via data-driven modeling is proposed that can be of interest to practitioners.