Data-Driven Predictive Control and MPC: Do we achieve optimality?
Abstract: In this paper, we explore the interplay between Predictive Control and closed-loop optimality, spanning from Model Predictive Control to Data-Driven Predictive Control. Predictive Control in general relies on some form of prediction scheme on the real system trajectories. However, these predictions may not accurately capture the real system dynamics, for e.g., due to stochasticity, resulting in sub-optimal control policies. This lack of optimality is a critical issue in case of problems with economic objectives. We address this by providing sufficient conditions on the underlying prediction scheme such that a Predictive Controller can achieve closed-loop optimality. However, these conditions do not readily extend to Data-Driven Predictive Control. In this context of closed-loop optimality, we conclude that the factor distinguishing the approaches within Data-Driven Predictive Control is if they can be cast as a sequential decision-making process or not, rather than the dichotomy of model-based vs. model-free. Furthermore, we show that the conventional approach of improving the prediction accuracy from data may not guarantee optimality.
- Data-enabled predictive control: In the shallows of the deepc. In ECC, 307–312.
- MPC: Current practice and challenges. Cont. Eng. Practice.
- On the relationship between data-enabled predictive control and subspace predictive control. In 2021 European Control Conference (ECC), 222–229. IEEE.
- Data-driven economic nmpc using reinforcement learning. IEEE Transactions on Automatic Control, 65(2), 636–648.
- Economic mpc of markov decision processes: Dissipativity in undiscounted infinite-horizon optimal control. Automatica.
- Learning-based model predictive control: Toward safe learning in control. Annual Review of Control, Robotics, and Autonomous Systems.
- On direct vs indirect data-driven predictive control. In CDC.
- Online learning-based model predictive control with gaussian process models and stability guarantees. Int. Jour. of Robust and Nonlinear Cont., 31(18), 8785–8812.
- On the regularization in deepc. IFAC-PapersOnLine, 56(2), 625–631.
- Fusion of machine learning and MPC under uncertainty: What advances are on the horizon? In ACC.
- Performance-oriented model learning for data-driven mpc design. IEEE control systems letters, 3(3), 577–582.
- Model predictive control: theory, computation, and design, volume 2. Nob Hill Publishing Madison, WI.
- Data-driven predictive control for nonlinear systems using feature selection. CDC.
- Causality-informed data-driven predictive control. arXiv preprint arXiv:2311.09545.
- Model-free data-driven predictive control using reinforcement learning. CDC.
- Reinforcement learning: An introduction. MIT press.
- Machine learning-based predictive control of nonlinear processes. part i: theory. AIChE Journal.
- A data-driven predictive controller design based on reduced hankel matrix. In ASCC, 1–7.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.
