English

Data-driven predictive control in a stochastic setting: a unified framework

Systems and Control 2022-11-22 v2 Systems and Control Optimization and Control

Abstract

Data-driven predictive control (DDPC) has been recently proposed as an effective alternative to traditional model-predictive control (MPC) for its unique features of being time-efficient and unbiased with respect to the oracle solution. Nonetheless, it has also been observed that noise may strongly jeopardize the final closed-loop performance since it affects both the data-based system representation and the control update computed from the online measurements. Recent studies have shown that regularization is potentially a successful tool to counteract the effect of noise. At the same time, regularization requires the tuning of a set of penalty terms, whose choice might be practically difficult without closed-loop experiments. In this paper, by means of subspace identification tools, we pursue a three-fold goal: (i)(i) we set up a unified framework for the existing regularized data-driven predictive control schemes for stochastic systems; (ii)(ii) we introduce γ\gamma-DDPC, an efficient two-stage scheme that splits the optimization problem into two parts: fitting the initial conditions and optimizing the future performance, while guaranteeing constraint satisfaction; (iii)(iii) we discuss the role of regularization for data-driven predictive control, providing new insight on whenwhen and howhow it should be applied. A benchmark numerical case study finally illustrates the performance of γ\gamma-DDPC, showing how controller design can be simplified in terms of tuning effort and computational complexity when benefiting from the insights coming from the subspace identification realm.

Keywords

Cite

@article{arxiv.2203.10846,
  title  = {Data-driven predictive control in a stochastic setting: a unified framework},
  author = {Valentina Breschi and Alessandro Chiuso and Simone Formentin},
  journal= {arXiv preprint arXiv:2203.10846},
  year   = {2022}
}

Comments

17 pages, 12 figures

R2 v1 2026-06-24T10:20:13.514Z