Online convex optimization for data-driven control of dynamical systems

Abstract

We propose an algorithm based on online convex optimization for controlling discrete-time linear dynamical systems. The algorithm is data-driven, i.e., does not require a model of the system, and is able to handle a priori unknown and time-varying cost functions. To this end, we make use of a single persistently exciting input-output sequence of the system and results from behavioral systems theory which enable it to handle unknown linear time-invariant systems. Moreover, we consider noisy output feedback instead of full state measurements and allow general economic cost functions. Our analysis of the closed loop reveals that the algorithm is able to achieve sublinear regret, where the measurement noise only adds an additional constant term to the regret upper bound. In order to do so, we derive a data-driven characterization of the steady-state manifold of an unknown system. Moreover, our algorithm is able to asymptotically exactly estimate the measurement noise. The effectiveness and applicational aspects of the proposed method are illustrated by means of a detailed simulation example in thermal control.

arXiv comment14 pages

References in corpus (7)

• Data-Driven Model Predictive Control with Stability and Robustness Guarantees
• Robust data-driven state-feedback design
• Combining Prior Knowledge and Data for Robust Controller Design
• A trajectory-based framework for data-driven system analysis and control
• Stability of Dynamic Feedback Optimization with Applications to Power Systems
• Online Gradient Descent for Linear Dynamical Systems
• An online convex optimization algorithm for controlling linear systems with state and input constraints

Cited by in corpus (4)

• Online Optimization of Dynamical Systems with Deep Learning Perception
• On the relation between dynamic regret and closed-loop stability
• Online convex optimization for constrained control of linear systems using a reference governor
• Online Optimization and Ambiguity-based Learning of Distributionally Uncertain Dynamic Systems