Data-Driven System Level Synthesis

Abstract

We establish data-driven versions of the System Level Synthesis (SLS) parameterization of achievable closed-loop system responses for a linear-time-invariant system over a finite-horizon. Inspired by recent work in data-driven control that leverages tools from behavioral theory, we show that optimization problems over system-responses can be posed using only libraries of past system trajectories, without explicitly identifying a system model. We first consider the idealized setting of noise free trajectories, and show an exact equivalence between traditional and data-driven SLS. We then show that in the case of a system driven by process noise, tools from robust SLS can be used to characterize the effects of noise on closed-loop performance, and further draw on tools from matrix concentration to show that a simple trajectory averaging technique can be used to mitigate these effects. We end with numerical experiments showing the soundness of our methods.

References in corpus (3)

• Global Convergence of Policy Gradient Methods for the Linear Quadratic Regulator
• Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systems
• Distributed and Localized Model Predictive Control via System Level Synthesis

Cited by in corpus (3)

• From System Level Synthesis to Robust Closed-loop Data-enabled Predictive Control
• Descending Predictive Feedback: From Optimal Control to the Sensorimotor System
• Sample Complexity of the Robust LQG Regulator with Coprime Factors Uncertainty