Convex Approximations for a Bi-level Formulation of Data-Enabled Predictive Control

TL;DR

This paper introduces convex approximations for a bi-level data-driven control formulation, unifies existing DeePC variants, and proposes a new variant with strong empirical performance on complex systems.

Contribution

It develops a bi-level optimization framework for DeePC, introduces convex relaxations, and establishes equivalences among variants, including a novel method with superior empirical results.

Findings

Unified framework for DeePC variants

Convex relaxations enable implicit system identification

New DeePC-SVD-Iter variant shows strong empirical performance

Abstract

The Willems' fundamental lemma, which characterizes linear time-invariant (LTI) systems using input and output trajectories, has found many successful applications. Combining this with receding horizon control leads to a popular Data-EnablEd Predictive Control (DeePC) scheme. DeePC is first established for LTI systems and has been extended and applied for practical systems beyond LTI settings. However, the relationship between different DeePC variants, involving regularization and dimension reduction, remains unclear. In this paper, we first introduce a new bi-level optimization formulation that combines a data pre-processing step as an inner problem (system identification) and predictive control as an outer problem (online control). We next discuss a series of convex approximations by relaxing some hard constraints in the bi-level optimization as suitable regularization terms, accounting for an implicit identification. These include some existing DeePC variants as well as two new variants, for which we establish their equivalence under appropriate settings. Notably, our analysis reveals a novel variant, called DeePC-SVD-Iter, which has remarkable empirical performance of direct methods on systems beyond deterministic LTI settings.