Datamodel-Based Data Selection for Nonlinear Data-Enabled Predictive Control
This work addresses a specific bottleneck in control systems for nonlinear applications, offering an incremental improvement over existing methods.
The paper tackles the problem of selecting relevant data subsets for nonlinear Data-Enabled Predictive Control by proposing a datamodel-based approach that learns context-dependent importance scores, resulting in task-aware selection that substantially outperforms geometry-based heuristics, especially with small data subsets.
Data-Enabled Predictive Control (DeePC) has emerged as a powerful framework for controlling unknown systems directly from input-output data. For nonlinear systems, recent work has proposed selecting relevant subsets of data columns based on geometric proximity to the current operating point. However, such proximity-based selection ignores the control objective: different reference trajectories may benefit from different data even at the same operating point. In this paper, we propose a datamodel-based approach that learns a context-dependent influence function mapping the current initial trajectory and reference trajectory to column importance scores. Adapting the linear datamodel framework from machine learning, we model closed-loop cost as a linear function of column inclusion indicators, with coefficients that depend on the control context. Training on closed-loop simulations, our method captures which data columns actually improve tracking performance for specific control tasks. Experimental results demonstrate that task-aware selection substantially outperforms geometry-based heuristics, particularly when using small data subsets.