VABO: Violation-Aware Bayesian Optimization for Closed-Loop Control Performance Optimization with Unmodeled Constraints
This work addresses performance optimization for control systems with unmodeled constraints, offering a practical solution for industrial applications like vapor compression systems, though it is incremental relative to existing Bayesian optimization methods.
The paper tackles the problem of optimizing closed-loop control systems with unmodeled constraints by proposing VABO, a violation-aware Bayesian optimization algorithm that allows budgeted constraint violations to accelerate learning and optimization, demonstrated through energy minimization in industrial vapor compression systems.
We study the problem of performance optimization of closed-loop control systems with unmodeled dynamics. Bayesian optimization (BO) has been demonstrated effective for improving closed-loop performance by automatically tuning controller gains or reference setpoints in a model-free manner. However, BO methods have rarely been tested on dynamical systems with unmodeled constraints. In this paper, we propose a violation-aware BO algorithm (VABO) that optimizes closed-loop performance while simultaneously learning constraint-feasible solutions. Unlike classical constrained BO methods which allow an unlimited constraint violations, or safe BO algorithms that are conservative and try to operate with near-zero violations, we allow budgeted constraint violations to improve constraint learning and accelerate optimization. We demonstrate the effectiveness of our proposed VABO method for energy minimization of industrial vapor compression systems.