Primal-Dual Contextual Bayesian Optimization for Control System Online Optimization with Time-Average Constraints
This addresses the problem of optimizing constrained control systems with unknown dynamics for engineers, offering a novel algorithm with proven theoretical guarantees and practical improvements over existing methods.
The paper tackles online optimization of constrained control systems with unknown black-box functions under contextual disturbances, proposing a primal-dual contextual Bayesian optimization algorithm that achieves sublinear cumulative regret and zero time-average constraint violation. Simulation results on Gaussian process instances and a reactor tuning problem show the method provides close-to-optimal performance while maintaining constraint feasibility, outperforming current state-of-the-art methods that suffer from large regret or severe violations.
This paper studies the problem of online performance optimization of constrained closed-loop control systems, where both the objective and the constraints are unknown black-box functions affected by exogenous time-varying contextual disturbances. A primal-dual contextual Bayesian optimization algorithm is proposed that achieves sublinear cumulative regret with respect to the dynamic optimal solution under certain regularity conditions. Furthermore, the algorithm achieves zero time-average constraint violation, ensuring that the average value of the constraint function satisfies the desired constraint. The method is applied to both sampled instances from Gaussian processes and a continuous stirred tank reactor parameter tuning problem; simulation results show that the method simultaneously provides close-to-optimal performance and maintains constraint feasibility on average. This contrasts current state-of-the-art methods, which either suffer from large cumulative regret or severe constraint violations for the case studies presented.