Cautious hierarchical switching control of stochastic linear systems

摘要

Standard switching control methods are based on the certainty equivalence philosophy in that, at each switching time, the supervisor selects the candidate controller that is better tuned to the currently estimated process model. In this paper, we propose a new supervisory switching logic that takes into account the uncertainty on the process description when performing the controller selection. Specifically, a probability measure describing the likelihood of the different models is computed on-line based on the collected data and, at each switching time, the supervisor selects the candidate controller that, according to this probability measure, performs the best on the average. If the candidate controller class is hierarchically structured so that for each model one has available several controllers with distinct levels of robustness, the supervisor automatically selects the controller that suitably compromises robustness versus performance, given the current level of model uncertainty. The use of randomized algorithms makes the supervisor implementation computationally tractable.