Controlling vapor compression system using probabilistic surrogate model

A method for controlling an operation of a vapor compression system (VCS), comprising:

• controlling the operation of the VCS with different combinations of setpoints for different actuators of the VCS to estimate a cost of operation of the VCS for each of the different combinations of setpoints;
• computing, using a Bayesian optimization of the combinations of setpoints and their corresponding estimated costs of operation, a probabilistic surrogate model providing a probabilistic mapping between various combinations of setpoints for different actuators of the VCS and their corresponding costs of operation, wherein the probabilistic surrogate model defines at least first two order moments of the cost of operation in the probabilistic mapping;
• selecting an optimal combination of setpoints having the largest likelihood of being a global minimum at the surrogate model according to an acquisition function of the first two order moments of the cost of operation;
• submitting the selected optimal combination of the setpoints to a feedback controller to change states of the actuators of the VCS according to their corresponding setpoints in the selected optimal combination;
• executing an extremum seeking controller perturbing an input to the feedback controller starting from the selected optimal combination of the setpoints to tune the selected optimal combination of the setpoints based on a gradient of the cost of operation caused by the perturbation;
• and
• estimating the gradient of the cost of operation caused by the perturbation by mapping the perturbed values of the selected optimal combination of the setpoints to values of the cost of operation on the surrogate model according to the acquisition function.

A non-transitory computer readable storage medium embodied thereon a program executable by a processor for performing a method for controlling an operation of a vapor compression system (VCS), the method comprising:

• controlling the operation of the VCS with different combinations of setpoints for different actuators of the VCS to estimate a cost of operation of the VCS for each of the different combinations of setpoints;
• computing, using a Bayesian optimization of the combinations of setpoints and their corresponding estimated costs of operation, a probabilistic surrogate model providing a probabilistic mapping between various combinations of setpoints for different actuators of the VCS and their corresponding costs of operation, wherein the probabilistic surrogate model defines at least first two order moments of the cost of operation in the probabilistic mapping;
• selecting an optimal combination of setpoints having the largest likelihood of being a global minimum at the surrogate model according to an acquisition function of the first two order moments of the cost of operation;
• submitting the selected optimal combination of the setpoints to a feedback controller to change states of the actuators of the VCS according to their corresponding setpoints in the selected optimal combination;
• executing an extremum seeking controller perturbing an input to the feedback controller starting from the selected optimal combination of the setpoints to tune the selected optimal combination of the setpoints based on a gradient of the cost of operation caused by the perturbation;
• and
• estimating the gradient of the cost of operation caused by the perturbation by mapping the perturbed values of the selected optimal combination of the setpoints to values of the cost of operation on the surrogate model according to the acquisition function.