Smart thermostat with model predictive control
A thermostat for a building zone includes at least one of a model predictive controller and an equipment controller. The model predictive controller is configured to obtain a cost function that accounts for a cost of operating HVAC equipment during each of a plurality of time steps, use a predictive model to predict a temperature of the building zone during each of the plurality of time steps, and generate temperature setpoints for the building zone for each of the plurality of time steps by optimizing the cost function subject to a constraint on the predicted temperature. The equipment controller is configured to receive the temperature setpoints generated by the model predictive controller and drive the temperature of the building zone toward the temperature setpoints during each of the plurality of time steps by operating the HVAC equipment to provide heating or cooling to the building zone.
1. A system for monitoring and controlling temperature of a building zone, the system comprising:
a thermostat; and
a model predictive controller separate from the thermostat and configured to:
predict a temperature of the building zone for a plurality of time steps as a function of temperature setpoints for the thermostat;
generate the temperature setpoints for the thermostat by performing an optimization subject to a constraint on the temperature of the building zone; and
provide at least a first temperature setpoint of the temperature setpoints to the thermostat via a communications network;
wherein the thermostat is configured to drive the temperature of the building zone toward the first temperature setpoint during a corresponding time step of the plurality of time steps by operating HVAC equipment to provide heating or cooling to the building zone.
2. The system of claim 1 , wherein performing the optimization comprises optimizing a predicted resource usage of the HVAC equipment.
3. The system of claim 1 , wherein performing the optimization comprises optimizing a cost of operating the HVAC equipment.
4. The system of claim 1 , wherein the thermostat is configured to:
receive user-provided temperature setpoints via a local user interface of the thermostat or a mobile device in communication with the thermostat; and
in response to receiving the user-provided temperature setpoints, override the temperature setpoints generated by the model predictive controller with the user-provided temperature setpoints and use the user-provided temperature setpoints to operate the HVAC equipment.
5. The system of claim 1 , wherein the model predictive controller is located in a separate building from the thermostat and configured to communicate with the thermostat via the communications network.
6. The system of claim 1 , wherein the model predictive controller is configured to:
predict the temperature of the building zone using a predictive model; and
generate the predictive model by:
modulating the temperature setpoints during a plurality of time steps of a learning period;
collecting a set of input-output data comprising values of the temperature setpoints and values of the temperature of the building zone that result from modulating the temperature setpoints; and
training the predictive model using the set of input-output data.
7. The system of claim 1 , wherein the model predictive controller is configured to predict the temperature of the building zone using a thermal mass storage model that defines the temperature of the building zone as a function of heat transfer between air within the building zone and solid mass within the building zone.
8. The system of claim 1 , wherein the model predictive controller is configured to predict the temperature of the building zone as a function of at least one of a weather forecast or a heat load disturbance experienced by the building zone.
9. A thermostat for monitoring and controlling temperature of a building zone, the thermostat comprising:
an equipment controller configured to drive the temperature of the building zone toward a temperature setpoint by operating HVAC equipment to provide heating or cooling to the building zone; and
a model predictive controller configured to determine the temperature setpoint by:
using a predictive model to predict a temperature of air within the building zone and a temperature of solid mass within the building zone for a plurality of time steps during a time period; and
determining temperature setpoints for the plurality of time steps subject to a constraint on the temperature of the air within the building zone.
10. The thermostat of claim 9 , wherein determining the temperature setpoints for the plurality of time steps comprises performing an optimization of resource consumption of the HVAC equipment subject to the constraint.
11. The thermostat of claim 9 , wherein determining the temperature setpoints for the plurality of time steps comprises performing an optimization of operational cost of the HVAC equipment subject to the constraint.
12. The thermostat of claim 9 , wherein the equipment controller is configured to:
receive user-provided temperature setpoints via a local user interface of the thermostat or a mobile device in communication with the thermostat; and
in response to receiving the user-provided temperature setpoints, override the temperature setpoints generated by the model predictive controller with the user-provided temperature setpoints and use the user-provided temperature setpoints to operate the HVAC equipment.
13. The thermostat of claim 9 , wherein the model predictive controller is configured to use the predictive model to predict the temperature of the air within the building zone and the temperature of the solid mass within the building zone as a function of temperature setpoints for the building zone.
14. The thermostat of claim 9 , wherein the model predictive controller is configured to generate the predictive model by
modulating the temperature setpoints during a plurality of time steps of a learning period;
collecting a set of input-output data comprising values of the temperature setpoints and values of the temperature of the building zone that result from modulating the temperature setpoints; and
training the predictive model using the set of input-output data.
15. The thermostat of claim 9 , wherein the predictive model is a grey-box model.
16. The thermostat of claim 9 , wherein the model predictive controller is configure to receive a weather forecast and use the weather forecast as an input to the predictive model.