Building control system with zone grouping based on predictive models

1. A controller for operating building equipment of a building, the controller comprising:

one or more processors; and

one or more non-transitory computer-readable media storing instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:

comparing one or more model parameters of a plurality of predictive models describing zones of the building to determine one or more zone groups for the building;

generating one or more zone group models corresponding to the one or more zone groups; and

operating the building equipment using the one or more zone group models to affect a variable state or condition of the building.

2. The controller of claim 1 , the operations further comprising identifying the plurality of predictive models by performing system identification processes based on building information describing the building.

3. The controller of claim 1 , wherein generating the one or more zone group models comprises aggregating model parameters of predictive models associated with the zones of the building to generate an aggregate value of each model parameter.

4. The controller of claim 1 , wherein generating the one or more zone group models comprises performing one or more system identification processes to identify the one or more zone group models.

5. The controller of claim 1 , the operations further comprising:

determining whether to group the one or more zone groups by comparing one or more model parameters of the one or more zone group models; and

in response to a determination to group the one or more zone groups, aggregating the one or more model parameters of the one or more zone group models to generate one or more new zone group models for the building.

6. The controller of claim 1 , wherein the one or more model parameters comprise at least one of:

thermal model parameters;

a cooling or heating mode;

an internal heat disturbance; or

a parameter derived from the one or more model parameters.

7. The controller of claim 1 , wherein comparing the one or more model parameters comprises at least one of:

calculating a standard deviation of values of the one or more model parameters; or

performing a clustering analysis on the values of the one or more model parameters.

8. A method for operating building equipment of a building, the method comprising:

comparing one or more model parameters of a plurality of predictive models describing zones of the building to determine one or more zone groups for the building;

generating one or more zone group models corresponding to the one or more zone groups; and

operating the building equipment using the one or more zone group models to affect a variable state or condition of the building.

9. The method of claim 8 , further comprising identifying the plurality of predictive models by performing system identification processes based on building information describing the building.

10. The method of claim 8 , wherein generating the one or more zone group models comprises aggregating model parameters of predictive models associated with the zones of the building to generate an aggregate value of each model parameter.

11. The method of claim 8 , wherein generating the one or more zone group models comprises performing one or more system identification processes to identify the one or more zone group models.

12. The method of claim 8 , further comprising:

determining whether to group the one or more zone groups by comparing one or more model parameters of the one or more zone group models; and

in response to a determination to group the one or more zone groups, aggregating the one or more model parameters of the one or more zone group models to generate one or more new zone group models for the building.

13. The method of claim 8 , wherein the one or more model parameters comprise at least one of:

thermal model parameters;

a cooling or heating mode;

an internal heat disturbance; or

a parameter derived from the one or more model parameters.

14. The method of claim 8 , wherein comparing the one or more model parameters comprises at least one of:

calculating a standard deviation of values of the one or more model parameters; or

performing a clustering analysis on the values of the one or more model parameters.

15. A controller for building equipment, the controller comprising a processing circuit configured to perform operations comprising:

identifying a zone group comprising a plurality of zones of a building;

extracting model parameters from a plurality of zone-specific predictive models associated with individual zones of the zone group;

generating a zone group model for the zone group by aggregating the model parameters of the plurality of zone-specific predictive models; and

operating the building equipment using the zone group model to affect a variable state or condition of the building.

16. The controller of claim 15 , further comprising generating the plurality of zone-specific predictive models by performing system identification processes based on building information describing the building.

17. The controller of claim 15 , wherein identifying the zone group comprises:

receiving grouping selections made by a user from a user device; and

forming the zone group as indicated by the grouping selections.

18. The controller of claim 15 , wherein identifying the zone group comprises:

obtaining real-time data describing the plurality of zones; and

forming the zone group based on the real-time data.

19. The controller of claim 15 , wherein the real-time data comprises at least one of:

model predictive control setpoints;

a cooling or heating mode;

bounds for the plurality of zones; or

occupancy information.

20. The controller of claim 15 , wherein identifying the zone group comprises comparing model parameters of the plurality of zone-specific predictive models to determine which of the plurality of zones exhibit similar behaviors.