Predictive building control system and method for optimizing energy use and thermal comfort for a building or network of buildings

• US 10,094,586 B2
• Filed: 04/20/2015
• Issued: 10/09/2018
• Est. Priority Date: 04/20/2015
• Status: Active Grant

• Current Assignee: Green Power Labs Inc.
• Original Assignee: Green Power Labs Inc.
• Inventors: Pavlovski, Alexandre, Qin, Zheng, Anichkov, Dmitriy, Fletcher, James
• Primary Examiner(s): Brown, Michael J
• Application Number:
  US14/690,671
• Publication Number:
  US 20160305678A1
• Time in Patent Office: 1,268 Days
• Field of Search: 700276, 700277
• CPC Class Codes: F24F 11/30 for purposes related to the operation of the system, e.g. for safety or monitoring
• CPC Class Codes: F24F 11/46 Improving electric energy efficiency or saving
• CPC Class Codes: F24F 11/47 Responding to energy costs
• CPC Class Codes: F24F 11/54 using one central controller connected to several sub-controllers
• CPC Class Codes: F24F 11/58 using Internet communication
• CPC Class Codes: F24F 11/62 characterised by the type of control or by internal processing, e.g. using fuzzy logic, adaptive control or estimation of values
• CPC Class Codes: F24F 11/64 using pre-stored data
• CPC Class Codes: F24F 11/65 for selecting an operating mode
• CPC Class Codes: F24F 2110/10 Temperature
• CPC Class Codes: F24F 2110/12 of the outside air
• CPC Class Codes: F24F 2120/10 Occupancy
• CPC Class Codes: F24F 2120/12 Position of occupants
• CPC Class Codes: F24F 2130/00 Control inputs relating to environmental factors not covered by group F24F2110/00
• CPC Class Codes: F24F 2130/10 Weather information or forecasts
• CPC Class Codes: F24F 2130/20 Sunlight
• CPC Class Codes: F24F 2140/50 Load
• CPC Class Codes: F24F 2140/60 Energy consumption
• CPC Class Codes: G05B 13/048 using a predictor
• CPC Class Codes: G05B 15/02 electric
• CPC Class Codes: G05B 2219/2642 Domotique, domestic, home control, automation, smart house
• CPC Class Codes: G05D 23/1917 : using digital means
• CPC Class Codes: G05D 23/1934 : each space being provided with one sensor acting on one or more control means

Abstract

A method for controlling temperature in a thermal zone within a building, comprising: using a processor, receiving a desired temperature range for the thermal zone; determining a forecast ambient temperature value for an external surface of the building proximate the thermal zone; using a predictive model for the building, determining set points for a heating, ventilating, and air conditioning (“HVAC”) system associated with the thermal zone that minimize energy use by the building; the desired temperature range and the forecast ambient temperature value being inputs to the predictive model; the predictive model being trained using respective historical measured value data for at least one of the inputs; and, controlling the HVAC system with the set points to maintain an actual temperature value of the thermal zone within the desired temperature range for the thermal zone.

Claims

1. A method for controlling temperature in a thermal zone within a building, comprising:

using a processor, receiving a desired temperature range for the thermal zone;

determining a forecast ambient temperature value for an external surface of the building proximate the thermal zone;

using a predictive model for the building, determining set points for a heating, ventilating, and air conditioning (“

HVAC”

) system associated with the thermal zone that minimize energy use by the building;

the desired temperature range and the forecast ambient temperature value being inputs to the predictive model;

the predictive model being trained using respective historical measured value data for at least one of the inputs and by one or more artificial intelligence-based modules;

controlling the HVAC system with the set points to maintain an actual temperature value of the thermal zone within the desired temperature range for the thermal zone;

receiving a demand response signal from a utility demand response control system associated with the building and further determining the set points using the demand response signal as one of the inputs to the predictive model; and

, determining a demand response capacity of the building available for bidding at least a portion thereof into at least one of a frequency response market, an electric power market, and an ancillary services market associated with the utility grid.

2. The method of claim 1, wherein the forecast ambient temperature value is determined using a weather forecasting model that includes a mesoscale numerical weather prediction model that adjusts for ambient solar irradiance and ambient wind speed at the external surface, the weather forecasting model being based on numerical weather predictions of ambient temperature value data for the external surface.

3. The method of claim 1, further comprising determining a forecast occupancy level and internal load value for the thermal zone and further determining the set points using the forecast occupancy level and internal load value as ones of the inputs to the predictive model.

4. The method of claim 3, wherein the forecast occupancy level and internal load value is determined using an occupancy level and internal load predictive model that is trained using historical measured occupancy level and internal load value data for the thermal zone.

5. The method of claim 1, further comprising determining a forecast fuel cost value for the building and further determining the set points using the forecast fuel cost value as one of the inputs to the predictive model.

6. The method of claim 5, wherein the forecast fuel cost value for the building is determined using a fuel cost model that is trained using historical measured fuel cost value data for the building.

7. The method of claim 1, further comprising receiving a forecast power output capacity value for distributed power generation and storage systems associated with the building and further determining the set points using the forecast power output capacity value as one of the inputs to the predictive model, the forecast power output capacity value being a forecast of power output capacity from the distributed power generation and storage systems associated with the building that is available for at least one of powering internal building loads and feed in to a utility grid.

8. The method of claim 1, wherein the demand response signal indicates a desired reduction in electric power demand received by the building from a utility grid.

9. The method of claim 8, wherein the demand response capacity of the building is a difference between a high electric power demand limit and a low electric power demand limit, and wherein the high electric power demand limit and the low electric power demand limit are associated with a lower limit of the desired temperature range and a higher limit of the desired temperature range.

10. The method of claim 9, wherein the high electric power demand limit and the low electric power demand limit are determined using a forecast power output capacity for distributed power generation and storage systems associated with the building.

11. The method of claim 1, wherein the set points are determined by a predictive building control system that is communicatively coupled to the HVAC system via a building energy management system for the building.

12. The method of claim 11, wherein the desired temperature range for the thermal zone is received from one of the HVAC system and the building energy management system.

13. The method of claim 11, wherein the actual temperature value for the thermal zone is received from the building energy management system.

14. The method of claim 11, wherein the actual temperature value for the thermal zone is measured using a sensor located in the thermal zone and coupled to the HVAC system.

15. The method of claim 11, further comprising transmitting the set points to the HVAC system from the predictive building control system via the building energy management system.

16. The method of claim 1, further comprising determining the set points to minimize energy costs for the building.

17. The method of claim 16, further comprising determining the set points to minimize a carbon footprint of the building.

18. The method of claim 1, wherein the set points are a schedule of set points.

19. The method of claim 1, wherein the thermal zone includes one or more of:

a room of the building, a floor of the building, and a wing of the building.

20. The method of claim 1, wherein the building is a network of buildings.

21. The method of claim 1, wherein the external surface of the building is one or more of an external face of the building, an external wall surface of the building, an external window surface of the building, an external roof surface of the building, an envelope of the building, and a portion of an envelope of the building.

22. The method of claim 1, wherein the forecast ambient temperature value is one or more of a forecast ambient weather condition value for the external surface of the building proximate the thermal zone, a forecast ambient wind speed value for the external surface of the building proximate the thermal zone, and a forecast ambient solar irradiance value for the external surface of the building proximate the thermal zone.

23. The method of claim 1, wherein the desired temperature range for the thermal zone is a desired thermal comfort condition range for the thermal zone and the actual temperature value of the thermal zone is an actual thermal comfort condition value of the thermal zone.

24. The method of claim 1, wherein the desired temperature range for the thermal zone is a desired relative humidity range for the thermal zone and the actual temperature value of the thermal zone is an actual relative humidity value of the thermal zone.

25. The method of claim 1, wherein the desired temperature range for the thermal zone is a desired air quality range for the thermal zone and the actual temperature value of the thermal zone is an actual air quality value of the thermal zone.

26. The method of claim 1, wherein the predictive model is a linear model.

27. The method of claim 1, wherein the predictive model is a non-linear model.

28. The method of claim 1, wherein the predictive model is trained off-line.

29. A predictive building control system for controlling temperature in a thermal zone of a building, comprising:

a processor coupled to memory; and

,

at least one of hardware and software modules within the memory and controlled or executed by the processor, the modules including computer readable instructions executable by the processor for causing the predictive building control system to implement the method of claim 1.

30. A method for controlling temperature in a thermal zone within a building, comprising:

using a processor, receiving a desired temperature range for the thermal zone;

determining a forecast ambient temperature value for an external surface of the building proximate the thermal zone;

using a predictive model for the building, determining set points for a heating, ventilating, and air conditioning (“

HVAC”

) system associated with the thermal zone that minimize energy use by the building;

the desired temperature range and the forecast ambient temperature value being inputs to the predictive model;

the predictive model being trained using respective historical measured value data for at least one of the inputs and by one or more artificial intelligence-based modules;

controlling the HVAC system with the set points to maintain an actual temperature value of the thermal zone within the desired temperature range for the thermal zone;

receiving a demand response signal from a utility demand response control system associated with the building and further determining the set points using the demand response signal as one of the inputs to the predictive model, the demand response signal indicating a desired reduction in electric power demand received by the building from a utility grid; and

determining a demand response capacity of the building as a difference between a high electric power demand limit and a low electric power demand limit, wherein the high electric power demand limit and the low electric power demand limit are associated with a lower limit of the desired temperature range and a higher limit of the desired temperature range, and wherein the demand response capacity or a portion thereof is available for bidding into at least one of a frequency response market, an electric power market, and an ancillary services market associated with the utility grid.