Systems and methods for generating an energy use model for a building

• US 9,152,610 B2
• Filed: 11/16/2012
• Issued: 10/06/2015
• Est. Priority Date: 11/16/2012
• Status: Active Grant

• Current Assignee: Tyco Fire & Security GmbH (Johnson Controls International plc)
• Original Assignee: Johnson Controls Technology Company (Johnson Controls International plc)
• Inventors: Drees, Kirk H., Wenzel, Michael J.
• Primary Examiner(s): Craig, Dwin M
• Application Number:
  US13/679,936
• Publication Number:
  US 20140142904A1
• Time in Patent Office: 1,054 Days
• Field of Search: 703/2
• US Class Current: 1/1
• CPC Class Codes: G06F 17/10 Complex mathematical operations function generation by table look-up G06F1/03; evaluation of elementary functions by calculation G06F7/544
• CPC Class Codes: G06Q 10/04 Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" market predictions or forecasting for commercial activities G06Q30/0202
• CPC Class Codes: G06Q 50/06 Energy or water supply

Abstract

A system for generating an energy use model of a building includes a processing circuit operable to receive building data indicative of a first type of building variable and to receive additional building data correlated to an energy use of the building. The processing circuit is also operable to determine a portion of the building variable that is uncorrelated with the additional building data. The processing circuit is further operable to use the additional building data and the uncorrelated portion of the building variable to generate the energy use model of the building.

Claims

1. A method for generating an energy use model of a building comprising:

receiving, at a processing circuit, building data indicative of a first type of building variable, the processing circuit comprising a processor, memory, and an interface;

receiving, at the processing circuit, additional building data correlated to an energy use of the building;

generating, by the processing circuit, a building variable model that estimates the building variable as a function of the additional building data, the building variable comprising a correlated portion that is correlated with the additional building data and an uncorrelated portion that is uncorrelated with the additional building data;

determining, by the processing circuit, the portion of the building variable that is uncorrelated with the additional building data by calculating a residual of the building variable model, the residual representing a non-random variable that is correlated with the building variable and uncorrelated with the additional building data; and

using the additional building data and the uncorrelated portion of the building variable to generate the energy use model of the building, wherein the energy use model estimates the energy use of the building as a function of the additional building data and at least one of the residual and the variable represented by the residual.

2. The method of claim 1, wherein the first type of building variable comprises water consumption by the building.

3. The method of claim 2, wherein the portion of the water consumption uncorrelated to the additional building data is used as a proxy for occupancy of the building, wherein the occupancy of the building is the variable.

4. The method of claim 1, wherein the energy use model comprises a regression model.

5. The method of claim 1, further comprising:

determining a classification of the building;

selecting, by the processing circuit, one or more other buildings having the classification; and

comparing a parameter of the energy use model of the building to energy use model parameters of the one or more other buildings, wherein the parameter relates to the uncorrelated portion of the building variable.

6. The method of claim 5, further comprising:

determining the building to be an outlier among the one or more other buildings based in part on the parameter.

7. The method of claim 5, wherein the classification is determined based on at least one of:

a location of the building or a usage type of the building.

8. The method of claim 3, wherein the uncorrelated amount of consumed water is determined by calculating a portion of the amount of consumed water that is orthogonal to the additional building data.

9. The method of claim 3, further comprising:

generating a water use model using the water use data and the additional building data; and

determining, by the processing circuit, a residual of the water use model, wherein the residual comprises the uncorrelated amount of consumed water.

10. A system for generating an energy use model of a building, the system comprising a processing circuit comprising a processor, memory, and an interface, wherein the processing circuit:

receives building data indicative of a first type of building variable;

receives additional building data correlated to an energy use of the building;

generates a building variable model that estimates the building variable as a function of the additional building data, the building variable comprising a correlated portion that is correlated with the additional building data and an uncorrelated portion that is uncorrelated with the additional building data;

determines the portion of the building variable that is uncorrelated with the additional building data by calculating a residual of the building variable model, the residual representing a variable that is correlated with the building variable and uncorrelated with the additional building data; and

uses the input data and the uncorrelated portion of the building variable to generate the energy use model of the building, wherein the energy use model estimates the energy use of the building as a function of the additional building data and at least one of the residual and the variable represented by the residual.

11. The system of claim 10, wherein the first type of building variable comprises water consumption by the building.

12. The system of claim 11, wherein the portion of the water consumption uncorrelated to the additional building data is used as a proxy for occupancy of the building, wherein the occupancy of the building is the variable.

13. The system of claim 10, wherein the energy use model comprises a regression model.

14. The system of claim 10, wherein the processing circuit is operable to determine a classification of the building, select one or more other buildings having the classification, and compare a parameter of the energy use model of the building to energy use model parameters of the one or more other buildings, wherein the parameter relates to the uncorrelated portion of the building variable.

15. The system of claim 14, wherein the processing circuit is operable to determine the building to be an outlier among the one or more other buildings based in part on the parameter.

16. The system of claim 14, wherein the classification is determined based on at least one of:

a location of the building or a usage type of the building.

17. The system of claim 12, wherein the uncorrelated amount of consumed water is determined by calculating a portion of the amount of consumed water that is orthogonal to the additional building data.

18. The system of claim 12, wherein the processing circuit is operable to generate a water use model using the water use data and the additional building data, wherein the processing circuit is operable to determine a residual of the water use model, wherein the residual comprises the uncorrelated amount of consumed water.

19. A non-transitory computer-readable storage medium having machine instructions stored therein, the instructions being executable by a processor to cause the processor to perform operations, the operations comprising:

receiving water use data indicative of an amount of water consumed by a building;

receiving additional building data correlated to an energy use of the building, the amount of consumed water comprising a correlated portion that is correlated with the additional building data and an uncorrelated portion that is uncorrelated with the additional building data;

determining the amount of consumed water that is uncorrelated with the additional building data, the uncorrelated amount of consumed water representing a variable; and

using the additional building data and the uncorrelated amount of consumed water to generate the energy use model of the building, wherein the energy use model estimates the energy use of the building as a function of the additional building data and at least one of the uncorrelated amount of consumed water and the variable represented by the uncorrelated amount of consumed water.

20. The computer-readable storage medium of claim 19, wherein the operations further comprise:

generating a water use model using the water use data and the additional building data; and

determining a residual of the water use model, wherein the residual comprises the uncorrelated amount of consumed water.