Systems and methods for detecting changes in energy usage in a building

Patent metadata

Field	Value
Publication number	US-10739741-B2
Application number	US-201916352536-A
Country	US
Kind code	B2
Filing date	Mar 13, 2019
Priority date	Jun 22, 2009
Publication date	Aug 11, 2020
Grant date	Aug 11, 2020

Abstract

A method for operating HVAC equipment includes obtaining building data for each of a plurality of time steps. The building data relates to resource usage of HVAC equipment. The method also includes calculating a recursive residual for each of a plurality of overlapping time periods using the building data. Each overlapping time period includes a subset of the plurality of time steps. The method also includes, for each of the plurality of time steps, calculating a metric based on the recursive residuals for overlapping time periods that end on or before the time step and automatically detecting a change in static factors for one or more buildings served by the HVAC equipment by comparing the metrics for the plurality of time steps based on a statistical property of the metrics.

First claim

What is claimed is:

1. A building management system comprising:
a plurality of sensors measuring a physical state or condition and generating sensor data indicating the physical state or condition measured by the plurality of sensors; and
a controller configured to:
use first sensor data from the plurality of sensors collected during a first time period to generate one or more first model coefficients for an energy usage model for HVAC equipment, the energy usage model configured to provide an energy usage of the HVAC equipment as a function of one or more model coefficients and one or more variables, wherein the energy usage of the HVAC equipment is an output of the energy usage model, the one or more model coefficients are parameters of the energy usage model, and the one or more variables are inputs to the energy usage model;
use second sensor data from the plurality of sensors collected during a second time period to generate one or more second model coefficients for the energy usage model;
generate a test statistic by comparing the first model coefficients and the second model coefficients;
compare the test statistic with a value; and
automatically identify a change in the energy usage of the HVAC equipment in response to the test statistic exceeding the value.

2. The building management system of claim 1 , wherein:
the first and second model coefficients are regression coefficients; and
the controller is configured to generate the first and second model coefficients by performing regression processes using the first and second sensor data.

3. The building management system of claim 1 , wherein the test statistic represents at least one of:
a difference between the first and second model coefficients;
an F-statistic that is related to the difference between the first and second model coefficients; and
a Z-statistic that is formed by standardizing the F-statistic.

4. The building management system of claim 1 , wherein the controller is configured to:
generate a different set of model coefficients for each of a plurality of windows of time;
calculate a test statistic for each different set of model coefficients;
determine an autocorrelation of a plurality of the test statistics for the plurality of windows of time; and
use the autocorrelation to determine whether the energy usage model with each different set of model coefficients has changed in a way that affects the energy usage of the HVAC equipment.

5. The building management system of claim 1 , wherein the controller is configured to identify a change in static factors in a building based on a difference between the first model coefficients and the second model coefficients.

6. The building management system of claim 1 , wherein the controller is configured to initiate an automated diagnostics process in response to identifying the change in the energy usage of the HVAC equipment.

7. The building management system of claim 1 , wherein the test statistic is generated without requiring the output of the energy usage model to be calculated.

8. The building management system of claim 1 , wherein comparing the first model coefficients and the second model coefficients comprises directly comparing a model coefficient of the first model coefficients with a corresponding model coefficient of the second model coefficients.

9. A controller for HVAC equipment, comprising:
one or more processors; and
non-transitory computer-readable media communicably coupled to the one or more processors and storing instructions that, when executed by the one or more processors, cause the one or more processors to:
generate a first energy usage model for HVAC equipment using first data from a building management system collected during a first time period, the first energy usage model predicting a first value of an energy usage of the HVAC equipment as an output of the first energy usage model as a function of coefficients of the first energy usage model;
generate a second energy usage model for the HVAC equipment using second data from the building management system collected during a second time period, the second energy usage model predicting a second value of the energy usage of the HVAC equipment as an output of the second energy usage model as a function of coefficients of the second energy usage model; and
determine that a change affecting the energy usage of the HVAC equipment has occurred by comparing the coefficients of the first energy usage model with the coefficients of the second energy usage model.

10. The controller of claim 9 , wherein:
the coefficients of the first and second energy usage models are regression coefficients; and
the instructions cause the one or more processors to generate the coefficients of the first and second energy usage models by performing regression processes using the first and second data from the building management system.

11. The controller of claim 9 , wherein the instructions cause the one or more processors to:
gather third data from a building management system in response to a determination that a change affecting the energy usage of the HVAC equipment has occurred;
use the third data gathered after the change has occurred to generate a third energy usage model for the HVAC equipment; and
use the third energy usage model to generate and transmit control signals for the HVAC equipment.

12. The controller of claim 9 , wherein the first time period is prior to implementing an energy conservation measure and the second time period is after implementing the energy conservation measure.

13. The controller of claim 9 , wherein comparing coefficients of the first and second energy usage models comprises generating a test statistic representing at least one of:
a difference between the coefficients of the first energy usage model and the coefficients of the second energy usage model;
an F-statistic that is related to the difference between the coefficients of the first energy usage model and the coefficients of the second energy usage model; and
a Z-statistic that is formed by standardizing the F-statistic.

14. The controller of claim 9 , wherein the instructions cause the one or more processors to determine an autocorrelation of a plurality of test statistics for varying windows of time and use the autocorrelation to determine whether the change affecting the energy usage of the HVAC equipment has occurred.

15. The controller of claim 9 , wherein the instructions cause the one or more processors to detect a change in static factors for the HVAC equipment based on a change in the coefficients.

16. The controller of claim 9 , wherein the instructions cause the one or more processors to initiate an automated diagnostics process in response to determining that the change affecting the energy usage of the HVAC equipment has occurred.

17. The controller of claim 9 , wherein the change affecting the energy usage of the HVAC equipment is determined to have occurred without requiring the output of the first energy usage model or the output of the second energy usage model to be calculated.

18. The controller of claim 9 , wherein comparing the coefficients of the first energy usage model with the coefficients of the second energy usage model comprises directly comparing a model coefficient of the first energy usage model with a corresponding model coefficient of the second energy usage model.

19. A method for operating HVAC equipment, comprising:
obtaining building data for each of a plurality of time steps, the building data relating

Assignees

• Johnson Controls Tech Co

Inventors

• Wenzel Michael J
• Eibsat Mohammad N
• Drees Kirk H

Classifications

• H02J2103/30

  Simulating, planning, modelling, reliability check or computer assisted design [CAD] of electric power networks · CPC title

• H02J13/10

  characterised by displaying of information or by user interaction, e.g. supervisory control and data acquisition [SCADA] systems · CPC title

• H02J13/1321

  using a wired telecommunication network or a data transmission bus · CPC title

• H02J2105/12

  supplying households or buildings · CPC title

• G06Q10/0637 Primary

  Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals · CPC title