Method to identify heating and cooling system power-demand

• US 9,633,401 B2
• Filed: 03/15/2013
• Issued: 04/25/2017
• Est. Priority Date: 10/15/2012
• Status: Active Grant

• Current Assignee: Opower, Inc. (Oracle Corporation)
• Original Assignee: Opower, Inc. (Oracle Corporation)
• Inventors: Curtis, Richard Tyler
• Primary Examiner(s): Lo, Kenneth M
• Assistant Examiner(s): Pan, Yuhui R
• Application Number:
  US13/839,082
• Publication Number:
  US 20140107850A1
• Time in Patent Office: 1,502 Days
• Field of Search: 700291
• 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 11/64 using pre-stored data
• CPC Class Codes: F24F 2110/00 Control inputs relating to air properties
• CPC Class Codes: F24F 2140/60 Energy consumption
• CPC Class Codes: G06Q 50/06 Energy or water supply
• CPC Class Codes: H02J 13/00001 characterised by the display of information or by user interaction, e.g. supervisory control and data acquisition systems [SCADA] or graphical user interfaces [GUI]
• CPC Class Codes: H02J 2203/20 Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
• CPC Class Codes: H02J 3/00 Circuit arrangements for ac mains or ac distribution networks
• CPC Class Codes: Y04S 10/40 Display of information, e.g. of data or controls

Abstract

Methods and computer systems are disclosed for identifying the power-demand of a climate-control system at a premises to reduce usage of energy at the premises. A computer system receives energy usage data and run-time data of the climate-control system. The operational data includes an on-time and/or off-time associated with the climate-control system. The computer system determines a power-draw of the climate-control system using the energy usage data and the run-time data and outputs the power-draw to be used to reduce the energy usage at the premises.

Claims

1. A computer-implemented method of determining power-demand of a climate-control system at a premises to reduce energy usage at the premises, the computer-implemented method comprising:

receiving energy usage data of the premises including energy usage of the climate-control system, the energy usage data corresponding to a usage time period;

receiving run-time data of the climate-control system corresponding to the usage time period, and determining from the run-time data one or more on-times that indicate when the climate-control system was running and one or more off-times that indicate when the climate-control system was not running;

determining a power-draw of the climate-control system using the energy usage data and the run-time data by correlating at least two energy usage datum of the energy usage data at a first and second time to at least two run-time datum at the first and second time, wherein the correlating produces a trend that represents the power-draw;

wherein determining the power-draw of the climate control system includes;

performing an analysis with at least two groups of memberships, including a first group corresponding to the climate-control system and a second group corresponding to a different energy usage unit, to provide a first trend corresponding to the climate-control system, wherein the first analysis includes a first finite mixture model analysis of the energy usage data and the run-time data;

performing additional analysis, including a second analysis, wherein each analysis includes at least one additional group of memberships corresponding to a likelihood of an additional different energy usage unit, wherein each analysis providing an additional trend corresponding to the climate-control system, and wherein each additional analysis includes a finite mixture model analysis of the energy usage data and the run-time data; and

determining the power-draw of the climate-control system as a trend selected among the groups of the analysis, wherein the selection is based on a coefficient of determination (R²) value derived from the trends.

2. The computer-implemented method of claim 1, wherein the trend is determined based on at least one of a least-square estimation, a generalized least-square estimation, an iteratively reweighted least-square estimation, a total least-square estimation, a maximum-likelihood estimation, a ridge-regression estimation, a least absolute deviation estimation, an adaptive estimation, a principal-component regression estimation, and a least-angle regression estimation.

3. The computer-implemented method of claim 1, wherein the power-draw is determined by

4. The computer-implemented method of claim 1, further comprising, after the verifying

correlating additional usage datum of the energy usage data to additional corresponding run-time datum until improvements of the trend is below a pre-specified value.

5. The computer-implemented method of claim 1, wherein the premises includes a second climate-control system operating independently of the climate-control system, the operation of determining the power-draw of the climate-control system includes:

determining a second trend associated with a group of datum within the energy usage data correlated to the run-time data wherein the second trend is associated to the power-draw of the climate-control system; and

determining a presence of a second group of datum within the energy usage data not correlated to the run-time data.

6. The computer-implemented method of claim 1, wherein the premises includes a second climate-control system operating independently of the climate-control system, the operation of determining the power-draw of the climate-control system includes:

determining a second trend associated with a group of datum within the energy usage data correlated to the run-time data, each datum of the energy usage data having a probability of membership associated with being in the group, the trend being determined in a manner that fits the probability of membership,

wherein the trend is associated to the power-draw of the climate-control system.

7. The computer-implemented method of claim 1, wherein determining the power-draw of the climate-control system is based on a finite mixture model analysis of the energy usage data and the run-time data.

8. The computer-implemented method of claim 1, wherein the additional trend of each additional analysis is weighted, wherein the weight is associated to a number of additional group of memberships.

9. The computer-implemented method of claim 5, wherein the climate-control system includes a heating-ventilation and air-conditioning system of the premises, and the second climate-control system includes at least one of an auxiliary air-conditioning system and a space heating unit located within the premises.

10. The computer-implemented method of claim 5, wherein the climate-control system is regulated by a thermostat providing the runtime data.

11. The computer-implemented method of claim 1 further comprising:

receiving the determined power-draw for the premises as a current power-draw data;

comparing the received power-draw data to historical power-draw data, the historical power-draw data preceding the current power-draw data in time; and

causing an output of a report when a difference between the current power-draw and the historical power-draw exceeds a pre-specified value.

12. The computer-implemented method of claim 1 further comprising:

receiving the determined power-draw for the premises as a first power-draw data;

comparing the received power-draw data to a second power-draw data corresponding a second premises sufficiently similar to the premises; and

causing an output of an report when the first power-draw exceeds the second power-draw by a pre-specified value.

13. The computer-implemented method of claim 1, wherein the energy usage data includes at least one of hourly usage data, sub-hourly usage data, daily usage data, weekly usage data, and seasonable usage data.

14. A non-transitory machine-readable medium comprising program code stored thereon and executable by at least a processor of a computer to cause the computer to determine a power-demand of a climate-control system at a premises to reduce usage of energy at the premises, the non-transitory machine-readable medium comprising:

computer code that when executed by at least the processor cause the processor to receive energy usage data of the premises for a time period, the energy usage data including energy usage by the climate-control system;

computer code that when executed by at least the processor cause the processor to receive runtime data of the climate-control system for a portion of the time period, and to determine from the runtime data one or more on-times that indicate when the climate-control system was running and one or more off-times that indicate when the climate-control system was not running;

computer code that when executed by at least the processor cause the processor to determine a power-draw of the climate-control system using the energy usage data and the runtime data by correlating at least two energy usage datum of the energy usage data at a first and second time to at least two run-time datum at the first and second time, wherein the correlating produces a trend that represents the power-draw;

wherein determining the power-draw of the climate control system includes;

performing an analysis with at least two groups of memberships, including a first group corresponding to the climate-control system and a second group corresponding to a different energy usage unit, to provide a first trend corresponding to the climate-control system, wherein the first analysis includes a first finite mixture model analysis of the energy usage data and the run-time data;

performing additional analysis, including a second analysis, wherein each analysis includes at least one additional group of memberships corresponding to a likelihood of an additional different energy usage unit, wherein each analysis provides an additional trend corresponding to the climate-control system, and wherein each additional analysis includes a finite mixture model analysis of the energy usage data and the run-time data; and

determining the power-draw of the climate-control system as a trend selected among the groups of the analysis, wherein the selection is based on a coefficient of determination (R²) value derived from the trends.

15. A system comprising:

a memory configured to store i) energy usage data of a premises for a time period and ii) runtime data of a climate-control system of the premises for a portion of the time period;

a non-transitory machine readable medium comprising a control program stored thereon including instructions that when executed by at least a processor cause the processor;

control the memory to

(i) receive the energy usage data for a portion of the time period; and

(ii) receive the runtime data, a portion of the runtime data having times corresponding to the time of the energy usage data;

determine from the run-time data one or more on-times that indicate when the climate-control system was running and one or more off-times that indicate when the climate-control system was not running;

determine a power-draw of the climate-control system using the energy usage data and the run-time data including the on-times and the off-times by correlating at least two energy usage datum of the energy usage data at a first time and a second time to at least two run-time datum at the first time and the second time, wherein the correlating produces a trend that represents the power-draw, the power-draw being associated to a pre-specified relationship between a portion of the energy usage data and a portion of the runtime data;

wherein determining the power-draw of the climate control system includes;

performing an analysis with at least two groups of memberships, including a first group corresponding to the climate-control system and a second group corresponding to a different energy usage unit, to provide a first trend corresponding to the climate-control system, wherein the first analysis includes a first finite mixture model analysis of the energy usage data and the run-time data;

performing additional analysis, including a second analysis, wherein each analysis includes at least one additional group of memberships corresponding to a likelihood of an additional different energy usage unit, wherein each analysis provides an additional trend corresponding to the climate-control system, and wherein each additional analysis includes a finite mixture model analysis of the energy usage data and the run-time data; and

determining the power-draw of the climate-control system as a trend selected among the groups of the analysis, wherein the selection is based on a coefficient of determination (R²) value derived from the trends.