Identification of peak days

• US 10,559,044 B2
• Filed: 11/20/2015
• Issued: 02/11/2020
• Est. Priority Date: 11/20/2015
• Status: Active Grant

• Current Assignee: Opower, Inc. (Oracle Corporation)
• Original Assignee: Opower, Inc. (Oracle Corporation)
• Inventors: Liptsey-Rahe, Alexandra
• Primary Examiner(s): Gart, Matthew S
• Assistant Examiner(s): Swartz, Stephen S
• Application Number:
  US14/947,664
• Publication Number:
  US 20170148114A1
• Time in Patent Office: 1,544 Days
• CPC Class Codes: G06Q 10/06315 Needs-based resource requirements planning or analysis
• CPC Class Codes: G06Q 10/067 Enterprise or organisation modelling
• CPC Class Codes: G06Q 30/0204 Market segmentation
• CPC Class Codes: G06Q 50/06 Energy or water supply

Abstract

The subject disclosure relates to systems and methods for calculating a peak consumption threshold, and for using the peak consumption threshold to determine the likelihood of future peak resource consumption events. In some aspects, methods of the subject technology include steps for receiving resource consumption data for a plurality of utility customers, wherein the resource consumption data comprises an indication of an amount of electric power used by each of the plurality of utility customers, and calculating, using the one or more processors, a plurality of consumption averages for the resource consumption data. In some aspects, the method can further include steps for calculating a peak consumption threshold based on the consumption values for the resource consumption data.

Claims

1. A computer-implemented method, executable by a processor, the method comprising:

receiving, by the processor, resource consumption data from one or more smart devices for a plurality of utility customers, wherein the resource consumption data comprises an indication of an amount of at least one consumable resource used by each of the plurality of utility customers;

segmenting, by the processor, the resource consumption data into one or more consumption categories based at least in part on similarity of resource consumption, wherein each of the one or more consumption categories are defined to include at least consumption data for similar days;

calculating, by the processor, a plurality of consumption values for each of the consumption categories;

identifying, by the processor, a peak consumption threshold for a selected consumption category, wherein the peak consumption threshold is based at least in part on a multiple of an average of the plurality of consumption values for the selected consumption category;

receiving, by the processor, weather forecast information for a future time period;

associating, by the processor, the weather forecast information with the selected consumption category;

determining, by the processor, a likelihood of a peak event for the selected consumption category, wherein the peak event includes exceeding the peak consumption threshold during the future time period based on the weather forecast information; and

if the likelihood of the peak event exceeds a boundary threshold indicating that the likelihood is high, triggering, by the processor, resource conservation for a portion of the utility customers associated with the selected consumption category, wherein the resource conservation includes sending instructions to reduce consumption of the consumable resource during the future time period, wherein the triggering resource conservation causes at least one of the one or more smart devices to adjust consumption of the at least one consumable resource during the future time period.

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

building, by the processor, a model for each of the consumption categories, wherein the model for a respective consumption category is based on weather data associated with the respective consumption category.

3. The computer-implemented method of claim 2, wherein building the model comprises applying a linear regression model based on the resource consumption data and the peak consumption threshold for the respective consumption category.

4. The computer-implemented method of claim 1, wherein segmenting the resource consumption data further comprises:

identifying two or more similar time periods; and

associating the resource consumption data for each of the two or more similar time periods into a common consumption category from among the consumption categories.

5. The computer-implemented method of claim 1, wherein a subset of resource consumption data associated with a particular consumption category of the consumption categories comprises energy consumption data collected for a plurality of similar days corresponding with the particular consumption category.

6. The computer-implemented method of claim 1, wherein the peak consumption threshold is defined based on a predetermined percentile of the consumption values for the selected consumption category.

7. The computer-implemented method of claim 1, wherein triggering resource conservation of the at least one consumable resource for the portion of the plurality of utility customers comprises:

issuing a notification to each utility customer of the portion of the plurality of utility customers.

8. The computer-implemented method of claim 7, wherein the notification is individualized for each utility customer of the portion of the plurality of utility customers.

9. A device, comprising:

a processor connected to at least a memory and configured to execute instructions from the memory; and

the memory configured to store instructions that when executed by the processor cause the processor to;

receive resource consumption data from one or more smart devices for a plurality of utility customers, wherein the resource consumption data comprises an indication of an amount of at least one consumable resource used by each of the plurality of utility customers;

segment the resource consumption data into one or more consumption categories based at least in part on similarity of resource consumption, wherein each of the one or more consumption categories are defined to include at least consumption data for similar days;

calculate a plurality of consumption values for each of the one or more consumption categories;

identify a peak consumption threshold for a selected consumption category, wherein the peak consumption threshold is based at least in part on a multiple of an average of the plurality of consumption values for the selected consumption category;

receive weather forecast information for a future time period;

associate the weather forecast information with the selected consumption category;

determine a likelihood of a peak event for the selected consumption category, wherein the peak event includes exceeding the peak consumption threshold during the future time period based on the weather forecast information; and

if the likelihood of the peak event exceeds a boundary threshold indicating that the likelihood is high, trigger resource conservation for a portion of the utility customers associated with the selected consumption category, wherein the resource conservation includes sending instructions to reduce consumption of the consumable resource during the future time period, wherein the triggering resource conservation causes at least one of the one or more smart devices to adjust consumption of the at least one consumable resource during the future time period.

10. The device of claim 9, wherein the instructions further comprise instructions that when executed by the processor cause the processor to:

build a model for each of the consumption categories, wherein the model for a respective consumption category is based on weather data associated with the respective consumption category.

11. The device of claim 10, wherein the model comprises a linear regression model based on the resource consumption data and the peak consumption threshold for the respective consumption category.

12. The device of claim 9, wherein the instructions to segment the resource consumption data into one or more consumption categories further comprise instructions that when executed by the processor cause the processor to:

identify two or more similar time periods; and

associate the resource consumption data for each of the two or more similar time periods into a common consumption category from among the consumption categories.

13. The device of claim 9, wherein the peak consumption threshold is based on a predetermined percentile of the consumption values for the selected consumption category.

14. The device of claim 9, wherein the instructions to trigger resource conservation of the at least one consumable resource for the portion of the plurality of utility customers further comprise instructions that when executed by the processor cause the processor to:

issue a notification to each utility customer of the portion of the plurality of utility customers.

15. A non-transitory, computer-readable medium having software encoded thereon, wherein the software, when executed by a processor, causes the processor to:

receive resource consumption data from one or more smart devices for a plurality of utility customers, wherein the resource consumption data comprises an indication of an amount of at least one consumable resource used by each of the plurality of utility customers;

segment the resource consumption data into one or more consumption categories based at least in part on similarity of resource consumption, wherein each of the one or more consumption categories are defined to include at least consumption data for similar days;

calculate a plurality of consumption values for each of the consumption categories;

identify a peak consumption threshold for a selected consumption category, wherein the peak consumption threshold is based at least in part on a multiple of an average of the plurality of consumption values for the selected consumption category;

receive weather forecast information for a future time period;

associate the weather forecast information with the selected consumption category;

determine a likelihood of a peak event for the selected consumption category, wherein the peak event includes exceeding the peak consumption threshold during the future time period based on the weather forecast information; and

if the likelihood of the peak event exceeds a boundary threshold indicating that the likelihood is high, trigger resource conservation for a portion of the utility customers associated with the selected consumption category, wherein the resource conservation includes sending instructions to reduce consumption of the consumable resource during the future time period, wherein the triggering resource conservation causes at least one of the one or more smart devices to adjust consumption of the at least one consumable resource during the future time period.

16. The non-transitory, computer-readable medium of claim 15, wherein the software causes the processor to segment the resource consumption data into one or more consumption categories by:

identifying two or more similar time periods; and

associating the resource consumption data for each of the two or more similar time periods into a common consumption category from among the consumption categories.

17. The non-transitory, computer-readable medium of claim 15, wherein the peak consumption threshold is based on a predetermined percentile of the consumption values for the selected consumption category.

18. The non-transitory, computer-readable medium of claim 15, wherein the software causes the processor to trigger resource conservation of the at least one consumable resource for the portion of the plurality of utility customers by:

issuing a notification to each utility customer of the portion of the plurality of utility customers.