Users campaign for peaking energy usage

• US 10,467,249 B2
• Filed: 12/23/2014
• Issued: 11/05/2019
• Est. Priority Date: 08/07/2014
• Status: Active Grant

• Current Assignee: Opower, Inc. (Oracle Corporation)
• Original Assignee: Opower, Inc. (Oracle Corporation)
• Inventors: Shilts, Erik, Chung, Garner, Yu, Suelyn, Royer, David
• Primary Examiner(s): Leroux, Etienne P
• Assistant Examiner(s): Samara, Husam Turki
• Application Number:
  US14/581,105
• Publication Number:
  US 20160042049A1
• Time in Patent Office: 1,778 Days
• CPC Class Codes: G06F 16/283 Multi-dimensional databases or data warehouses, e.g. MOLAP or ROLAP
• 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
• CPC Class Codes: H04L 67/12 specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
• CPC Class Codes: Y02D 10/00 Energy efficient computing, e.g. low power processors, power management or thermal management

Abstract

Aspects of the subject technology relate to a system that analyzes customers'"'"' AMI load curves, identifies evening peak users as defined by their load curves, and provides Energy Efficiency (EE) advice related to their periods of high use. For example, identified high evening users can be sent an email with normative comparisons on evening load use, along with tips to reduce energy usage. Other aspects relate to additional targets/communications. Aspects of the subject technology relate to categorizing a user'"'"'s energy consumption tendencies based on a user'"'"'s load curve and providing customized content based on the user'"'"'s category. By taking into consideration the user'"'"'s actual energy consumption patterns, the system may be able to provide more relevant content to the user.

Claims

1. A computer-implemented method, comprising:

aggregating, by a processor of a computer, consumption data for a plurality of users, the consumption data corresponding with an amount of energy resource consumption for each of the plurality of users, wherein the consumption data is retrieved over a network from meters;

generating, by the processor from the consumption data, a load curve for each of the plurality of users;

identifying, by the processor from the load curves, a set of target users that consume more resources during a first time period than a second time period out of the plurality of users;

wherein the identifying comprises;

comparing the load curve of each of the plurality of users to a plurality of load curve archetypes, wherein each load curve archetype includes a respective load curve that represents a type of user based on energy consumption tracked during a time period;

wherein the plurality of load curve archetypes includes a first archetype that categorizes the user as an evening peak user that has a peak usage in an evening time period and a second archetype that categorizes the user as a morning peak user that has the peak usage in a morning time period;

associating each of the plurality of users as the evening peak user or the morning peak user based on the load curve archetype that the user'"'"'s load curve most closely resembles; and

identifying the set of target users from the plurality of users as users being the evening peak users whose load curve resembles the first archetype that has the peak usage in the evening time period;

analyzing, by the processor, a plurality of available recommendations to identify a first recommendation associated with the evening peak users;

modifying, by the processor, the first recommendation to include an instruction for causing an action to be performed to adjust a setting in a climate control device to reduce resource consumption during the evening time period;

generating, by the processor, use reports in electronic form for each target user in the set of target users, and modifying the use reports to include the first recommendation for each target user, wherein the modified use report provides a visual display of the consumption data for a corresponding target user; and

controlling, by the processor over a computer network based on the set of target users, transmission of each of the use reports in electronic form to remote devices associated with corresponding target users from the set of target users, wherein the use report and the first recommendation is transmitted to cause the evening peak user to adjust the climate control device to reduce resource consumption during the evening time period.

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

modifying the first recommendation with a suggestion to switch from a current electricity rate plan to a different electricity rate plan based upon a load curve of a target user and rate plan data of electricity rate plans.

3. The computer-implemented method of claim 1, wherein generating load curves for the plurality of users further comprises:

determining one or more values measuring energy consumption at specified intervals over a specified time period, each of the one or more values at the specified intervals representing an average amount of energy usage at a specified interval of the specified time period;

determining a total amount of energy usage for the specified time period;

for each value measured at each specified interval over the specified time period, determining a percentage of the total amount of energy usage based on the value; and

generating a graphical representation of a respective load curve based at least in part on the percentage of the total amount of energy usage at each of the specified intervals over the specified time period.

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

determining, by the processor, that a target user owns an electric vehicle based upon a load curve of the target user; and

modifying, by the processor, the first recommendation to further include a suggestion for charging the electric vehicle at a particular time.

5. The computer-implemented method of claim 3, wherein the values measuring energy consumption at specified intervals over the specified time period further represent a standard deviation of usage at a respective interval, or a baseload at the respective interval.

6. The computer-implemented method of claim 1, wherein the identifying a set of target users further comprises:

using a clustering algorithm to segment users into one or more categories based on the load curves and the plurality of load curve archetypes.

7. The computer-implemented method of claim 6, wherein the clustering algorithm comprises a k-means algorithm.

8. The computer-implemented method of claim 6, wherein the one or more categories comprise at least one of the evening peak user, the morning peak user, a mid-day peak user, or a peak user corresponding to a season within a year.

9. A computing device for implementing an evening peak user campaign, the computing device comprising:

at least one processor; and

memory storing instructions that, when executed by the at least one processor, cause the computing device to;

aggregate consumption data for a plurality of users, the consumption data corresponding with an amount of energy resource consumption for each of the plurality of users;

generate, from the consumption data, a load curve for each of the plurality of users;

identify, based at least in part on the load curves, a set of target users that consume more resources during a first time period than a second time period out of the plurality of users;

wherein the identifying comprises;

comparing the load curve of each of the plurality of users to a plurality of load curve archetypes, wherein each load curve archetype includes a respective load curve that represents a type of user based on energy consumption tracked during a time period;

wherein the plurality of load curve archetypes includes a first archetype that categorizes the user as an evening peak user that has a peak usage in an evening time period and a second archetype that categorizes the user as a morning peak user that has the peak usage in a morning time period;

associating each of the plurality of users as the evening peak user or the morning peak user based on the load curve archetype that the user'"'"'s load curve most closely resembles; and

identifying the set of target users from the plurality of users as users being the evening peak users whose load curve resembles the first archetype that has the peak usage in the evening time period;

analyze a plurality of available recommendations to identify a first recommendation associated with the evening peak users;

modify the first recommendation to include an instruction for causing an action to be performed to adjust a setting in climate control device to reduce resource consumption during the evening time period;

generate use reports in electronic form for each target user in the set of target users, and modifying the use reports to include the first recommendation for each target user, wherein the modified use report provides a visual display of the consumption data for a corresponding target user; and

control transmission of each of the use reports in electronic form over a computer network based on the set of target users to remote devices associated with corresponding target users from the set of target users, wherein use report and the first recommendation is transmitted to cause the evening peak user to adjust the climate control device to reduce resource consumption during the evening time period.

10. The computing device of claim 9, wherein a target user consumes more resources during evening hours than other hours in a day, and wherein the instructions cause the computing device to:

determine that a target user owns an electric vehicle based upon a load curve of the target user;

modify the first recommendation to include energy efficiency advice for charging the electric vehicle at a particular time.

11. The computing device of claim 9, wherein at least one load curve from the load curves includes a peak portion that indicates a higher usage of resources during a portion of a time period in comparison with remaining portions of the time period.

12. The computing device of claim 9, wherein to generate load curves for the plurality of users further comprises:

determining one or more values measuring energy consumption at specified intervals over a specified time period, each of the one or more values at the specified intervals representing an average amount of energy usage at a specified interval of the specified time period;

determining a total amount of energy usage for the specified time period;

for each value measured at each specified interval over the specified time period, determining a percentage of the total amount of energy usage based on the value; and

generating a graphical representation of a respective load curve based at least in part on the percentage of the total amount of energy usage at each of the specified intervals over the specified time period.

13. The computing device of claim 12, wherein the specified time period is a day and each of the specified intervals are respective hours in the day.

14. The computing device of claim 12, wherein the values measuring energy consumption at specified intervals over the specified time period further represent a standard deviation of usage at a respective interval, or a baseload at the respective interval.

15. The computing device of claim 9, wherein the identifying a set of target users user further comprises:

using a clustering algorithm to identify a respective user as a target user for inclusion within the set of target users based on a load curve of the target user and one or more categories represented by the plurality of load curve archetypes.

16. The computing device of claim 15, wherein the one or more categories comprise at least one of the evening peak user, the morning peak user, a mid-day peak user, or a peak user corresponding to a season within a year.