Inferring residential home characteristics based on energy data

• US 10,410,130 B1
• Filed: 08/07/2014
• Issued: 09/10/2019
• Est. Priority Date: 08/07/2014
• Status: Active Grant

• Current Assignee: Opower, Inc. (Oracle Corporation)
• Original Assignee: Opower, Inc. (Oracle Corporation)
• Inventors: Kochaniak, Joanna, Gunel, Arhan, Nerlikar, Rajesh, Ben-Meshulam, Yoni, Rubio, Jan, Vattay, Anton, Siemon, Randall Benjamin, Shilts, Erik
• Primary Examiner(s): Chaki, Kakali
• Assistant Examiner(s): Smith, Brian M
• Application Number:
  US14/454,360
• Time in Patent Office: 1,860 Days
• Field of Search: None
• CPC Class Codes: G06N 20/10 using kernel methods, e.g. support vector machines [SVM]
• CPC Class Codes: G06N 3/088 Non-supervised learning, e.g. competitive learning
• CPC Class Codes: G06N 5/048 Fuzzy inferencing
• CPC Class Codes: G06Q 30/0201 Market modelling; Market analysis; Collecting market data
• CPC Class Codes: G06Q 50/06 Energy or water supply

Abstract

A residential home characteristics inferring method and system that receives information about energy usage by an energy user, determines using a processor and the received information about energy usage average daily usage during a heating season and average daily usage during a shoulder season, and identifies the fuel type used for heating by the energy user using the determined average daily usage during the heating season and the determined average daily usage during the shoulder season.

Claims

1. A method for controlling transmission of energy efficiency tips based on a fuel type identified as being used for heating by a plurality of energy users and promoting energy efficiency, the method comprising:

receiving energy usage information from at least one energy usage data source, the energy usage information comprising a quantity of energy supplied by a utility to each of the energy users;

generating, using a processor and the energy usage information received, for each of the energy users, a data structure populated with content comprising;

(i) average usage during a heating season and average usage during a shoulder season;

(ii) a difference between the average usage during the heating season and the average usage during the shoulder season; and

(iii) a ratio between the average usage during the heating season and the average usage during the shoulder season;

identifying, for each of the plurality of energy users for whom the fuel type used for heating is unavailable to be retrieved from the at least one energy usage data source, the fuel type used for heating from a plurality of fuel types, wherein the fuel type is identified using a learned linear discrimination function that is a function of the generated difference and the generated ratio from the content of the data structure;

controlling classification of the energy users into sets of compatible users corresponding to the plurality of fuel types identified for the energy users using the learned linear discrimination function, wherein the classification generates a first set of comparable energy users, and each of the comparable energy users classified in the first set uses a first fuel type from the plurality of fuel types;

conducting a comparison of the energy usage by at least one of the comparable energy users in the first set to energy usage by other comparable energy users in the first set to provide the at least one of the comparable energy users in the first set with a comparison result that is relevant to usage of the first fuel type for heating;

generating a targeted energy efficiency tip for the at least one of the comparable energy users that is relevant to the first fuel type, wherein the targeted energy efficiency tip is based, at least in part, on the comparison;

based on the classification of the at least one of the compatible users in the first set, controlling transmission of an electronic message including the targeted energy efficiency tip and the comparison over a communication network to a remote device associated with the at least one of the comparable energy users for changing a setting of heating systems associated with the at least one of the comparable energy users; and

generating, by a printer and based on the classification of at least a second compatible user in the first set, a paper report comprising a comparison of energy usage by the second compatible user to the energy usage by other comparable energy users included in the first set.

2. The method of claim 1, wherein receiving the energy usage information comprises receiving information about at least one of electricity usage or gas usage by the energy users.

3. The method of claim 1, wherein identifying the fuel type used for heating by the energy users further comprises, for each of the energy users:

determining a level of confidence in the fuel type used for heating identified using the determined difference and the determined ratio;

receiving information on the fuel type used for heating from at least one of the energy user, the utility, a third party, or rate plan information received from the utility;

determining a level of confidence in the received information on the fuel type used for heating; and

identifying the fuel type used for heating using the level of confidence in the identified fuel type and the level of confidence in the received information on the fuel type.

4. The method of claim 1, wherein identifying the fuel type used for heating further comprises, for each of the energy users, determining a confidence level regarding the identified fuel type used for heating.

5. The method of claim 1, wherein:

the average usage during the heating season comprises information about average daily usage during the heating season; and

the average usage during the shoulder season comprises information about average daily usage during the shoulder season.

6. A non-transitory computer readable medium storing instructions that, when executed by a processor of a computing device, cause the computing device to:

receive average energy usage information for a heating season from at least one energy usage data source, the average energy usage information for the heating season comprising an average quantity of energy used by energy users during the heating season;

receive average energy usage information for a shoulder season from the at least one energy usage data source, the average energy usage information for the shoulder season comprising an average quantity of energy used by the energy users during the shoulder season;

generate, for each of the energy users, a data structure populated with content comprising;

(i) a difference between the average quantity of energy used during the heating season and the average quantity of energy used during the shoulder season; and

(ii) a ratio between the average quantity of energy used during the heating season and the average quantity of energy used during the shoulder season;

identify, for each of the plurality of energy users for whom a fuel type used for heating is unavailable to be retrieved from the at least one energy usage data source, a fuel type used for heating from a plurality of fuel types, wherein the fuel type is identified using a learned linear discriminant function that is a function of the generated difference and the generated ratio from the content of the data structure;

control classification of the energy users into sets of compatible users corresponding to the plurality of fuel types identified for the energy users using the learned linear discrimination function, wherein the classification generates a first set of comparable energy users, and each of the comparable energy users classified in the first set uses a first fuel type from the plurality of fuel types;

conduct a comparison of energy usage by at least one of the comparable energy users in the first set to energy usage by other comparable energy users in the first set to provide the at least one of the comparable energy users in the first set with a comparison result that is relevant to usage of the first fuel type for heating;

generate a targeted energy efficiency tip for the at least one of the comparable energy users that is relevant to the first fuel type, wherein the targeted energy efficiency tip is based, at least in part, on the comparison; and

based on the set of comparable users, control transmission of electronic messages including the targeted energy efficiency tip and the comparison over a communication network to a remote device associated with the at least one of the comparable energy users for changing a setting of heating systems associated with the at least one of the comparable energy users.

7. The non-transitory computer readable medium of claim 6, further comprising instructions that, when executed, cause the computing device to receive information about at least one of electricity usage or gas usage as the average energy usage information.

8. The non-transitory computer readable medium of claim 6 further comprising instructions that, when executed, cause the computing device to, for each of the energy users:

determine a level of confidence in the fuel type used for heating identified using the received average energy usage during the heating season and the received average energy usage during the shoulder season;

receive information on the fuel type used for heating from at least one of the energy user, the utility, a third party, or rate plan information received from the utility;

determine a level of confidence in the received information on the fuel type used for heating; and

identify the fuel type used for heating using the level of confidence in the identified fuel type and the level of confidence in the received information on the fuel type.

9. The non-transitory computer readable medium of claim 6 further comprising instructions that, when executed, cause the computing device to determine a confidence level regarding the identified fuel type used for heating.

10. A system for controlling transmission of energy efficiency tips based on a fuel type identified as being used for heating by energy users and promoting energy efficiency, the system comprising:

a network receiver that receives information about energy usage by each of the energy users from a network resource over a network; and

a processor that uses the information about energy usage received by the network receiver to generate, for each energy user;

(i) an average daily usage during a heating season,

(ii) an average daily usage during a shoulder season,

(iii) a difference between the average daily usage during the heating season and the average daily usage during the shoulder season, and

(iv) a ratio between the average daily usage during the heating season and the average daily usage during the shoulder season;

wherein the processor further;

identifies, for each of the plurality of energy users for whom the fuel type used for heating is unavailable to be retrieved from the at least one energy usage data source, the fuel type used for heating from a plurality of fuel types, wherein the fuel type is identified using a learned linear discriminant function that is a function of the generated difference and the generated ratio,

controlling classification of the energy users into sets of compatible users corresponding to the plurality of fuel types identified for the energy users using the learned linear discrimination function, wherein the classification generates a first set of comparable energy users, and each of the comparable energy users classified in the first set uses a first fuel type from the plurality of fuel types,

conducts a comparison of the energy usage by at least one of the comparable energy users in the first set to energy usage by other comparable energy users in the first set to provide the at least one of the comparable energy users in the first set with a comparison result that is relevant to usage of the first fuel type for heating,

generates a targeted energy efficiency tip for the at least one of the comparable energy users that is relevant to the first fuel type, wherein the targeted energy efficiency tip is based, at least in part, on the comparison; and

based on the classification of the at least one of the compatible users in the first set, controls transmission of an electronic message including the targeted energy efficiency tip and the comparison over a communication network to a remote device associated with the at least one of the comparable energy users for changing a setting of heating systems associated with the at least one of the comparable energy users.

11. The system of claim 10, wherein the network receiver receives information about at least one of electricity usage or gas usage as the average daily usage.

12. The system of claim 10, wherein the processor, in identifying the fuel type used for heating, uses at least one of rate plan information received from a utility, or a specified fuel type obtained from at least one of:

(i) the energy users, (ii) the utility, and (iii) a third party.

13. The system of claim 10, wherein the processor, in identifying the fuel type used for heating, determines a confidence level regarding the identified fuel type used for heating.