Systems and Methods for Disaggregating Appliance Loads

1 . A method for identifying appliances and energy usage in a home, the method comprising the steps of:

performing energy disaggregation of household energy consumption data to obtain at least partially disaggregated energy data and identify at least some appliances and energy usage in the home, energy disaggregation of household energy consumption data based at least in part upon:

(i) household energy consumption data for the home; and

(ii) (ii) one or more parameters associated with the home corresponding to a plurality of appliances installed in the home;

applying a rule-based model based at least in part on localized energy consumption data and one or more parameters associated with the home corresponding to at least some appliances and energy usage in the home, comprising:

receiving localized energy consumption data of a region where the home is located;

selecting a predefined rule-based model from one or more predefined rule-based models based on the localized energy consumption data;

adjusting the predefined rule-based model based on the one or more parameters; and

applying the adjusted predefined rule-based model to the at least partially disaggregated energy data to perform complete or near complete disaggregation of the household energy consumption data into a plurality of appliance categories.

2 . (canceled)

3 . The method of claim 1 , wherein the one or more parameters comprises: plurality of patterns indicating energy consumption, plurality of base load activities, plurality of user attributes, plurality of home attributes, plurality of appliances attributes, plurality of weather attributes, energy disaggregation output from other algorithms, and historical energy disaggregation results.

4 . The method of claim 1 , wherein the localized energy consumption data comprises: data indicating type, size of the home, and age of the home, type of devices being used in the region, and weather condition of the region.

5 . The method of claim 1 , wherein the one or more predefined energy disaggregation models are created based on at least one of: home attributes, appliance attributes, region attributes, and/or combination thereof.

6 . The method of claim 1 , wherein the predefined disaggregation models comprise:

one or more constraints, rules and weights that define how energy should be distributed across different output categories.

7 . The method of claim 1 , wherein executing the adjusted predefined energy disaggregation model comprises executing the adjusted model for at least one specific period of aggregate energy consumption.

8 . The method of claim 1 , wherein detecting the energy consumption data comprises receiving the energy consumption data sampled at a predefined interval of time.

9 . The method of claim 1 , wherein the plurality of appliance categories comprises at least one of: “always on’; “space heating”; “refrigeration”; “entertainment”; “water heating”;

“cooking”; “laundry”; “electric vehicle”; “pool and sauna”; “lighting” and/or a combination thereof.

10 . An energy disaggregation device for performing energy disaggregation of plurality of appliances installed in a home, the device comprising:

at least one hardware processor;

a memory coupled to the at least one hardware processor, storing instructions, that when executed by the at least one hardware processor, causes the at least one hardware processor to perform operations comprising:

performing energy disaggregation of household energy consumption data to obtain at least partially disaggregated energy data and identify at least some appliances and energy usage in the home, energy disaggregation of household energy consumption data based at least in part upon:

household energy consumption data for the home; and

(ii) (ii) one or more parameters associated with the home corresponding to a plurality of appliances installed in the home;

applying a rule-based model based at least in part on localized energy consumption data and one or more parameters associated with the home corresponding to at least some appliances and energy usage in the home, comprising:

receiving localized energy consumption data of a region where the home is located through the energy disaggregation device;

selecting a predefined rule-based model from one or more predefined rule-based models based on the localized energy consumption data;

adjusting the predefined rule-based model based on the one or more parameters; and

applying the adjusted predefined rule-based model to the at least partially disaggregated energy data to perform complete or near complete disaggregation of the household energy consumption data into a plurality of appliance categories by the energy disaggregation device.

11 . (canceled)

12 . The device of claim 10 , wherein the one or more parameters comprises: plurality of patterns indicating energy consumption, plurality of base load activities, plurality of user attributes, plurality of home attributes, plurality of appliances attributes, plurality of weather attributes, energy disaggregation output from other algorithms, and historical energy disaggregation results.

13 . The device of claim 10 , wherein the localized energy consumption data comprises data indicating type, size of the home, and age of buildings, type of devices being used in the region, and weather condition of the region.

14 . The device of claim 10 , wherein the one or more predefined energy disaggregation models are created based on at least one of: home attributes, appliance attributes, region attributes, and/or combination thereof.

15 . The device of claim 10 , wherein executing the adjusted predefined energy disaggregation model comprises executing the adjusted model for at least one specific period of aggregate energy consumption.

16 . The device of claim 10 , wherein detecting the energy consumption data comprises receiving the energy consumption data sampled at a predefined interval of time.

17 . A non-transitory computer storage medium storing instructions, that when executed by the at least one hardware processor, causes the at least one hardware processor to perform operations comprising:

performing energy disaggregation of household energy consumption data to obtain at least partially disaggregated energy data and identify at least some appliances and energy usage in the home, energy disaggregation of household energy consumption data based at least in part upon:

(i) household energy consumption data for the home; and

(ii) (ii) one or more parameters associated with the home corresponding to a plurality of appliances installed in the home;

applying a rule-based model based at least in part on localized energy consumption data and one or more parameters associated with the home corresponding to at least some appliances and energy usage in the home, comprising:

receiving localized energy consumption data of a region where the home is located;

selecting a predefined rule-based model from one or more predefined rule-based models based on the localized energy consumption data;

adjusting the predefined rule-based model based on the one or more parameters; and

applying the adjusted predefined rule-based model to the at least partially disaggregated energy data to perform complete or near complete disaggregation of the household energy consumption data into a plurality of appliance categories.

18 . (canceled)

19 . The medium of claim 17 , wherein the one or more parameters comprises: plurality of patterns indicating energy consumption, plurality of base load activities, plurality of user attributes, plurality of home attributes, plurality of appliances attributes, plurality of weather attributes, energy disaggregation output from other algorithms, energy disaggregation results of other similar homes, and historical energy disaggregation results.

20 . The medium of claim 17 , wherein executing the adjusted predefined energy disaggregation model comprises executing the adjusted model for at least one specific period of aggregate energy consumption.