Energy disaggregation techniques for low resolution whole-house energy consumption data

• US 10,114,347 B2
• Filed: 04/25/2013
• Issued: 10/30/2018
• Est. Priority Date: 04/25/2012
• Status: Active Grant

• Current Assignee: Bidgely, Inc.
• Original Assignee: Bidgely, Inc.
• Inventors: Gupta, Abhay, Kharbouch, Alaa, Garud, Vivek, Cheng, Hsien-Ting
• Primary Examiner(s): Ali, Mohammad
• Assistant Examiner(s): Lindsay, Bernard G
• Application Number:
  US13/870,838
• Publication Number:
  US 20130289788A1
• Time in Patent Office: 2,014 Days
• Field of Search: None
• CPC Class Codes: G01D 2204/24 Identification of individual loads, e.g. by analysing current/voltage waveforms
• CPC Class Codes: G05B 13/02 electric
• CPC Class Codes: G05B 15/02 electric
• CPC Class Codes: G05B 2219/2642 Domotique, domestic, home control, automation, smart house
• CPC Class Codes: H02J 2310/14 The load or loads being home appliances
• CPC Class Codes: H02J 2310/70 Load identification
• CPC Class Codes: H02J 3/14 by switching loads on to, or off from, network, e.g. progressively balanced loading
• CPC Class Codes: Y02B 70/30 Systems integrating technologies related to power network operation and communication or information technologies for improving the carbon footprint of the management of residential or tertiary loads, i.e. smart grids as climate change mitigation technology in the buildings sector, including also the last stages of power distribution and the control, monitoring or operating management systems at local level
• CPC Class Codes: Y02B 70/3225 Demand response systems, e.g. load shedding, peak shaving
• CPC Class Codes: Y02B 90/20 Smart grids as enabling technology in buildings sector smart grids supporting the management or operation of end-user stationary applications in general, or like technologies with no associated climate change mitigation effect Y04S20/00
• CPC Class Codes: Y04S 20/00 Management or operation of end-user stationary applications or the last stages of power distribution; Controlling, monitoring or operating thereof
• CPC Class Codes: Y04S 20/222 Demand response systems, e.g. load shedding, peak shaving
• CPC Class Codes: Y04S 20/242 Home appliances
• CPC Class Codes: Y04S 20/30 Smart metering, e.g. specially adapted for remote reading

Abstract

The present invention is generally directed to methods of disaggregating low resolution whole-house energy consumption data. In accordance with some embodiments of the present invention, methods may include steps of: receiving at a processor the low resolution whole house profile; selectively communicating with a first database including non-electrical information; selectively communicating with a second database including training data; and determining by the processor based on the low resolution whole house profile, the non-electrical information and the training data, individual appliance load profiles for one or more appliances.

Claims

1. A method for learning an energy consumption signature associated with a specific appliance from low resolution energy consumption interval data associated with a specific house, comprising:

receiving at a processor low-resolution energy consumption interval data corresponding to whole house energy consumption for the specific house, wherein the low-resolution energy consumption interval data is sampled periodically with periods ranging from minute to hourly;

selectively communicating by the processor with a first database comprising non-electrical information;

selectively communicating by the processor with a second database comprising training data, the training data comprised at least in part of high resolution energy consumption data received from a plurality of homes associated with appliances at least some of which are the same type as the specific appliance, wherein the high resolution energy consumption data is sampled periodically with periods of less than one minute;

wherein training data comprises at least in part feedback information by a user through an interactive user interface using interactive charts;

determining a correlation between the low-resolution energy consumption interval data with a sample of the high resolution training data;

based on at least in part on the correlation and the non-electrical information, making a determination that the specific appliance was running during the sample of the interval data;

identifying the energy consumption signature of the specific appliance, at least in part by estimating of the energy consumption by the specific appliance at a hourly, daily or monthly scale; and

performing an action of energy management by presenting information regarding the energy consumption signature of the specific appliance to a user.

2. The method of claim 1, wherein the low-resolution energy consumption interval data is received from one or more of the group consisting of:

a smart meter;

a meter data management system from a utility;

a web site of a utility; and

a non-utility installed sensor or measuring device.

3. The method of claim 1, wherein the non-electric information comprises home and community specific attributes comprising one or more of the group consisting of:

zip code;

local weather;

home size;

home age;

information about presence of various appliances in the household;

sensor inputs such as thermostat data;

gas consumption data; and

water consumption data.

4. The method of claim 3, wherein the non-electric information is procured from third party sources.

5. The method of claim 1, wherein the first and second database are the same database.

6. The method of claim 1, wherein at least some of the training data in the second database is obtained by:

receiving high frequency energy consumption or power data from a plurality of homes;

running one or more disaggregation algorithms to produce a disaggregated appliance output;

saving the disaggregated appliance output in the second database.

7. The method of claim 1, wherein at least some of the training data in the second database is obtained from plug-level sensors.

8. The method of claim 1, wherein at least some of the training data in the second database is obtained from user provided information about start and stop times of appliances in the user'"'"'s home.

9. The method of claim 1, wherein the step of making a determination that the specific appliance was running and a probability score for each occurrence comprises:

segmenting or grouping training data based upon various criteria;

receive the input low resolution energy consumption data and determine a matching segment or group for analysis;

train a classifier based upon the determined matching segment or group;

use the trained classifier to identify occurrences of usage of the specific appliance in the input low resolution energy consumption data.

10. The method of claim 1, further comprising detecting heating or cooling appliance consumption in the low-resolution energy consumption interval data, comprising:

selecting time intervals in which heating or cooling appliances are determined to be running;

applying filters to ensure regularity of the heating and cooling appliance patterns.

11. The method of claim 1, wherein the step of learning the energy consumption signature of the specific appliance comprises:

identifying any patterns of certain periodic loads in the input low resolution energy consumption data;

determining, based upon non-electrical data, whether the house has a pool;

determining, based on scheduling consistency and the presence of a pool the existence of a pool pump;

determining, based upon the existence of a pool pump and scheduling consistency of certain periodic loads in the input low resolution energy consumption data, the individual energy consumption profile for the pool pump.

12. The method of claim 11, wherein a confidence level of energy consumption profile for the detected pool pump is calculated based on a number of attributes.

13. The method of claim 1, wherein the step of estimation of energy consumption by the specific appliance comprises:

receiving a series of detections identified occurrences of the specific appliance;

calculating weights based at least in part on the temperature profile data;

calculating the estimated energy consumption as a weighted sum of the series of detections.

14. The method of claim 13, wherein the step of estimation of energy consumption by the specific appliance comprises determining a temperature setpoint during the calculation of weights based on temperature profile data.

15. The method of claim 1, wherein the user who provides feedback information is associated with the specific house.