Detecting actuation of electrical devices using electrical noise over a power line

• US 8,094,034 B2
• Filed: 09/16/2008
• Issued: 01/10/2012
• Est. Priority Date: 09/18/2007
• Status: Expired due to Fees

• Current Assignee: Georgia Tech Research Corporation (University System of Georgia)
• Original Assignee: Georgia Tech Research Corporation (University System of Georgia)
• Inventors: Patel, Shwetak N., Robertson, Thomas M., Abowd, Gregory D., Reynolds, Matthew S.
• Primary Examiner(s): La, Anh V
• Application Number:
  US12/283,869
• Publication Number:
  US 20090072985A1
• Time in Patent Office: 1,211 Days
• Field of Search: 340/538, 340/657, 340/310.11, 340/310.12, 340/644, 375/219, 375/220, 375/240.18, 375/240.19
• US Class Current: 340/657
• CPC Class Codes: G01D 2204/24 Identification of individual loads, e.g. by analysing current/voltage waveforms
• CPC Class Codes: G01R 21/006 Measuring power factor
• CPC Class Codes: G01R 29/26 Measuring noise figure; Measuring signal-to-noise ratio
• CPC Class Codes: G05B 2219/40408 Intention learning
• CPC Class Codes: G06F 17/00 Digital computing or data processing equipment or methods, specially adapted for specific functions information retrieval, database structures or file system structures therefor G06F16/00
• CPC Class Codes: H04B 2203/5425 improving S/N by matching impedance, noise reduction, gain control
• CPC Class Codes: H04B 2203/5458 Monitor sensor; Alarm systems
• CPC Class Codes: H04B 3/544 Setting up communications; Call and signalling arrangements
• CPC Class Codes: Y04S 20/30 Smart metering, e.g. specially adapted for remote reading

Abstract

Activity sensing in the home has a variety of important applications, including healthcare, entertainment, home automation, energy monitoring and post-occupancy research studies. Many existing systems for detecting occupant activity require large numbers of sensors, invasive vision systems, or extensive installation procedures. Disclosed is an approach that uses a single plug-in sensor to detect a variety of electrical events throughout the home. This sensor detects the electrical noise on residential power lines created by the abrupt switching of electrical devices and the noise created by certain devices while in operation. Machine learning techniques are used to recognize electrically noisy events such as turning on or off a particular light switch, a television set, or an electric stove. The system has been tested to evaluate system performance over time and in different types of houses. Results indicate that various electrical events can be learned and classified with accuracies ranging from 85-90%.

Claims

1. Apparatus for use with one or more electrical loads coupled by way of one or more switching devices to an electrical power line infrastructure, wherein the one or more electrical loads generate one or more transient electrical noise patterns when the one or more electrical loads are switched on or off, the apparatus comprising:

a computer apparatus configured to couple the electrical power line infrastructure and further configured to identify one or more first transient electrical noise signatures associated with the one or more electrical loads,

wherein;

the computer apparatus comprises;

a power line interface configured to filter one or more transient electrical noise signals transmitted over the electrical power line infrastructure caused by switching the one or more electrical loads on or off;

a fast Fourier transform module configured to process the one or more transient electrical noise signals from the power line interface to generate voltage versus frequency data, the voltage versus frequency data corresponding to a first transient electrical noise pattern of the one or more transient electrical noise patterns corresponding to a first electrical load of the one or more electrical loads that has been switched on or off; and

computer software configured to run on a computer and further configured to process the voltage versus frequency data to generate a unique second transient electrical noise signature, the computer software is further configured to identify the first electrical load of the one or more electrical loads based upon the unique second transient electrical noise signature and the one or more first transient electrical noise signatures associated with the one or more electrical loads;

the computer software is in communication with the fast Fourier transform module; and

the power line interface is further configured to couple to an electrical outlet of the electrical power line infrastructure.

2. The apparatus recited in claim 1 wherein

the computer apparatus is further configured to record the one or more first transient electrical noise signatures, the one or more first transient electrical noise signatures identify the one or more electrical loads as the one or more electrical loads are switched on and off;

and the computer apparatus is further configured to identify the first electrical load of the one more electrical loads by comparing the one or more first transient electrical noise signatures to the unique second transient electrical noise signature.

3. The apparatus recited in claim 1 wherein the computer apparatus further comprises:

a transmitter configured to transmit an interrogation signal over the electrical power line infrastructure that interacts with a first switching device of the one or more switching devices; and

a receiver configured to receive a return noise signature from the first switching device of the one or more switching devices in response to the interrogation signal; and

wherein the computer apparatus is further configured to process the return noise signature to determine whether the one or more electrical loads have been switched on or off.

4. The apparatus recited in claim 1 wherein the fast Fourier transform module is configured to perform a fast Fourier transform on the one or more transient electrical noise signals to separate component frequencies contained in the one or more transient electrical noise signals, and wherein the computer software running on the computer is further configured to process the voltage versus frequency data to generate the unique second transient electrical noise signature, and the computer software is further configured to store the unique second transient noise signature in a database or retrieve at least one of the one or more first transient noise signatures from the database that corresponds to the unique second transient electrical noise signature.

5. The apparatus recited in claim 4 wherein the computer software is configured to store the one or more first transient electrical noise signatures in the database.

6. The apparatus recited in claim 5 wherein the computer software is further configured to process the unique second transient electrical noise signature and present information regarding the first electrical load of the one or more electrical loads in a graphical user interface in a format indicating when and how often the first electrical load of the one or more electrical loads is switched on and off.

7. The apparatus recited in claim 1 wherein the computer software is further configured to remotely transfer the unique second transient electrical noise signature to a central database for power consumption analysis.

8. The apparatus recited in claim 1 wherein the computer software is further configured to process the voltage versus frequency data using machine learning techniques.

9. The apparatus recited in claim 1 wherein the fast Fourier transform module comprises fast Fourier transform circuitry or fast Fourier transform software;

and

the fast Fourier transform software is configured to run on the computer.

10. Apparatus for use with one or more electrical loads coupled by way of one or more switching devices to an electrical power line infrastructure, wherein one or more electrical noise patterns are generated when the one or more electrical loads are switched on or off, the apparatus comprising:

a power line interface configured to filter one or more electrical noise signals transmitted over the electrical power line infrastructure caused by switching the one or more electrical loads on or off;

a fast Fourier transform module configured to process the one or more electrical noise signals from the power line interface to generate voltage versus frequency data, the voltage versus frequency data corresponding to a first electrical noise pattern of the one or more electrical noise patterns corresponding to a first electrical load of the one or more electrical loads that has been switched on or off;

computer software configured to run on a computer in communication with the Fourier transform module and further configured to process the voltage versus frequency data to generate a unique first electrical noise signature, the computer software is further configured to identify the first electrical load of the one or more electrical loads based upon one or more second electrical noise signatures and the unique first electrical noise signature,

wherein;

each signature of the one or more second electrical noise signatures is associated with switching on or off one of the one or more electrical loads.

11. The apparatus recited in claim 10 wherein the fast Fourier transform module is configured to perform a fast Fourier transform on the electrical noise signals to separate two or more component frequencies contained in the one or more electrical noise signals, and wherein the computer software is further configured to process the voltage versus frequency data to generate the unique first electrical noise signature, and is further configured to store the unique first electrical noise signature in a database or retrieve one of the one or more second electrical noise signatures from the database that corresponds to the unique first electrical noise signature.

12. The apparatus recited in claim 11 wherein the computer software is further configured to store the one or more second electrical noise signatures in the database.

13. The apparatus recited in claim 12 wherein the computer software is further configured to process the unique first electrical noise signature and presents information regarding the first electrical load of the one or more electrical loads in a graphical user interface indicating when and how often the first electrical load of the one or more electrical loads is switched on and off.

14. The apparatus recited in claim 10 wherein the computer software is further configured to remotely transfer the unique first electrical noise signature to a central database for power consumption analysis.

15. The apparatus recited in claim 10 wherein the computer software is further configured to processes the voltage versus frequency data using machine learning techniques.

16. The apparatus recited in claim 10 wherein the power line interface is further configured to couple to an electrical outlet of the electrical power line infrastructure.

17. A method comprising:

monitoring electrical noise transmitted over an electrical power line infrastructure;

using a processor in a data analysis apparatus to detect one or more electrical noise patterns in the electrical noise transmitted over the electrical power line infrastructure that corresponds to actuation of the one or more electrical devices; and

using the processor in the data analysis apparatus to process the one or more electrical noise patterns to generate a unique first electrical noise signature that identifies a first electrical device of the one or more electrical devices that was actuated,

wherein;

using the processor in the data analysis apparatus to detect the one or more electrical noise patterns comprises;

using the processor in the data analysis apparatus to fast Fourier transform the electrical noise transmitted over the electrical power line infrastructure to generate voltage versus frequency data corresponding to the first electrical device of the one or more electrical devices that was actuated; and

using the processor in the data analysis apparatus to process the one or more electrical noise patterns comprises;

using the processor in the data analysis apparatus to process the voltage versus frequency data to generate the unique first electrical noise signature associated with the first electrical device of the one or more electrical devices that was actuated.

18. The method recited in claim 17 further comprising:

storing the unique first electrical noise signature in a database or retrieving a second electrical noise signature from the database that corresponds to the unique first electrical noise signature.

19. The method recited in claim 17 further comprising:

using the processor in the data analysis apparatus to correlate the unique first electrical noise signature to the first electrical device of the one or more electrical devices that was actuated.

20. The method recited in claim 17 wherein:

using the processor in the data analysis apparatus to detect the one or more electrical noise patterns comprises;

using a computer to detect the one or more electrical noise patterns in the electrical noise transmitted over the electrical power line infrastructure that corresponds to actuation of the one or more electrical devices;

using the processor in the data analysis apparatus to process the electrical noise patterns comprises;

using the computer to process the one or more electrical noise patterns to generate the unique first electrical noise signature that identifies the first electrical device of the one or more electrical devices that was actuated; and

the data analysis apparatus comprises the computer.

21. A method comprising:

coupling one or more electrical devices to an electrical power line infrastructure by way of one or more switching devices;

monitoring electrical noise transmitted over the electrical power line infrastructure;

detecting one or more electrical noise patterns in the electrical noise transmitted over the electrical power line infrastructure that corresponds to actuation of the one or more electrical devices; and

processing the one or more electrical noise patterns to generate a unique first electrical noise signature that identifies a first electrical device of the one or more electrical devices that was actuated,

wherein;

monitoring the electrical noise transmitted over the electrical power line infrastructure comprises actuating the first electrical device of the one or more electrical devices to generate the electrical noise on the electrical power line infrastructure, and filtering the electrical noise generated on the electrical power line infrastructure by the first electrical device of the one or more electrical devices; and

processing the one or more electrical noise patterns further comprises storing the unique first electrical noise signature in a database or retrieving a second electrical noise signature from the database that corresponds to the unique first electrical noise.

22. The method recited in claim 21 further comprising:

displaying the unique electrical noise signature in a graphical user interface of a computer.