MONITORING OF RESOURCE CONSUMPTION PATTERNS IN AN AUTOMATED ENVIRONMENT

• US 20160091540A1
• Filed: 09/16/2015
• Published: 03/31/2016
• Est. Priority Date: 11/15/2013
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: Apple Inc.
• Inventors: Marti, Lukas M., Huang, Ronald Keryuan, Mathias, Arun G., McLaughlin, Kevin P.
• Granted Patent: US 10,416,205 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G01R 21/133 by using digital technique
• CPC Class Codes: G01R 21/1333 adapted for special tariff measuring

Abstract

An automated environment can monitor its resource consumption at the environment level and detect anomalies. Resource consumption can be monitored using a sparse set of sensors that provide information about the total resource consumption of the automated environment. The sensor data can be analyzed together with information about a behavioral routine of users in the automated environment to define a baseline resource consumption pattern. Once a baseline resource consumption pattern is established, anomalies in resource consumption can be detected and reported to users.

Claims

1. A method comprising:

identifying, by a monitoring device in an automated environment, a pattern of resource consumption for the automated environment, the pattern including a correlation between resource consumption data from one or more environment-level resource consumption sensors in the automated environment and user routine data indicative of an established routine for one or more users who frequent the automated environment;

detecting, by the monitoring device, an anomaly in a resource consumption behavior of the automated environment, wherein the anomaly includes a consumption deviation of an observed resource consumption from the pattern of resource consumption in the automated environment, wherein the consumption deviation is not correlated with a user deviation from the established routine; and

notifying at least one of the one or more users of the anomaly.

2. The method of claim 1, wherein the one or more environment-level resource consumption sensors include one or more of a group consisting of:

an electric meter;

a water meter; and

a gas meter.

3. The method of claim 1, wherein identifying the pattern of resource consumption includes:

collecting the resource consumption data from the environment-level resource consumption sensors; and

collecting the user routine data from a mobile device belonging to one of the one or more users who frequent the automated environment.

4. The method of claim 1, wherein identifying the pattern of resource consumption includes:

collecting the resource consumption data from the environment-level resource consumption sensors;

collecting the user routine data from a plurality of mobile devices belonging to a plurality of users who frequent the automated environment; and

detecting an aggregate routine for the automated environment based on the user routine data.

5. The method of claim 1, wherein identifying the pattern of resource consumption includes determining a resource consumption profile for an appliance located in the automated environment.

6. The method of claim 5, wherein the resource consumption profile includes an impulse-response model.

7. The method of claim 5, wherein the appliance communicates with the monitoring device to provide information indicating when the appliance is operating.

8. The method of claim 5, further comprising:

receiving, at the monitoring device, user input indicating when the appliance is operating.

9. The method of claim 5, wherein detecting the anomaly includes detecting a discrepancy between the resource consumption profile and the observed resource consumption while the appliance is operating.

10. The method of claim 5, wherein separate resource consumption profiles are determined for each of a plurality of appliances in the automated environment and wherein detecting the anomaly includes:

decomposing resource consumption data for a time period into contributions from the resource consumption profiles for the plurality of appliances and a residual contribution; and

determining whether the residual contribution represents an anomaly.

11. The method of claim 1, wherein detecting the anomaly includes detecting an increase in the observed resource consumption relative to the pattern.

12. The method of claim 1, further comprising:

providing, to the user, additional information about a characteristic of the anomaly, including one or more of a temporal characteristic and/or a size characteristic.

13. The method of claim 1, wherein the anomaly includes a change in a power factor on a power line leading into the automated environment.

14. The method of claim 1, wherein detecting the anomaly includes correlating resource consumption sensor data with data from another sensor in the automated environment.

15. The method of claim 14, wherein the other sensor is an indoor temperature sensor.

16. The method of claim 1, further comprising:

receiving, at the monitoring device, data indicative of a predicted future deviation from the established routine; and

predicting, at the monitor device, a change in the resource consumption behavior resulting from the predicted future deviation.

17. The method of claim 16, further comprising:

when the predicted future deviation from the established routine subsequently occurs, using the predicted change in the resource consumption behavior to detect an anomaly in the resource consumption behavior.

18. The method of claim 1, wherein the automated environment is a home environment.

19. An electronic device comprising:

a communication interface to communicate with one or more sensors in an automated environment; and

a processor coupled to the communication interface and configured to;

identify a pattern of resource consumption for the automated environment, the pattern including a correlation between resource consumption data from the one or more sensors in the automated environment and user routine data indicative of an established routine for one or more users who frequent the automated environment;

detect an anomaly in a resource consumption behavior of the automated environment, wherein the anomaly includes a consumption deviation of an observed resource consumption from the pattern of resource consumption in the automated environment, wherein the consumption deviation is not correlated with a user deviation from the established routine; and

notify at least one of the one or more users of the anomaly.