Electric vehicle disaggregation and detection in whole-house consumption signals

1. A method of electronically detecting and disaggregating a consumption signal associated with the charging of an electric vehicle from a whole-house profile, comprising:

identifying by an electronic processor potential interval candidates of electric vehicle charging, based at least in part upon long and decreasing patterns;

determining by the electronic processor intervals associated with the charging of an electric vehicle, based at least in part on evaluating each potential interval candidate;

determining by the electronic processor an initial point of charging for each interval associated with the charging of an electric vehicle; and

identifying that energy consumption associated with the charging of the electric vehicle occurred, and informing a user of the same.

2. The method of claim 1 , wherein the potential interval candidates are identified using sliding windows of various sizes.

3. The method of claim 1 , wherein identifying potential interval candidates further comprises using optimization techniques selected from the group consisting of: dynamic programming, alpha-beta pruning, and branch-and-bound algorithms.

4. The method of claim 1 , wherein the evaluation of each potential interval candidate comprises fitting each potential interval candidate shape with one or more parametric models.

5. The method of claim 4 , further comprising determining goodness-of-fit of each parametric model to determine if each potential interval candidate represents the charging of an electric vehicle.

6. The method of claim 1 , wherein the evaluation of each potential interval candidate comprises applying a log-linear model to each potential interval candidate.

7. The method of claim 1 , wherein the initial point of charging for each interval associated with the charging of an electric vehicle is determined identifying upward transitions in the whole-house profile.

8. The method of claim 7 , further comprising applying signal processing techniques of smoothing, filtering, and/or change-point detecting.

9. The method of claim 1 , wherein the feedback may be supervised or semi-supervised.

10. The method of claim 1 , wherein the feedback may be received from a user.

11. A method of electronically detecting and disaggregating a consumption signal associated with the charging of an electric vehicle from a whole-house profile, comprising:

identifying by an electronic processor, based at least in part upon long and decreasing patterns, potential interval candidates of electric vehicle charging using sliding windows of various sizes and optimization techniques including dynamic programming, alpha-beta pruning, and/or branch-and-bound algorithms;

determining by the electronic processor intervals associated with the charging of an electric vehicle, based at least in part on evaluating each potential interval candidate by fitting each potential interval candidate shape with one or more parametric models;

determining by the electronic processor an initial point of charging for each interval associated with the charging of an electric vehicle based at least in part upon identifying upward transitions in the whole-house profile and applying signal processing techniques;

receiving feedback from a user of the electric vehicle; and

identifying that energy consumption associated with the charging of the electric vehicle occurred, and informing a user of the same.

12. The method of claim 1 , wherein the parametric models comprise a log-linear model.

13. The method of claim 1 , wherein the signal processing techniques are selected from the group consisting of smoothing, filtering, and change-point detecting.

14. A method of electronically detecting and disaggregating a consumption signal associated with the partial charging of an electric vehicle from a whole-house profile, comprising:

identifying by an electronic processor potential interval candidates of electric vehicle charging, based at least in part upon features characteristic of previously determined electric vehicle charging;

determining by the electronic processor intervals associated with the charging of an electric vehicle, based at least in part on evaluating each potential interval candidate;

determining by the electronic processor an initial point of charging for each interval associated with the charging of an electric vehicle; and

identifying that energy consumption associated with the charging of the electric vehicle occurred, and informing a user of the amount of energy consumption associated with the charging of the electric vehicle.

15. The method of claim 1 , wherein the features characteristic of previously determined electric vehicle charging may be selected from the group consisting of: amplitude interval candidates, duration of interval candidates, and time-of-day of interval candidates.

16. A system for detecting and disaggregating a consumption signal associated with the charging of an electric vehicle from a whole-house profile, comprising:

a candidate search module, configured to identify potential interval candidates of electric vehicle charging, based at least in part upon long and decreasing patterns;

a parametric fitting module, configured to determine intervals associated with the charging of an electric vehicle, based at least in part on evaluating each potential interval candidate by fitting each potential interval candidate shape with one or more parametric models;

an initial point detection module, configured to determine an initial point of charging for each interval associated with the charging of an electric vehicle; and

a feedback module, configured to receive feedback associated with detected signals.

17. The system of claim 16 , wherein the candidate search module utilizes sliding windows of various sizes and optimization techniques including dynamic programming, alpha-beta pruning, and/or branch-and-bound algorithms.

18. The system of claim 16 , wherein the initial point detection module determines initial points based at least in part upon identifying upward transitions in the whole-house profile and applying signal processing techniques.

19. The system of claim 16 , wherein the feedback module receives supervised and semi-supervised feedback.

20. A method of electronically detecting and disaggregating a consumption signal associated with the charging of an electric vehicle from a whole-house profile, comprising:

identifying by an electronic processor potential interval candidates of electric vehicle charging, based at least in part upon identifying box-shaped energy usage patterns;

determining by the electronic processor intervals associated with the charging of an electric vehicle, based at least in part on evaluating each potential interval candidate against factors including amplitude, duration, and time-of-day; and

identifying that energy consumption associated with the charging of the electric vehicle occurred, and informing a user of the amount of energy consumption associated with the charging of the electric vehicle.

21. The method of claim 20 , further comprising:

determining certain household appliances within the home an disaggregating energy usage associated with such certain household appliances; and

wherein the step of determining intervals associated with the charging of an electric vehicle further comprises eliminating from potential interval candidates candidate who are have profiles associated with certain household appliances.

22. The method of claim 21 , wherein certain household appliances within the home are determined based upon non-intrusive load monitoring.

23. The method of claim 21 , wherein the certain household appliances within the home are determined based information provided by a user.

24. The method of claim 21 , wherein the certain household appliances may be selected from the group consisting of: refrigerator, pool pump, sump pump, and heating, ventilation, and air-conditioning (HVAC) unit.