Methods and apparatuses for monitoring energy consumption and related operations
OwnerMario E. Berges Gonzalez, Ethan J. Goldman +5inventors
InventorsMario E. Berges Gonzalez, Ethan J. Goldman, Luciio Soibelman, Burton W. Andrews, Diego S. Benitez Meijia, H. Scott Matthews, Michael Hoynck
Life of this patent
Estimating the term…
Abstract
Apparatus and method including acquiring a signal indicative of power consumption; detecting a transient in the signal; extracting a feature indicative of the transient, wherein extracting the feature includes: fitting a plurality of models to the transient, selecting one of the plurality of models as a model for the transient, and defining the feature indicative of the transient based on at least one parameter of the model for the transient; and classifying the transient based on the feature.
Claims23
A method, comprising:
- acquiring (50) a signal indicative of power consumption;
- detecting (52) a transient in the signal;
- extracting (54) a feature indicative of the transient, wherein extracting the feature includes:
- fitting (60) a plurality of models to the transient;
- selecting (62) one of the plurality of models as a model for the transient;
- defining (64) the feature indicative of the transient based on at least one parameter of the model for the transient;
- and
- classifying (56) the transient based on the feature.
A system (10), comprising:
- a sensor (20);
- an input device (16);
- an output device (18);
- a processor (12);
- computer-readable memory (14) including computer-readable instructions which, when executed by the processor (12), cause the processor (12) to perform the steps of:
- acquiring (50) a signal indicative of power consumption;
- detecting (52) a transient in the signal;
- extracting (54) a feature indicative of the transient, wherein extracting the feature includes:
- fitting (60) a plurality of models to the transient;
- selecting (62) one of the plurality of models as a model for the transient;
- defining (64) the feature indicative of the transient based on at least one parameter of the model for the transient;
- and
- classifying (56) the transient based on the feature.
Dependencies are inferred from the claim text.