Methods and system for nonintrusive load monitoring
First Claim
Patent Images
1. A method for nonintrusive monitoring of electrical energy usage by a plurality of electrical loads at a premise to which electrical power is supplied via a common feed, comprising:
- clustering, using at least one processor, tuples of power changes in the electrical energy usage at the premise that are attributable to a same load of the plurality of electrical loads at the premise, wherein the clustering comprises analyzing power changes in the electrical energy usage based on usage statistics for the plurality of electrical loads to identify power changes attributable to the same load;
calculating, using the at least one processor, a degree of similarity between clusters of tuples of power changes based at least in part on times associated with power changes in the clusters;
merging, using the at least one processor, clusters of tuples of power changes having a degree of similarity above a threshold;
updating, using the at least one processor, the usage statistics to estimate times different loads of the plurality of electrical loads are in different states; and
based on the updated usage statistics, processing, using the at least one processor, real-time power-change measurements to develop real-time load state information based on detected power changes in the electrical energy usage.
1 Assignment
0 Petitions
Accused Products
Abstract
Identification and tracking of major electric appliances by using aggregate power data obtained at the main breaker level of a residence or commercial establishment. Step power changes and power surges characterize appliances. These features are identified and the time of use and duration statistics are considered to match an observed sequence of power changes with the appliances being turned on and off. The time-dependent usage of appliances and their power consumption are then reconstructed.
-
Citations
10 Claims
-
1. A method for nonintrusive monitoring of electrical energy usage by a plurality of electrical loads at a premise to which electrical power is supplied via a common feed, comprising:
-
clustering, using at least one processor, tuples of power changes in the electrical energy usage at the premise that are attributable to a same load of the plurality of electrical loads at the premise, wherein the clustering comprises analyzing power changes in the electrical energy usage based on usage statistics for the plurality of electrical loads to identify power changes attributable to the same load; calculating, using the at least one processor, a degree of similarity between clusters of tuples of power changes based at least in part on times associated with power changes in the clusters; merging, using the at least one processor, clusters of tuples of power changes having a degree of similarity above a threshold; updating, using the at least one processor, the usage statistics to estimate times different loads of the plurality of electrical loads are in different states; and based on the updated usage statistics, processing, using the at least one processor, real-time power-change measurements to develop real-time load state information based on detected power changes in the electrical energy usage. - View Dependent Claims (2, 3, 4, 10)
-
-
5. A method for nonintrusive monitoring of electrical energy usage by a plurality of electrical loads at a premise to which electrical power is supplied via a common feed, comprising:
-
a. via a sensor, providing a sensor output signal indicative of power delivered through the feed over a first time interval; b. monitoring, using at least one processor, the sensor output signal to detect positive and negative changes of power, power surge amplitudes and durations; c. clustering, using the at least one processor, negative changes of power, wherein clustering negative changes in power comprises; clustering, using the at least one processor, tuples of power changes in the electrical energy usage at the premise that are attributable to a same load of the plurality of electrical loads at the premise, wherein the clustering comprises analyzing power changes in the electrical energy usage based on usage statistics for the plurality of electrical loads to identify power changes attributable to the same load; calculating, using the at least one processor, a degree of similarity between clusters of tuples of power changes based at least in part on times associated with power changes in the clusters; and merging, using the at least one processor, clusters of tuples of power changes having a degree of similarity above a threshold; d. matching, using the at least one processor, negative and positive changes of power; e. estimating, using the at least one processor, times loads were turned on and turned off during a second time interval; and f. statistically, using the at least one processor, characterizing the operation of at least one of said loads. - View Dependent Claims (6, 7, 8)
-
-
9. A system for nonintrusive monitoring of electrical energy usage by a plurality of electrical loads at a premise to which electrical power is supplied via a common feed, comprising:
-
a. a power sensor configured and arranged to monitor aggregate power consumed at the premise; b. means for detecting changes in the monitored power; and c. a processor executing stored program instructions to disambiguate the detected power changes and associate them with individual loads by clustering power changes and, by means of a Viterbi algorithm, matching clusters to identify power changes associated with individual loads, wherein clustering the power changes comprises; clustering tuples of power changes in the electrical energy usage at the premise that are attributable to a same load of the plurality of electrical loads at the premise, wherein the clustering comprises analyzing power changes in the electrical energy usage based on usage statistics for the plurality of electrical loads to identify power changes attributable to the same load; calculating a degree of similarity between clusters of tuples of power changes based at least in part on times associated with power changes in the clusters; and merging clusters of tuples of power changes having a degree of similarity above a threshold.
-
Specification