System and method for electric load recognition from centrally monitored power signal and its application to home energy management
First Claim
1. A computer-implemented method for load recognition from a monitored signal and application to energy management service, comprising the steps of:
- extracting, by a feature extraction algorithm processor, features from a set of power data using a feature extraction algorithm to obtain a plurality of events, wherein the set of power data reflects power consumed by one or more loads;
initializing, by an initializing processor, a load library repository with initial load instance data, the initial load instance data comprising;
initial estimates of state probabilities and state transition probabilities that represent a plurality of loads;
performing a load recognition algorithm, by a load recognition algorithm processor, said load recognition algorithm comprising the steps of;
for an event x from said plurality of events;
assigning, by an assigning processor, said event x and particular subsequent events to a particular load,wherein the assigning is based on said particular load giving a best posterior probability from a best posterior probability algorithm performed on said plurality of events, andwherein said assigning is performed after performing a search and classification algorithm on said plurality of events; and
adding, by an adding processor, load instance data associated with said particular load to said load library repository and continuing the adding load instance data for a next available event from said plurality of events; and
updating based on said adding of load instance data, by an updating processor, said load library repository with new state probabilities and state transition probabilities,repeating said load recognition algorithm using the updated load library repository until a particular criterion is met; and
using, by an energy management service processor, said added load instance data in providing energy consuming feedback and usage analysis to be used for energy management service;
wherein said updated load library repository is used in a continuous mode on a continuous stream of power data from the plurality of loads and wherein when said added load instance data is added, combining said added load instance data with said initial load instance data to compute said new state probabilities and state transition probabilities from said combination;
said continuous mode further comprising the steps of;
extracting in real time, by said feature extraction algorithm, features from a window of said stream of power data for eligible events of said plurality of events in said window, performing a roughly estimated assignment to the particular load based on a state and state transition probability of each eligible event only;
if there are not enough subsequent events for each roughly assigned event from said window and past windows of power data, then return to said extracting in real time step, otherwise;
performing load recognition, by said load recognition algorithm, to a roughly assigned event with enough subsequent events based on a highest posterior probability search and classification and creating load instance recognition data;
marking, by a marking processor, said roughly assigned event with said enough subsequent events as used;
adding, by said adding processor, said load instance recognition data to said load library repository;
updating based on the added load instance recognition, by said updating processor, state and state transition probability estimates for said particular load data; and
with the arrival of a new window of power data, repeating said steps beginning from said step of extracting in real time features from said window of stream of power data;
wherein said plurality of loads comprise a plurality of appliances.
0 Assignments
0 Petitions
Accused Products
Abstract
A method and apparatus are provided for a home energy management platform. The platform includes using a whole house power sensor or subset thereof. Data from the power sensor are analyzed using advanced statistical and machine learning techniques for extracting detailed usage information and generating specific energy saving measures, among other relevant information. In an embodiment, a gateway console is provided that has various communication capabilities. The gateway console may communicate with and control HAN devices. The gateway console may collect data from the power sensor as well as HAN devices and upload such collected data to servers for the analysis processing. Certain amounts of data processing and analysis may be performed at a server or at the local level, such as at the power sensor, gateway, or other HAN device, as well. The platform may include a user interface, such as web, mobile, email, mail, phone call, etc.
-
Citations
17 Claims
-
1. A computer-implemented method for load recognition from a monitored signal and application to energy management service, comprising the steps of:
-
extracting, by a feature extraction algorithm processor, features from a set of power data using a feature extraction algorithm to obtain a plurality of events, wherein the set of power data reflects power consumed by one or more loads; initializing, by an initializing processor, a load library repository with initial load instance data, the initial load instance data comprising;
initial estimates of state probabilities and state transition probabilities that represent a plurality of loads;performing a load recognition algorithm, by a load recognition algorithm processor, said load recognition algorithm comprising the steps of; for an event x from said plurality of events; assigning, by an assigning processor, said event x and particular subsequent events to a particular load, wherein the assigning is based on said particular load giving a best posterior probability from a best posterior probability algorithm performed on said plurality of events, and wherein said assigning is performed after performing a search and classification algorithm on said plurality of events; and adding, by an adding processor, load instance data associated with said particular load to said load library repository and continuing the adding load instance data for a next available event from said plurality of events; and updating based on said adding of load instance data, by an updating processor, said load library repository with new state probabilities and state transition probabilities, repeating said load recognition algorithm using the updated load library repository until a particular criterion is met; and using, by an energy management service processor, said added load instance data in providing energy consuming feedback and usage analysis to be used for energy management service; wherein said updated load library repository is used in a continuous mode on a continuous stream of power data from the plurality of loads and wherein when said added load instance data is added, combining said added load instance data with said initial load instance data to compute said new state probabilities and state transition probabilities from said combination; said continuous mode further comprising the steps of; extracting in real time, by said feature extraction algorithm, features from a window of said stream of power data for eligible events of said plurality of events in said window, performing a roughly estimated assignment to the particular load based on a state and state transition probability of each eligible event only; if there are not enough subsequent events for each roughly assigned event from said window and past windows of power data, then return to said extracting in real time step, otherwise; performing load recognition, by said load recognition algorithm, to a roughly assigned event with enough subsequent events based on a highest posterior probability search and classification and creating load instance recognition data; marking, by a marking processor, said roughly assigned event with said enough subsequent events as used; adding, by said adding processor, said load instance recognition data to said load library repository; updating based on the added load instance recognition, by said updating processor, state and state transition probability estimates for said particular load data; and with the arrival of a new window of power data, repeating said steps beginning from said step of extracting in real time features from said window of stream of power data; wherein said plurality of loads comprise a plurality of appliances. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14)
-
-
15. A system for load recognition from a monitored signal and application to energy management service, comprising:
-
a feature extraction algorithm processor configured for extracting features from a set of power data using a feature extraction algorithm to obtain a plurality of events, wherein the set of power data reflects power consumed by one or more loads; an initializing processor configured for initializing a load library repository with initial load instance data, the initial load instance data comprising;
initial estimates of state probabilities and state transition probabilities that represent a plurality of loads;a load recognition algorithm processor configured for performing a load recognition algorithm, comprising the steps of; for an event x from said plurality of events; assigning, by an assigning processor, said event x and particular subsequent events to a particular load, wherein the assigning is based on said particular load giving a best posterior probability from a best posterior probability algorithm performed on said plurality of events, and wherein said assigning is performed after performing a search and classification algorithm on said plurality of events; and adding, by an adding processor, load instance data associated with said particular load to said load library repository and continuing the adding load instance data for a next available event from said plurality of events; and updating based on said adding of load instance data, by an updating processor, said load library repository with new state probabilities and state transition probabilities, repeating said load recognition algorithm using the updated load library repository until a particular criterion is met; and using, by an energy management service processor, said added load instance data in providing energy consuming feedback and usage analysis to be used for energy management service; wherein said updated load library repository is used in a continuous mode on a continuous stream of power data from the plurality of loads and wherein when said added load instance data is added, combining said added load instance data with said initial load instance data to compute said new state probabilities and state transition probabilities from said combination; said continuous mode further comprising the steps of; extracting in real time, by said feature extraction algorithm, features from a window of said stream of power data for eligible events of said plurality of events in said window, performing a roughly estimated assignment to the particular load based on a state and state transition probability of each eligible event only; if there are not enough subsequent events for each roughly assigned event from said window and past windows of power data, then return to said extracting in real time step, otherwise; performing load recognition, by said load recognition algorithm, to a roughly assigned event with enough subsequent events based on a highest posterior probability search and classification and creating load instance recognition data; marking, by a marking processor, said roughly assigned event with said enough subsequent events as used; adding, by said adding processor, said load instance recognition data to said load library repository; updating based on the added load instance recognition, by said updating processor, state and state transition probability estimates for said particular load data; and with the arrival of a new window of power data, repeating said steps beginning from said step of extracting in real time features from said window of stream of power data; wherein said plurality of loads comprise a plurality of appliances.
-
-
16. A non-transitory machine-readable storage medium storing one or more sequences of instructions for load recognition from a monitored signal and application to energy management service, which instructions, when executed by one or more processors, cause the one or more processors to carry out the steps of:
-
extracting, by a feature extraction algorithm processor, features from a set of power data using a feature extraction algorithm to obtain a plurality of events, wherein the set of power data reflects power consumed by one or more loads; initializing, by an initializing processor, a load library repository with initial load instance data, the initial load instance data comprising;
initial estimates of state probabilities and state transition probabilities that represent a plurality of loads;performing a load recognition algorithm, by a load recognition algorithm processor, said load recognition algorithm comprising the steps of; for an event x from said plurality of events; assigning, by an assigning processor, said event x and particular subsequent events to a particular load, wherein the assigning is based on said particular load giving a best posterior probability from a best posterior probability algorithm performed on said plurality of events, and wherein said assigning is performed after performing a search and classification algorithm on said plurality of events; and adding, by an adding processor, load instance data associated with said particular load to said load library repository and continuing the adding load instance data for a next available event from said plurality of events; and updating based on said adding of load instance data, by an updating processor, said load library repository with new state probabilities and state transition probabilities, repeating said load recognition algorithm using the updated load library repository until a particular criterion is met; and using, by an energy management service processor, said added load instance data in providing energy consuming feedback and usage analysis to be used for energy management service; wherein said updated load library repository is used in a continuous mode on a continuous stream of power data from the plurality of loads and wherein when said added load instance data is added, combining said added load instance data with said initial load instance data to compute said new state probabilities and state transition probabilities from said combination; said continuous mode further comprising the steps of; extracting in real time, by said feature extraction algorithm, features from a window of said stream of power data for eligible events of said plurality of events in said window, performing a roughly estimated assignment to the particular load based on a state and state transition probability of each eligible event only; if there are not enough subsequent events for each roughly assigned event from said window and past windows of power data, then return to said extracting in real time step, otherwise; performing load recognition, by said load recognition algorithm, to a roughly assigned event with enough subsequent events based on a highest posterior probability search and classification and creating load instance recognition data; marking, by a marking processor, said roughly assigned event with said enough subsequent events as used; adding, by said adding processor, said load instance recognition data to said load library repository; updating based on the added load instance recognition, by said updating processor, state and state transition probability estimates for said particular load data; and with the arrival of a new window of power data, repeating said steps beginning from said step of extracting in real time features from said window of stream of power data; wherein said plurality of loads comprise a plurality of appliances.
-
-
17. A computer implemented method for searching and for classifying events for load recognition, comprising the steps of:
iterating over available events; for a given event x of said available events, searching, by a searching processor, possible state transition sequences for a load i, wherein subsequent events after said given event x are considered in finding the state transition sequences for said load, wherein said given event x and said subsequent events are referred to collectively as vector x, and; pruning, by a pruning processor, impossible state transition sequences from a particular search stack, based on state or based on state transition probability for a particular time limit and until possible state sequences are found; computing, by a computing processor, a likelihood xi, for candidates and choosing a state sequence with a maximum xi; computing a posterior probability of said load i, for said vector x, wherein the posterior probability of load i is a product of likelihood and prior probability and p(x) is a normalization factor according to;
Specification