Cognitive electric power meter
View Patent ↗An electric power meter includes an embedded decomposition module that is configured to decompose a power meter signal into constituent loads to segregate and identify energy consumption associated with each individual energy consumption device within a plurality of energy consumption devices coupled to the power meter.
1. An electric power meter comprising:
at least one sensor configured to measure at least one desired energy consumption variable associated with a plurality of energy consumption devices, and to generate at least one output signal therefrom; and
a decomposition module configured to decompose the at least one output signal into constituent individual loads and therefrom identify energy consumption corresponding to each energy consumption device within the plurality of energy consumption devices,
wherein the decomposition module comprises a cognitive decomposition algorithm configured to store knowledge and learn, continuously adapting to changes in household power line characteristics to improve power line monitoring and energy consumption device control capabilities,
and further wherein the decomposition algorithm employs invariant representation and associative processing to implement its learning.
2. The electric power meter according to claim 1 , wherein the at least one sensor is selected from a current sensor, a voltage sensor, a temperature sensor, an activity sensor, and an acoustic sensor.
3. The electric power meter according to claim 1 , further comprising a communication interface configured for receiving user commands and queries and for transmitting decomposition results.
4. The electric power meter according to claim 3 , wherein the communication interface is selected from wired and wireless communication technologies.
5. The electric power meter according to claim 3 , wherein the communication interface is selected from RSb232, USB, Firewire, Ethernet, Zigbee, Wifi, Bluetooth, RFJID, wireless USB, cellular, and WMAN communication technologies.
6. The electric power meter according to claim 1 , wherein the decomposition module is further configured to perform a cognitive cycle to a) determine the instantaneous state of a power line, b) perform grid scene analysis based on the instantaneous state to identify individual and combined load signatures of power consuming devices coupled to the power line, c) predict future power grid behavior of individual and combined power consuming devices coupled to the power line, d) create a decision about the state of the power line based on the future power grid behavior, and e) perform a desired energy preservation act based on the decision.
7. The electric power meter according to claim 1 , wherein the decomposition algorithm uses a Bayesian-inference based classifier configured to identify energy consumption devices on a household power line.
8. The electric power meter according to claim 1 , further comprising a communication interface configured to communicate directly with smart appliances over a power line carrier or a wireless communication link.
9. The electric power meter according to claim 1 , wherein the decomposition module is integrated into a revenue metering portion of the electric power meter to form a portion of an intelligent billing system within the electric power meter.
10. The electric power meter according to claim 9 , wherein the intelligent billing system is configured to link washing, air conditioning and dishwashing activities to time of use pricing based on data generated by the decomposition module.
11. The electric power meter according to claim 9 , wherein the intelligent billing system is configured to identify an appliance that is using more energy than the national average energy usage for the appliance based on data generated by the decomposition module.
12. The electric power meter according to claim 9 , wherein the intelligent billing system is configured to identify a wiring flaw within a home using the electric power meter based on data generated by the decomposition module.
13. An electric power meter comprising:
at least one sensor configured to measure at least one desired energy consumption variable associated with a plurality of energy consumption devices, and to generate at least one output signal therefrom; and
a decomposition module configured to decompose the at least one output signal into constituent individual loads and therefrom identify energy consumption corresponding to each energy consumption device within the plurality of energy consumption devices,
wherein the decomposition module comprises a cognitive decomposition algorithm configured to store knowledge and learn, continuously adapting to changes in household power line characteristics to improve power line monitoring and energy consumption device control capabilities,
and further wherein the decomposition algorithm is aggregated in a multidimensional associative array that is segmented based on the particular element of the cognitive cycle it supports.
14. The electric power meter according to claim 13 , wherein the at least one sensor is selected from a current sensor, a voltage sensor, a temperature sensor, an activity sensor, and an acoustic sensor.
15. The electric power meter according to claim 13 , further comprising a communication interface configured for receiving user commands and queries and for transmitting decomposition results.
16. The electric power meter according to claim 15 , wherein the communication interface is selected from wired and wireless communication technologies.
17. The electric power meter according to claim 15 , wherein the communication interface is selected from RSb232, USB, Firewire, Ethernet, Zigbee, Wifi, Bluetooth, RFJID, wireless USB, cellular, and WMAN communication technologies.
18. The electric power meter according to claim 13 , wherein the decomposition module is further configured to perform a cognitive cycle to a) determine the instantaneous state of a power line, b) perform grid scene analysis based on the instantaneous state to identify individual and combined load signatures of power consuming devices coupled to the power line, c) predict future power grid behavior of individual and combined power consuming devices coupled to the power line, d) create a decision about the state of the power line based on the future power grid behavior, and e) perform a desired energy preservation act based on the decision.
19. The electric power meter according to claim 13 , wherein the decomposition algorithm uses a Bayesian-inference based classifier configured to identify energy consumption devices on a household power line.
20. An electric power meter comprising:
at least one sensor configured to measure at least one desired energy consumption variable associated with a plurality of energy consumption devices, and to generate at least one output signal therefrom; and
a decomposition module configured to decompose the at least one output signal into constituent individual loads and therefrom identify energy consumption corresponding to each energy consumption device within the plurality of energy consumption devices, wherein the decomposition module comprises a cognitive decomposition algorithm configured to identify, without requiring field training, energy consumption devices on a household power line.
21. The electric power meter according to claim 20 , wherein the at least one sensor is selected from a current sensor, a voltage sensor, a temperature sensor, an activity sensor, and an acoustic sensor.
22. The electric power meter according to claim 20 , further comprising a communication interface configured for receiving user commands and queries and for transmitting decomposition results.
23. The electric power meter according to claim 22 , wherein the communication interface is selected from wired and wireless communication technologies.
24. The electric power meter according to claim 22 , wherein the communication interface is selected from RS232, USB, Firewire, Ethernet, Zigbee, Wifi, Bluetooth, RFJID, wireless USB, cellular, and WMAN communication technologies.
25. The electric power meter according to claim 20 , wherein the decomposition module is further configured to perform a cognitive cycle to a) determine the instantaneous state of a power line, b) perform grid scene analysis based on the instantaneous state to identify individual and combined load signatures of power consuming devices coupled to the power line, c) predict future power grid behavior of individual and combined power consuming devices coupled to the power line, d) create a decision about the state of the power line based on the future power grid behavior, and e) perform a desired energy preservation act based on the decision.
26. The electric power meter according to claim 20 , wherein the decomposition algorithm uses a Bayesian-inference based classifier configured to identify energy consumption devices on a household power line.
27. A method of decomposing a household power meter signal, the method comprising:
measuring a household meter power line signal;
decomposing within the household power meter, the power line signal into constituent individual loads; and
identifying within the household power meter, energy consumption corresponding to each individual load within a plurality of loads that operate together to generate the household meter power line signal;
storing knowledge and learning, based on the measuring, decomposing and identifying, and continuously adapting to changes in household power line characteristics to improve power line monitoring and energy consumption device control capabilities, wherein the learning is based on invariant representation and associative processing techniques.
28. The method according to claim 27 , wherein decomposing the power line signal into constituent individual loads comprises:
determining the instantaneous state of the power line; and
performing grid scene analysis based on the instantaneous state to identify individual and combined load signatures of power consuming devices coupled to the power line.
29. The method according to claim 27 , wherein identifying energy consumption corresponding to each individual load within a plurality of loads comprises:
predicting future power grid behavior of individual and combined power consuming devices coupled to the power line;
creating a decision about the state of the power line based on the future power grid behavior; and
performing a desired energy preservation act based on the decision.
30. The method according to claim 27 , wherein the measuring, decomposing and identifying comprises configuring a Bayesian-inference based classifier to identify energy consumption devices on the household power line.
31. The method according to claim 27 , further comprising communicating directly with smart appliances over a power line carrier or a wireless communication link to identify individual smart appliances contributing to the household meter power line signal.
32. The method according to claim 27 , further comprising identifying within a revenue metering portion of the household power meter, energy consumption corresponding to each individual load within a plurality of loads, to form a portion of an intelligent billing system within the electric power meter.
33. The method according to claim 32 , further comprising linking washing, air conditioning and dishwashing activities to time of use pricing based on data generated by the revenue metering portion of the household power meter.
34. The method according to claim 32 , further comprising identifying an appliance that is using more energy than the national average energy usage for the appliance based on data generated by the revenue metering portion of the household power meter.
35. The method according to claim 32 , further comprising identifying a wiring flaw within a home using the electric power meter based on data generated by the revenue metering portion of the household power meter.
36. A method of decomposing a household power meter signal, the method comprising:
measuring a household meter power line signal;
decomposing within the household power meter, the power line signal into constituent individual loads; and
identifying within the household power meter, energy consumption corresponding to each individual load within a plurality of loads that operate together to generate the household meter power line signal; and
storing knowledge and learning, based on the measuring, decomposing and identifying, and continuously adapting to changes in household power line characteristics to improve power line monitoring and energy consumption device control capabilities, wherein storing knowledge comprises aggregating a multidimensional associative array that is segmented based on a particular element of a desired cognitive cycle.
37. The method according to claim 36 , wherein decomposing the power line signal into constituent individual loads comprises:
determining the instantaneous state of the power line; and
performing grid scene analysis based on the instantaneous state to identify individual and combined load signatures of power consuming devices coupled to the power line.
38. The method according to claim 36 , wherein identifying energy consumption corresponding to each individual load within a plurality of loads comprises:
predicting future power grid behavior of individual and combined power consuming devices coupled to the power line;
creating a decision about the state of the power line based on the future power grid behavior; and
performing a desired energy preservation act based on the decision.
39. The method according to claim 36 , wherein the measuring, decomposing and identifying comprises configuring a Bayesian-inference based classifier to identify energy consumption devices on the household power line.
40. The method according to claim 36 , further comprising communicating directly with smart appliances over a power line carrier or a wireless communication link to identify individual smart appliances contributing to the household meter power line signal.
41. The method according to claim 36 , further comprising identifying within a revenue metering portion of the household power meter, energy consumption corresponding to each individual load within a plurality of loads, to form a portion of an intelligent billing system within the electric power meter.
42. The method according to claim 41 , further comprising linking washing, air conditioning and dishwashing activities to time of use pricing based on data generated by the revenue metering portion of the household power meter.
43. The method according to claim 41 , further comprising identifying an appliance that is using more energy than the national average energy usage for the appliance based on data generated by the revenue metering portion of the household power meter.
44. The method according to claim 41 , further comprising identifying a wiring flaw within a home using the electric power meter based on data generated by the revenue metering portion of the household power meter.
45. A method of decomposing a household power meter signal, the method comprising:
measuring a household meter power line signal;
decomposing within the household power meter, the power line signal into constituent individual loads; and
identifying within the household power meter, energy consumption corresponding to each individual load within a plurality of loads that operate together to generate the household meter power line signal, wherein the identifying comprises identifying, without requiring field training, energy consumption devices on a household power line.
46. The method according to claim 45 , wherein decomposing the power line signal into constituent individual loads comprises:
determining the instantaneous state of the power line; and
performing grid scene analysis based on the instantaneous state to identify individual and combined load signatures of power consuming devices coupled to the power line.
47. The method according to claim 45 , wherein identifying energy consumption corresponding to each individual load within a plurality of loads comprises:
predicting future power grid behavior of individual and combined power consuming devices coupled to the power line;
creating a decision about the state of the power line based on the future power grid behavior; and
performing a desired energy preservation act based on the decision.
48. The method according to claim 45 , wherein the measuring, decomposing and identifying comprises configuring a Bayesian-inference based classifier to identify energy consumption devices on the household power line.
49. The method according to claim 45 , further comprising communicating directly with smart appliances over a power line carrier or a wireless communication link to identify individual smart appliances contributing to the household meter power line signal.
50. The method according to claim 45 , further comprising identifying within a revenue metering portion of the household power meter, energy consumption corresponding to each individual load within a plurality of loads, to form a portion of an intelligent billing system within the electric power meter.
51. The method according to claim 50 , further comprising linking washing, air conditioning and dishwashing activities to time of use pricing based on data generated by the revenue metering portion of the household power meter.
52. The method according to claim 50 , further comprising identifying an appliance that is using more energy than the national average energy usage for the appliance based on data generated by the revenue metering portion of the household power meter.
53. The method according to claim 50 , further comprising identifying a wiring flaw within a home using the electric power meter based on data generated by the revenue metering portion of the household power meter.
54. An electric power meter comprising an embedded decomposition module configured for decomposing a power signal into constituent loads to segregate and identify energy consumption associated with each individual energy consumption device within a plurality of energy consumption devices, wherein the decomposition module comprises a cognitive decomposition algorithm configured to store knowledge and learn, continuously adapting to changes in household power line characteristics to improve power line monitoring and energy consumption device control capabilities, wherein the decomposition algorithm comprises invariant representation and associative processing to implement its learning.
55. The electric power meter according to claim 54 , wherein the cognitive decomposition algorithm is configured to perform a cognitive cycle that a) determines the instantaneous state of a power line, b) performs grid scene analysis based on the instantaneous state to identify individual and combined load signatures of power consuming devices coupled to the power line, c) predicts future power grid behavior of individual and combined power consuming devices coupled to the power line, d) creates a decision about the state of the power line based on the future power grid behavior, and e) performs a desired energy preservation act based on the decision.
56. The electric power meter according to claim 54 , wherein the cognitive decomposition algorithm uses a Bayesian-inference based classifier configured to identify energy consumption devices on a household power line.
57. The electric power meter according to claim 54 , further comprising a communication interface configured to communicate directly with smart appliances over a power line carrier or a wireless communication link.
58. The electric power meter according to claim 54 , wherein the decomposition module is integrated into a revenue metering portion of the electric power meter to form a portion of an intelligent billing system within the electric power meter.
59. The electric power meter according to claim 58 , wherein the revenue metering portion is configured to link washing, air conditioning and dishwashing activities to time of use pricing based on data generated by the decomposition module.
60. The electric power meter according to claim 58 , wherein the revenue metering portion is configured to identify an appliance that is using more energy than the national average energy usage for the appliance based on data generated by the decomposition module.
61. The electric power meter according to claim 58 , wherein the revenue metering portion is configured to identify a wiring flaw within a home using the electric power meter based on data generated by the decomposition module.
62. An electric power meter comprising an embedded decomposition module configured for decomposing a power signal into constituent loads to segregate and identify energy consumption associated with each individual energy consumption device within a plurality of energy consumption devices, wherein the decomposition module comprises a cognitive decomposition algorithm configured to store knowledge and learn, continuously adapting to changes in household power line characteristics to improve power line monitoring and energy consumption device control capabilities, wherein the decomposition algorithm is aggregated in a multidimensional associative array that is segmented based on the particular element of the cognitive cycle it supports.
63. The electric power meter according to claim 62 , wherein the cognitive decomposition algorithm is configured to perform a cognitive cycle that a) determines the instantaneous state of a power line, b) performs grid scene analysis based on the instantaneous state to identify individual and combined load signatures of power consuming devices coupled to the power line, c) predicts future power grid behavior of individual and combined power consuming devices coupled to the power line, d) creates a decision about the state of the power line based on the future power grid behavior, and e) performs a desired energy preservation act based on the decision.
64. The electric power meter according to claim 62 , wherein the cognitive decomposition algorithm uses a Bayesian-inference based classifier configured to identify energy consumption devices on a household power line.
65. The electric power meter according to claim 62 , further comprising a communication interface configured to communicate directly with smart appliances over a power line carrier or a wireless communication link.
66. The electric power meter according to claim 62 , wherein the decomposition module is integrated into a revenue metering portion of the electric power meter to form a portion of an intelligent billing system within the electric power meter.
67. The electric power meter according to claim 65 , wherein the revenue metering portion is configured to link washing, air conditioning and dishwashing activities to time of use pricing based on data generated by the decomposition module.
68. The electric power meter according to claim 65 , wherein the revenue metering portion is configured to identify an appliance that is using more energy than the national average energy usage for the appliance based on data generated by the decomposition module.
69. The electric power meter according to claim 65 , wherein the revenue metering portion is configured to identify a wiring flaw within a home using the electric power meter based on data generated by the decomposition module.
70. An electric power meter comprising an embedded decomposition module configured for decomposing a power signal into constituent loads to segregate and identify energy consumption associated with each individual energy consumption device within a plurality of energy consumption devices, wherein the decomposition module comprises a cognitive decomposition algorithm configured to identify, without requiring field training, energy consumption devices on a household power line.
71. The electric power meter according to claim 70 , wherein the cognitive decomposition algorithm is configured to perform a cognitive cycle that a) determines the instantaneous state of a power line, b) performs grid scene analysis based on the instantaneous state to identify individual and combined load signatures of power consuming devices coupled to the power line, c) predicts future power grid behavior of individual and combined power consuming devices coupled to the power line, d) creates a decision about the state of the power line based on the future power grid behavior, and e) performs a desired energy preservation act based on the decision.
72. The electric power meter according to claim 70 , wherein the cognitive decomposition algorithm uses a Bayesian-inference based classifier configured to identify energy consumption devices on a household power line.
73. The electric power meter according to claim 70 , further comprising a communication interface configured to communicate directly with smart appliances over a power line carrier or a wireless communication link.
74. The electric power meter according to claim 70 , wherein the decomposition module is integrated into a revenue metering portion of the electric power meter to form a portion of an intelligent billing system within the electric power meter.
75. The electric power meter according to claim 74 , wherein the revenue metering portion is configured to link washing, air conditioning and dishwashing activities to time of use pricing based on data generated by the decomposition module.
76. The electric power meter according to claim 74 , wherein the revenue metering portion is configured to identify an appliance that is using more energy than the national average energy usage for the appliance based on data generated by the decomposition module.
77. The electric power meter according to claim 74 , wherein the revenue metering portion is configured to identify a wiring flaw within a home using the electric power meter based on data generated by the decomposition module.