Load power device and system for real-time execution of hierarchical load identification algorithms

• US 9,819,226 B2
• Filed: 12/01/2014
• Issued: 11/14/2017
• Est. Priority Date: 12/01/2014
• Status: Active Grant

• Current Assignee: Eaton Intelligent Power Limited (Eaton Corporation PLC.)
• Original Assignee: Eaton Corp. (Wisconsin) (Eaton Corporation PLC.)
• Inventors: Yang, Yi, Madane, Mayura Arun, Zambare, Prachi Suresh
• Primary Examiner(s): Johnson, Ryan
• Application Number:
  US14/556,515
• Publication Number:
  US 20160156225A1
• Time in Patent Office: 1,079 Days
• CPC Class Codes: G01R 19/2513 Arrangements for monitoring electric power systems, e.g. power lines or loads; Logging
• CPC Class Codes: G01R 21/06 by measuring current and voltage G01R21/08 - G01R21/133 take precedence
• CPC Class Codes: H02J 13/00002 characterised by monitoring
• CPC Class Codes: H02J 13/00022 using wireless data transmission
• CPC Class Codes: H02J 3/00 Circuit arrangements for ac mains or ac distribution networks
• CPC Class Codes: Y02B 70/30 Systems integrating technologies related to power network operation and communication or information technologies for improving the carbon footprint of the management of residential or tertiary loads, i.e. smart grids as climate change mitigation technology in the buildings sector, including also the last stages of power distribution and the control, monitoring or operating management systems at local level
• CPC Class Codes: Y02B 70/3225 Demand response systems, e.g. load shedding, peak shaving
• CPC Class Codes: Y02B 90/20 Smart grids as enabling technology in buildings sector smart grids supporting the management or operation of end-user stationary applications in general, or like technologies with no associated climate change mitigation effect Y04S20/00
• CPC Class Codes: Y02E 60/00 Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
• CPC Class Codes: Y04S 10/30 State monitoring, e.g. fault, temperature monitoring, insulator monitoring, corona discharge
• CPC Class Codes: Y04S 20/00 Management or operation of end-user stationary applications or the last stages of power distribution; Controlling, monitoring or operating thereof
• CPC Class Codes: Y04S 40/126 using wireless data transmission

Abstract

A load power device includes a power input; at least one power output for at least one load; and a plurality of sensors structured to sense voltage and current at the at least one power output. A processor is structured to provide real-time execution of: (a) a plurality of load identification algorithms, and (b) event detection and operating mode detection for the at least one load.

Claims

1. A load power device comprising:

a power input;

at least one power output for at least one load;

a plurality of sensors structured to sense voltage and current at said at least one power output; and

a processor structured to provide real-time execution of;

(a) a plurality of load identification algorithms, and (b) event detection and operating mode detection for the at least one load;

wherein the load identification algorithms include a mode identification algorithm and a plurality of load classification algorithms for the at least one load,

wherein the load classification algorithms include a first level identification function structured to read a cycle data buffer of the sensed voltage and current, extract voltage-current features, and output a first level identification and a corresponding confidence level for the at least one load,

wherein the load classification algorithms further include a second level identification function structured to input the first level identification, an event sequence and a power event sequence, extract finite state machine features, and output a second level identification and a corresponding confidence level for the at least one load,

wherein the load classification algorithms further include a third level identification function structured to input the second level identification and operating pattern information, and output a load device identification for the at least one load, and

wherein said processor further includes a load use sequence function structured to input the first level identification, the second level identification, the load device identification, and a control action which controls the corresponding one of said at least one power output, and to create or update a load use database.

2. The load power device of claim 1 wherein said at least one power output for the at least one load includes a first power outlet and a second power outlet;

and

wherein the first power outlet is always on for an uncontrolled load device and the second power outlet is controllable by said processor for a controlled load device.

3. The load power device of claim 1 wherein said processor is further structured to provide in real-time an energy or power consumption profile for each of said at least one power output.

4. The load power device of claim 1 wherein the load identification algorithms are structured to identify a device type or a banned load device powered by one of said at least one power outlet.

5. The load power device of claim 1 wherein said processor includes a power quality features function structured to input cycle data of the sensed voltage and current, calculate voltage-current features from the cycle data, and output a number of active and reactive power, total harmonic distortion, true and displacement power factor, and cumulative energy.

6. The load power device of claim 1 wherein said processor includes a user occupancy estimation function based upon user input, and a number of automatic detection of user occupancy and a building load management policy.

7. The load power device of claim 6 wherein the user occupancy estimation function is structured to estimate user occupancy status with or without an external occupancy sensor.

8. The load power device of claim 1 wherein said processor includes a state machine engine cooperating with the mode identification algorithm and the load classification algorithms.

9. The load power device of claim 8 wherein the state machine engine is structured to control steady state features extraction from the sensed voltage and current, the operating mode detection, the load classification algorithms, second level finite state machine feature extraction, and operating pattern feature extraction.

10. The load power device of claim 8 wherein the state machine engine employs quantized state sequence generation, event sequence generation, operating mode sequence generation, and the operating mode detection to establish a plurality of states based on status of the at least one load.

11. The load power device of claim 10 wherein said processor further includes a quantization function structured to input a cumulative sum of the average power and sensed current, calculate average power and average current, perform quantization and generate a quantized state sequence using RMS current and a quantized state sequence using real power, and calculate features which are specific to a current one of the states.

12. The load power device of claim 10 wherein said processor further includes an event sequence trigger evaluation function structured to generate a temporary event sequence using the quantized state sequence using real power, check step up and step down conditions from the temporary event sequence, and determine a start trigger or a stop trigger for an event sequence using the quantized state sequence using RMS current based on mode transition type and a step up and step down ratio.

13. The load power device of claim 12 wherein said processor further includes an event sequence generation function structured to generate, if the start trigger is detected, the last said event sequence from the quantized state sequence using RMS current until the event sequence stop trigger is detected, generate a power event sequence from the quantized state sequence using real power until a power event sequence stop trigger is detected, and generate an event sequence complete trigger.

14. The load power device of claim 12 wherein the start trigger is in response to start conditions for event sequence generation and the stop trigger is in response to stop conditions for event sequence generation.

15. A load power device comprising:

a power input;

at least one power output for at least one load;

a plurality of sensors structured to sense voltage and current at said at least one power output; and

a processor structured to provide real-time execution of;

(a) a plurality of load identification algorithms, and (b) event detection and operating mode detection for the at least one load;

wherein the load identification algorithms include a mode identification algorithm and a plurality of load classification algorithms for the at least one load,

wherein the load classification algorithms include a first level identification function structured to read a cycle data buffer of the sensed voltage and current, extract voltage-current features, and output a first level identification and a corresponding confidence level for the at least one load,

wherein the load classification algorithms further include a second level identification function structured to input the first level identification, an event sequence and a power event sequence, extract finite state machine features, and output a second level identification and a corresponding confidence level for the at least one load,

wherein the load classification algorithms further include a third level identification function structured to input the second level identification and operating pattern information, and output a load device identification for the at least one load, and

wherein said processor further includes a load control and management function structured to read a management policy compliance database, evaluate management policy compliance based upon the load device identification, output an alert if the load device identification violates a management policy, evaluate user occupancy based on a load control database, and, based on the user occupancy and a number of local and remote commands, control a corresponding one of said at least one power output.

16. The load power device of claim 15 wherein the management policy compliance database includes plug-in loads management policies that regulate use of plug-in loads and verify user compliance of the management policies, and outlet control strategies that define local and remote conditions of when to automatically turn on or off said at least one power output.

17. An energy system comprising:

a plurality of load power devices, each of said load power devices comprising;

a power input,

at least one power output for at least one load,

a plurality of sensors structured to sense voltage and current at said at least one power output, and

a processor structured to provide real-time execution of;

(a) a plurality of load identification algorithms, and (b) event detection and operating mode detection for the at least one load; and

an energy management system remote from and in communication with said load power devices,

wherein the load identification algorithms include a mode identification algorithm and a plurality of load classification algorithms for the at least one load,

wherein the load classification algorithms include a first level identification function structured to read a cycle data buffer of the sensed voltage and current, extract voltage-current features, and output a first level identification and a corresponding confidence level for the at least one load,

wherein the load classification algorithms further include a second level identification function structured to input the first level identification, an event sequence and a power event sequence, extract finite state machine features, and output a second level identification and a corresponding confidence level for the at least one load,

wherein the load classification algorithms further include a third level identification function structured to input the second level identification and operating pattern information, and output a load device identification for the at least one load, and

wherein said processor further includes a load use sequence function structured to input the first level identification, the second level identification, the load device identification, and a control action which controls the corresponding one of said at least one power output, and to create or update a load use database.

18. The energy system of claim 17 wherein said energy management system wirelessly communicates with said load power devices.

19. The energy system of claim 17 wherein said energy management system is structured to provide web-browsing, create a communication network to manage said load power devices, display status of plugged-in load devices in the communication network, and aggregate information by load device classes or load operating modes.