Centralized controller for intelligent control of thermostatically controlled devices

• US 9,477,240 B2
• Filed: 04/29/2013
• Issued: 10/25/2016
• Est. Priority Date: 04/29/2013
• Status: Active Grant

• Current Assignee: Eaton Intelligent Power Limited (Eaton Corporation PLC.)
• Original Assignee: Eaton Corp. (Wisconsin) (Eaton Corporation PLC.)
• Inventors: Musunuri, Shravana Kumar, Thokala, Naveen Kumar, Luebke, Charles J., Shinde, Abhay
• Primary Examiner(s): KASENGE, CHARLES R
• Application Number:
  US13/872,541
• Publication Number:
  US 20140324244A1
• Time in Patent Office: 1,275 Days
• Field of Search: 700/276, 700/278, 700/291, 700/299, 700/300, 236/1.C, 236/46.A, 236/91.C, 236/91.D, 236/91.F
• US Class Current: 1/1
• CPC Class Codes: G05B 15/02 electric
• CPC Class Codes: G05D 23/19 characterised by the use of electric means G05D23/1393 takes precedence
• CPC Class Codes: G05D 23/1934 each space being provided with one sensor acting on one or more control means
• CPC Class Codes: G06N 20/00 Machine learning

Abstract

A control module for controlling a thermostatically controlled device includes a processor apparatus adapted to obtain first values for a plurality of parameters for the thermostatically controlled device, the parameters including actual power consumed by the thermostatically controlled device and a number of input parameters, determine a learned correlation function for the thermostatically controlled device based on the obtained values, wherein the learned correlation function relates power consumption of the thermostatically controlled device to at least the number of input parameters, obtain second values for each of the number of input parameters for a future usage period, and determine at least one recommended set point for the thermostatically controlled device using the learned correlation function and at least the second values for each of the number of input parameters.

Claims

1. A control module for controlling a thermostatically controlled device, comprising:

a processor apparatus including a processing unit and a memory, the memory storing one or more routines executable by the processing unit, the one or more routines being adapted to;

obtain first values for a plurality of parameters for the thermostatically controlled device, the parameters including actual power consumed by the thermostatically controlled device and a number of input parameters, wherein the number of input parameters include external temperature and current temperature settings of the thermostatically controlled device, external humidity, current time of day, current day, and current season;

determine a learned correlation function for the thermostatically controlled device based on the obtained values, wherein the learned correlation function relates power consumption of the thermostatically controlled device to at least the number of input parameters;

obtain second values for each of the number of input parameters for a future usage period;

determine at least one recommended set point for the thermostatically controlled device using the learned correlation function and at least the second values for each of the number of input parameters; and

control the thermostatically controlled device based on the at least one recommended set point.

2. The control module according to claim 1, wherein the one or more routines are also adapted to:

(i) obtain energy pricing information for the future usage period, (ii) determine a predicted power consumption of the thermostatically controlled device for the future usage period using the learned correlation function and the second values for each of the number of input parameters, (iii) determine a predicted energy cost for the thermostatically controlled device for the future usage period based on the energy pricing information and the predicted power consumption, and (iv) determine the at least one recommended set point based on the predicted energy cost.

3. The control module according to claim 2, wherein the energy pricing information is electricity pricing information for the future usage period.

4. The control module according to claim 2, wherein the at least one recommended set point is determined so as to achieve an energy savings for the future usage period as compared to the predicted energy cost.

5. The control module according to claim 1, wherein the one or more routines are also adapted to cause the at least one recommended set point to be communicated to a user, receive a signal indicating that the at least one recommended set point has been approved, and in response to receiving the signal, cause a control signal including the at least one recommended set point to be communicated to the thermostatically controlled device for controlling the thermostatically controlled device.

6. The control module according to claim 5, further comprising a display, wherein the one or more routines are also adapted to cause the at least one recommended set point to be communicated to the user by causing the at least one recommended set point to be displayed on the display.

7. The control module according to claim 5, wherein the one or more routines are also adapted to cause the at least one recommended set point to be communicated to the user by transmitting the at least one recommended set point to an electronic device.

8. The control module according to claim 1, wherein the thermostatically controlled device is selected from a group consisting of an HVAC system, a space heater and a water heater.

9. The control module according to claim 1, wherein the number of input parameters include one or more of external temperature, external humidity, current time of day, current day, current season, and current temperature settings of the thermostatically controlled device.

10. The control module according to claim 1, wherein the one or more routines are adapted to determine the learned correlation function using an expert system based learning technique.

11. The control module according to claim 10, wherein the one or more routines are adapted to determine the learned correlation function using an artificial neural network.

12. The control module according to claim 1, wherein the one or more routines are adapted to determine the at least one recommended set point using the learned correlation function, at least the second values for each of the number of input parameters, and a learned pattern of usage of the thermostatically controlled device.

13. The control module according to claim 1, wherein the one or more routines are also adapted to cause the at least one recommended set point to be communicated to a user, receive a signal indicating that the at least one recommended set point has been approved, and in response to receiving the signal, cause a control signal including the at least one recommended set point to be communicated to a circuit breaker for controlling the thermostatically controlled device.

14. The control module according to claim 1, wherein a local input device for receiving one or more inputs indicting when an environment including the thermostatically controlled device will be occupied is provided in the environment, and wherein the processor apparatus is configured to control the thermostatically controlled device based on the one or more inputs.

23. The method according to claim 13, wherein the step of determining the at least one recommended set point uses the learned correlation function, at least the second values for each of the number of input parameters, and a learned pattern of usage of the thermostatically controlled device.

15. A method of controlling a thermostatically controlled device, comprising:

obtaining, by a processor, first values for a plurality of parameters for the thermostatically controlled device, the parameters including actual power consumed by the thermostatically controlled device and a number of input parameters, wherein the number of input parameters include external temperature and current temperatures settings of the thermostatically controlled device, external humidity, current time of day, current day, and a current season;

determining, by the processor, a learned correlation function for the thermostatically controlled device based on the obtained values, wherein the learned correlation function relates power consumption of the thermostatically controlled device to at least the number of input parameters;

obtaining, by the processor, second values for each of the number of input parameters for a future usage period;

determining, by the processor, at least one recommended set point for the thermostatically controlled device using the learned correlation function and at least the second values for each of the number of input parameters; and

controlling the thermostatically controlled device based on the at least one recommended set point.

16. The method according to claim 15, further comprising obtaining energy pricing information for the future usage period, determining a predicted power consumption of the thermostatically controlled device for the future usage period using the learned correlation function and the second values for each of the number of input parameters, determining a predicted energy cost for the thermostatically controlled device for the future usage period based on the energy pricing information and the predicted power consumption, and determining the at least one recommended set point based on the predicted energy cost.

17. The method according to claim 16, wherein the energy pricing information is electricity pricing information for the future usage period.

18. The method according to claim 16, wherein the at least one recommended set point is determined so as to achieve an energy savings for the future usage period as compared to the predicted energy cost.

19. The method according to claim 15, further comprising causing the at least one recommended set point to be communicated to a user, receiving a signal indicating that the at least one recommended set point has been approved, and in response to receiving the signal, causing the thermostatically controlled device to be controlled based on the at least one recommended set point.

20. The method according to claim 15, wherein the number of input parameters include one or more of external temperature, external humidity, current time of day, current day, current season, and current temperature settings of the thermostatically controlled device.

21. The method according to claim 15, wherein the step of determining the learned correlation function employs an expert system based learning technique.

22. The method according to claim 21, wherein the step of determining the learned correlation function employs an artificial neural network.