Progressive Humidity Filter For Load Data Forecasting

• US 20100153035A1
• Filed: 12/12/2008
• Published: 06/17/2010
• Est. Priority Date: 12/12/2008
• Status: Active Grant

• Current Assignee: Schneider Electric USA, Inc. (Schneider Electric SE)
• Original Assignee: Square D Company (Schneider Electric SE)
• Inventors: Gautam, Shruti
• Granted Patent: US 8,065,098 B2
• Time in Patent Office: Days
• US Class Current: 702/62
• CPC Class Codes: G06Q 10/04 Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" market predictions or forecasting for commercial activities G06Q30/0202
• CPC Class Codes: G06Q 10/0833 Tracking
• CPC Class Codes: G06Q 30/0283 Price estimation or determination
• CPC Class Codes: G06Q 50/06 Energy or water supply
• CPC Class Codes: Y04S 10/50 Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Abstract

A method, via a processor, of forecasting energy usage including selecting a plurality of reference days with at least one feature matching a corresponding feature of a day to be forecasted and filtering the plurality of reference days with a humidity filter to identify at least one matching reference day. The at least one matching reference day is associated with a correlation coefficient greater than or equal to a minimum correlation coefficient, and a minimum number of humidity values within a range of corresponding humidity values of the day to be forecasted. The method also includes retrieving energy load values and corresponding temperature values corresponding to the at least one matching reference day, calculating a plurality of regression coefficients of a polynomial equation linking the temperature values to the energy load values, and calculating and storing a forecasted load value of the day to be forecasted according to the polynomial equation.

Claims

1. Via a processor, a method of forecasting energy usage comprising:

selecting a plurality of reference days with at least one feature matching a corresponding feature of a day to be forecasted;

filtering the plurality of reference days with a humidity filter to identify at least one matching reference day wherein the at least one matching reference day is associated with;

a correlation coefficient greater than or equal to a minimum correlation coefficient, and

a minimum number of humidity values within a range of corresponding humidity values of the day to be forecasted;

retrieving energy load values and corresponding temperature values corresponding to the at least one matching reference day;

calculating a plurality of regression coefficients of a polynomial equation linking the temperature values to the energy load values; and

calculating and storing a forecasted load value of the day to be forecasted according to the polynomial equation.

2. The method of claim 1, wherein the identifying the at least one matching reference day comprises:

calculating the correlation coefficient associated with the at least one matching reference day, wherein the correlation coefficient represents an estimated magnitude and a direction of a linear relationship between a first set of humidity values associated with time intervals for the reference day and a second set of humidity values associated with corresponding time intervals for the day to be forecasted; and

comparing the correlation coefficient to the minimum correlation coefficient.

3. The method of claim 2, wherein the minimum correlation coefficient is greater than 0.5.

4. The method of claim 1, further comprising:

accessing stored historical load values at a plurality of time intervals for the at least one matching reference day;

accessing stored humidity data corresponding to the time intervals; and

accessing stored temperature data corresponding to the time intervals.

5. The method of claim 1, further comprising outputting the forecasted load value at an output device.

6. The method of claim 5, wherein the output device comprises at least one of a display and a printer.

7. The method of claim 1, wherein the calculating the forecasted load value of the day to be forecasted comprises calculating a load value associated with a time interval of the day to be forecasted.

8. The method of claim 1, wherein the at least one feature comprises a day of the week, a work day, a weekend day, or a holiday.

9. A method of identifying, via a processor, a matching reference day for energy usage forecasting, the method comprising:

retrieving a reference day record from a memory;

comparing feature information of the reference day record to a feature criteria;

responsive to the feature information matching the feature criteria,

comparing at least one humidity value associated with the reference day record to at least one forecasted humidity value, and

calculating a correlation coefficient representing a comparison of a humidity profile associated with the reference day record to a forecasted humidity profile;

responsive to the at least one humidity value being within a humidity deviation range of the at least one forecasted humidity value and the correlation coefficient equaling or exceeding a minimum correlation coefficient,

identifying the reference day as a matching reference day; and

storing the matching reference day in a matching reference day list in the memory.

10. The method of claim 9, further comprising:

calculating a current number of matching reference days; and

responsive to the current number of matching references being below a minimum number of reference days, increasing the humidity deviation range or decreasing the minimum correlation coefficient.

11. The method of claim 9, wherein the feature criteria comprises a value representing a day of the week, a value representing a work day, a value representing a weekend day, a value representing a holiday, or a value representing an atypical load day.

12. The method of claim 9, wherein the at least one humidity value corresponds to a time increment.

13. The method of claim 12, wherein the time increments comprise increments of 15 minutes, 30 minutes, or one hour.

14. The method of claim 9,

wherein the comparing the at least one humidity value of the reference day record to the at least one forecasted humidity value comprises comparing a plurality of humidity values of the reference day, each humidity value associated with a time interval of the reference day, to a plurality of forecasted humidity values, each forecasted humidity value associated with a corresponding time interval of the forecasted day,

the method further comprising:

determining a number of the plurality of humidity values that are within the humidity range of a forecasted humidity value associated with a corresponding time interval; and

determining that the number of the plurality of humidity values equals or exceeds a minimum number of humidity values.

15. The method of claim 9, further comprising:

retrieving a plurality of temperature values from the reference day record; and

calculating a regression method based on the plurality of temperature values from the reference day record, wherein the regression method predicts energy usage values corresponding to temperature values.

16. The method of claim 15, further comprising calculating and storing a predicted load value for a forecasted temperature value based on the regression method.

17. The method of claim 16, further comprising outputting the predicted load value at an output device, wherein the output device comprises at least one of a display and a printer.

18. A computer readable medium having stored thereon instructions for identifying a matching reference day for energy usage forecasting, comprising machine executable code that when executed by a processor, causes the processor to perform steps comprising:

retrieving a reference day record from a memory;

comparing feature information of the reference day record to a feature criteria;

responsive to the feature information matching the feature criteria,

comparing at least one humidity value associated with the reference day record to at least one forecasted humidity value, and

calculating a correlation coefficient representing a comparison of a humidity profile of the reference day record to a forecasted humidity profile;

responsive to the at least one humidity value being within a humidity deviation range of the at least one forecasted humidity value and the correlation coefficient equaling or exceeding a minimum correlation coefficient, identifying the reference day as a matching reference day; and

storing the matching reference day in a matching reference day list in the memory.

19. The medium as set forth in claim 18, further comprising:

calculating a current number of matching reference days; and

responsive to the current number of matching references being below a minimum number of reference days, increasing the humidity range or decreasing the minimum correlation coefficient.

20. The medium as set forth in claim 18, further comprising:

retrieving a plurality of temperature values from the reference day record; and

calculating a regression method based on the plurality of temperature values from the reference day record, wherein the regression method predicts energy usage values corresponding to the temperature values.