UTILITY USAGE FORECASTING

• US 20150192697A1
• Filed: 01/07/2014
• Published: 07/09/2015
• Est. Priority Date: 01/07/2014
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Hosking, Jonathan R. M., Natarajan, Ramesh
• Granted Patent: US 9,739,908 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G01W 1/10 Devices for predicting weather conditions computers per se G06; display devices G09

Abstract

The computer creates a utility demand forecast model for weather parameters by receiving a plurality of utility parameter values, wherein each received utility parameter value corresponds to a weather parameter value. Determining that a range of weather parameter values lacks a sufficient amount of corresponding received utility parameter values. Determining one or more utility parameter values that corresponds to the range of weather parameter values. Creating a model which correlates the received and the determined utility parameter values with the corresponding weather parameters values.

Claims

1. A method for creating a utility demand forecast model for weather parameters, the method comprising:

receiving, by one or more processors, a plurality of utility parameter values, wherein each received utility parameter value corresponds to a weather parameter value;

determining, by one or more processors, that a range of weather parameter values lacks a sufficient amount of corresponding received utility parameter values;

determining, by one or more processors, one or more utility parameter values that corresponds to the range of weather parameter values; and

creating, by one or more processors, a model which correlates the received and the determined utility parameter values with corresponding weather parameters values.

2. The method of claim 1, wherein the step of, determining that a range of weather parameter values lacks a sufficient amount of corresponding received utility parameter values, comprises:

determining, by one or more processors, that an amount of received utility parameter values that correspond to the range of the weather parameter values neither meet nor exceed a threshold.

3. The method of claim 1, wherein the weather parameter values includes a group comprising one or more of:

past outdoor temperatures, past wind chill factors, past heat indices, and past precipitation measurements.

4. The method of claim 1, wherein the utility parameter values includes a group comprising one or more of:

past natural gas consumption, past electrical consumption, water consumption, and past heating oil consumption.

5. The method of claim 2, wherein the step of, determining one or more utility parameter values that corresponds to the range of weather parameter values, comprises:

determining, by one or more processors, a plurality of utility parameter values that may correspond to a first weather parameter value of the range of weather parameter values, wherein each of the plurality of utility parameter values has an associated probability of occurrence; and

determining, by one or more processors, one or more utility parameter values from the plurality of utility parameter values, wherein the determined one or more utility parameter values has the highest associated probability of occurrence.

6. The method of claim 1, wherein the step of, creating a model which correlates the received and the determined utility parameter values with the weather parameters values, comprises:

determining, by one or more processors, a single utility parameter value that corresponds to each weather parameter value.

7. The method of claim 1, wherein the step of, creating a model which correlates the received and the determined utility parameter values with the weather parameters values, comprises:

determining, by one or more processors, a first slope for a first portion of determined utility parameter values;

determining, by one or more processors, a second slope for a second portion of determined utility parameter values; and

generating, by one or more processors, a model, utilizing a cubic spline approximation, based on the determined first and second slopes.

8. A computer program product for creating a utility demand forecast model for weather parameters, the computer program product comprising:

one or more computer readable storage media;

program instructions stored on the one or more computer readable storage media, which when executed by one or more processors, to;

receive, by one or more processors, a plurality of utility parameter values, wherein each received utility parameter value corresponds to a weather parameter value;

determine, by one or more processors, that a range of weather parameter values lacks a sufficient amount of corresponding received utility parameter values;

determine, by one or more processors, one or more utility parameter values that corresponds to the range of weather parameter values; and

create, by one or more processors, a model which correlates the received and the determined utility parameter values with corresponding weather parameters values.

9. The computer program product of claim 8, wherein the step of, determining that a range of weather parameter values lacks a sufficient amount of corresponding received utility parameter values, comprises program instructions, stored on the one or more computer readable storage media, which when executed by a processor, to:

determine, by one or more processors, that an amount of received utility parameter values that correspond to the range of the weather parameter values neither meet nor exceed a threshold.

10. The computer program product of claim 8, wherein the weather parameter values includes a group comprising one or more of:

past outdoor temperatures, past wind chill factors, past heat indices, and past precipitation measurements.

11. The computer program product of claim 8, wherein the utility parameter values includes a group comprising one or more of:

past natural gas consumption, past electrical consumption, water consumption, and past heating oil consumption.

12. The computer program product of claim 9, wherein the step of, determining one or more utility parameter values that corresponds to the range of weather parameter values, comprises program instructions, stored on the one or more computer readable storage media, which when executed by a processor, to:

determine, by one or more processors, a plurality of utility parameter values that may correspond to a first weather parameter value of the range of weather parameter values, wherein each of the plurality of utility parameter values has an associated probability of occurrence; and

determine, by one or more processors, one or more utility parameter values from the plurality of utility parameter values, wherein the determined one or more utility parameter values has the highest associated probability of occurrence.

13. The computer program product of claim 8, wherein the step of, creating a model which correlates the received and the determined utility parameter values with the weather parameters values, comprises program instructions, stored on the one or more computer readable storage media, which when executed by a processor, to:

determine, by one or more processors, a single utility parameter value that corresponds to each weather parameter value.

14. The computer program product of claim 8, wherein the step of, creating a model which correlates the received and the determined utility parameter values with the weather parameters values, comprises program instructions, stored on the one or more computer readable storage media, which when executed by a processor, to:

determine, by one or more processors, a first slope for a first portion of determined utility parameter values;

determine, by one or more processors, a second slope for a second portion of determined utility parameter values; and

generate, by one or more processors, a model, utilizing a cubic spline approximation, based on the determined first and second slopes.

15. A computer system for creating a utility demand forecast model for weather parameters, the computer system comprising:

one or more computer processors;

one or more computer readable storage media;

program instructions stored on the one or more computer readable storage media, for execution by at least one of the one or more computer processors, which when executed, to;

receive, by one or more processors, a plurality of utility parameter values, wherein each received utility parameter value corresponds to a weather parameter value;

determine, by one or more processors, that a range of weather parameter values lacks a sufficient amount of corresponding received utility parameter values;

determine, by one or more processors, one or more utility parameter values that corresponds to the range of weather parameter values; and

create, by one or more processors, a model which correlates the received and the determined utility parameter values with corresponding weather parameters values.

16. The computer system of claim 15, wherein the step of, determining that a range of weather parameter values lacks a sufficient amount of corresponding received utility parameter values, comprises program instructions, stored on the one or more computer readable storage media, which when executed by a processor, to:

determine, by one or more processors, that an amount of received utility parameter values that correspond to the range of the weather parameter values neither meet nor exceed a threshold.

17. The computer system of claim 15, wherein the utility parameter values includes a group comprising one or more of:

past natural gas consumption, past electrical consumption, water consumption, and past heating oil consumption.

18. The computer system of claim 16, wherein the step of, determining one or more utility parameter values that corresponds to the range of weather parameter values, comprises program instructions, stored on the one or more computer readable storage media, which when executed by a processor, to:

determine, by one or more processors, a plurality of utility parameter values that may correspond to a first weather parameter value of the range of weather parameter values, wherein each of the plurality of utility parameter values has an associated probability of occurrence; and

determine, by one or more processors, one or more utility parameter values from the plurality of utility parameter values, wherein the determined one or more utility parameter values has the highest associated probability of occurrence.

19. The computer system of claim 15, wherein the step of, creating a model which correlates the received and the determined utility parameter values with the weather parameters values, comprises program instructions, stored on the one or more computer readable storage media, which when executed by a processor, to:

determine, by one or more processors, a single utility parameter value that corresponds to each weather parameter value.

20. The computer system product of claim 15, wherein the step of, creating a model which correlates the received and the determined utility parameter values with the weather parameters values, comprises program instructions, stored on the one or more computer readable storage media, which when executed by a processor, to:

determine, by one or more processors, a first slope for a first portion of determined utility parameter values;

determine, by one or more processors, a second slope for a second portion of determined utility parameter values; and

generate, by one or more processors, a model, utilizing a cubic spline approximation, based on the determined first and second slopes.