Energy intensity variability analysis

Patent metadata

Field	Value
Publication number	US-10438150-B2
Application number	US-201514753610-A
Country	US
Kind code	B2
Filing date	Jun 29, 2015
Priority date	Jun 29, 2015
Publication date	Oct 8, 2019
Grant date	Oct 8, 2019

Abstract

A method for reducing energy costs at a facility includes identifying candidate production entities at the facility having a high potential for energy intensity variation reduction, determining potential cost savings associated with reducing energy intensity variation in the candidate production entities, identifying a root cause for energy intensity variation in the candidate production entities, and causing an action to be performed to mitigate the root cause.

First claim

What is claimed is:

1. A method for reducing energy costs at a facility, the method comprising:
reading data related to power consumption and production of production entities at the facility via one or more input devices of a control system associated with the facility;
identifying, by a computer processor of the control system, candidate production entities at the facility having energy intensity distributions with positive skew towards high energy intensity values;
identifying, by the computer processor, a root cause for energy intensity variation in the candidate production entities, identifying the root cause for energy intensity variation in the candidate production entities including determining a time of a change in energy intensity variation in the candidate production entities through a method of change-point detection, the method of change-point detection including a bootstrapping analysis; and
causing, by an output device of the control system, an action to be performed to mitigate the root cause by adjusting one of one or more operation parameters of the one or more of the candidate production entities by providing one or more control signals to the one or more of the candidate production entities or one or more operation parameters of one or more ancillary systems associated with one or more of the candidate production entities by providing one or more control signals to the one or more of the ancillary systems.

2. The method of claim 1 , wherein the candidate production entities are identified through compression pre-testing.

3. The method of claim 2 , wherein the compression pre-testing includes combining a first energy intensity dataset associated with a first group of variables with a second energy intensity dataset statistically similar to the first data set and associated with a second group of variables into a composite macro group variable for analysis.

4. The method of claim 3 , wherein the compression pre-testing includes combining statistically similar datasets associated with a plurality of groups of variables into a plurality of composite macro group variables, each of the composite macro group variables having statistically different associated data sets.

5. The method of claim 4 , wherein the root cause is identified through analysis of parameters of variables included in each macro group variable, the analysis including identifying one or more variables that have different values in different of the macro group variables as being related to the root cause.

6. The method of claim 2 , wherein the compression pre-testing includes ranking of parameters derived from each of variability of energy intensity, energy intensity skewness, and total amount of production for each of the candidate production entities.

7. The method of claim 1 , wherein the bootstrapping analysis includes:
calculating a first CUSUM range of error values for a data set including time ordered values of a variable identified as being associated with the root cause;
randomly reordering the values of the variable in the data set to create a plurality of randomly reordered data sets;
calculating CUSUM ranges of error values for the plurality of randomly reordered data sets; and
determining if the first CUSUM range of error values differs from the CUSUM ranges of error values for the plurality of randomly reordered data sets with a confidence level more than a predetermined confidence level.

8. The method of claim 1 , wherein the method of change-point detection includes a Mean Square Error analysis.

9. The method of claim 1 , wherein the method of change-point detection includes a BS-MSE analysis.

10. The method of claim 1 , wherein the method of change-point detection includes a relative standard deviation analysis.

11. The method of claim 1 , wherein the root cause is determined by comparison of a signature of the energy intensity variation in the candidate production entities with a database of energy intensity variation signatures and associated root causes.

12. A computer system comprising:
a processor configured to perform a method including:
reading data related to power consumption and production of production entities at a facility via one or more input devices of a control system associated with the facility;
identifying candidate production entities at the facility having energy intensity distributions with positive skew towards high energy intensity values;
identifying a root cause for energy intensity variation in the candidate production entities, identifying the root cause for energy intensity variation in the candidate production entities including determining a time of a change in energy intensity variation in the candidate production entities through a method of change-point detection, the method of change-point detection including a bootstrapping analysis;
causing an action to be performed to mitigate the root cause; and
an output device configured to provide control signals to one or more of the candidate production entities or one or more ancillary systems associated with one or more of the candidate production entities, wherein causing the action to be performed to mitigate the root cause includes adjusting one or more operation parameters of the one or more of the candidate production entities or one or more ancillary systems by providing one or more control signals from the output device to the one or more of the candidate production entities or one or more ancillary systems.

13. The computer system of claim 12 , configured to identify the root cause for energy intensity variation in the candidate production entities by a method including determining a time of a change in energy intensity variation in the candidate production entities though a method of change-point detection.

14. The computer system of claim 12 , further comprising a database, wherein the processor is configured to determine the root cause is by comparing a signature of the energy intensity variation in the candidate production entities with energy intensity variation signatures and associated root causes stored in the database.

15. A non-transitory computer readable media including instructions that when executed on a computer system cause the computer system to perform a method comprising:
reading data related to power consumption and production of production entities at a facility via one or more input devices;
identifying candidate production entities at the facility having energy intensity distributions with positive skew towards high energy intensity values;
identifying a root cause for energy intensity variation in the candidate production entities, identifying the root cause for energy intensity variation in the candidate production entities including determining a time of a change in energy intensity variation in the candidate production entities through a method of change-point detection, the method of change-point detection including a bootstrapping analysis; and
causing an action to be performed to mitigate the root cause by adjusting one of one or more operation parameters of the one or more of the candidate production entities by providing one or more control signals to the one or more of the candidate production entities or one or more operation parameters of one or more ancillary systems associated with one or more of the candidate production entities by providing one or more control signals to the one or more of the ancillary systems.

16. The method of claim 1 , further comprising determining, by the computer processor, potential cost savings associated with reducing energy intensity var

Assignees

• Schneider Electric Usa Inc

Inventors

• Stanlake Matthew
• Mackenzie Michael Brian
• Cheraghi Shirazi Mohammad Amin

Classifications

• G06Q50/06

  Energy or water supply · CPC title

• G06Q10/06

  Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling · CPC title

• G06Q10/04

  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 title

• G06Q10/06313 Primary

  Resource planning in a project environment · CPC title

• Y02P90/82

  Energy audits or management systems therefor · CPC title