Energy consumption assessment

• US 10,394,266 B2
• Filed: 08/26/2015
• Issued: 08/27/2019
• Est. Priority Date: 08/26/2015
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Jin, Feng, Li, Bin, Lv, Xin Jie, Tian, Qi Ming, Ye, Lei, Zhang, Li, Zhou, Gang
• Primary Examiner(s): Cassity, Robert A
• Assistant Examiner(s): Coughlan, Peter D
• Application Number:
  US14/836,468
• Publication Number:
  US 20170060159A1
• Time in Patent Office: 1,462 Days
• Field of Search: 706 27
• CPC Class Codes: G05B 2219/2639 Energy management, use maximum of cheap power, keep peak load low
• CPC Class Codes: G05F 1/66 Regulating electric power

Abstract

According to embodiments of the present invention, the energy consumption assessment is done by identifying the benchmark production processes or enterprises. First, a process similarity between a target production process and a candidate production process is determined based on energy consumption units (ECUs) involved in the target production process and the candidate production process. In response to the process similarity being greater than a first threshold, an energy consumption similarity between the target production process and the candidate production process is determined based on a factor that has influence on energy consumption of at least one of the ECUs. In response to the energy consumption similarity being greater than a second threshold, the candidate production process is identified as a benchmark for assessing energy consumption of the target production process.

Claims

1. A computer-implemented method, comprising:

determining a process similarity between a target production process and a candidate production process based on energy consumption units (ECUs) involved in the target production process and the candidate production process, wherein determining the process similarity comprises;

determining, from a pool of critical ECUs, a first set of critical ECUs involved in the target production process, the pool of the critical ECUs being obtained based on a plurality of reference production processes, wherein obtaining the pool of critical ECUs by;

creating, by utilizing a computing device, a topology for each of the plurality of reference production processes, and

identifying an ECU as a critical ECU, wherein the topology for each of the plurality of reference production processes is broken without the ECU;

determining, from the pool of critical ECUs, a second set of critical ECUs involved in the candidate production process, wherein one or more identified critical ECUs are automatically added into the pool of critical ECUs;

determining, from a pool of non-critical ECUs, a first set of non-critical ECUs involved in the target production process, the pool of the non-critical ECUs being obtained based on the plurality of reference production processes;

determining, from the pool of non-critical ECUs, a second set of non-critical ECUs involved in the candidate production process; and

determining the process similarity based on comparing the number of critical ECUs shared in the first and second sets of critical ECUs and the number of non-critical ECUs shared in the first and second sets of critical ECUs, wherein the number of critical ECUs shared are weighted higher relative to the number of non-critical ECUs shared;

in response to the process similarity being greater than a first threshold, correlating an energy consumption similarity between the target production process and the candidate production process based on a factor that has influence on energy consumption of at least one of the ECUs; and

in response to the energy consumption similarity being greater than a second threshold, identifying, by utilizing a benchmark identifying module in the computing device, the candidate production process as a benchmark for assessing energy consumption of the target production process.

2. The method of claim 1, wherein determining the energy consumption similarity comprises:

obtaining a first value of the factor in the target production process;

obtaining a second value of the factor in the candidate production process;

determining a weight for the factor in association with the target production process; and

determining the energy consumption similarity by comparing the first value and the second value based on the determined weight.

3. The method of claim 2, wherein determining the weight for the factor in association with the target production process comprises:

determining reference values of the factor in a plurality of reference production processes;

dividing the plurality of reference production processes into a plurality of segments according to the reference values of the factor; and

determining the weight based on the dividing of the plurality of reference production processes.

4. The method of claim 3, wherein determining the weight based on the dividing of the plurality of reference production processes comprises:

obtaining reference metrics of energy consumption related to the factor in the plurality of reference production processes;

calculating a first average of the reference metrics;

determining one of the segments to which the target production process belongs;

calculating a second average of the reference metrics in the determined segment;

calculating a deviation of the reference metrics among the plurality of segments; and

determining the weight based on the first average, the second average and the deviation.

5. The method of claim 1, wherein the factor includes at least one of:

a design variable associated with the least one of the ECUs; and

an operational variable associated with the at least one of the ECUs.

6. A computer system, comprising:

one or more processors, one or more computer-readable memories, one or more computer-readable tangible storage media, and program instructions stored on at least one of the one or more computer-readable tangible storage media for execution by at least one of the one or more processors via at least one of the one or more computer-readable memories, wherein the computer system is capable of performing a method comprising;

determining a process similarity between a target production process and a candidate production process based on energy consumption units (ECUs) involved in the target production process and the candidate production process, wherein determining the process similarity comprises;

determining, from a pool of critical ECUs, a first set of critical ECUs involved in the target production process, the pool of the critical ECUs being obtained based on a plurality of reference production processes, wherein obtaining the pool of critical ECUs by;

creating, by utilizing a computing device, a topology for each of the plurality of reference production processes, and

identifying an ECU as a critical ECU, wherein the topology for each of the plurality of reference production processes is broken without the ECU;

determining, from the pool of critical ECUs, a second set of critical ECUs involved in the candidate production process, wherein one or more identified critical ECUs are automatically added into the pool of critical ECUs;

determining, from a pool of non-critical ECUs, a first set of non-critical ECUs involved in the target production process, the pool of the non-critical ECUs being obtained based on the plurality of reference production processes;

determining, from the pool of non-critical ECUs, a second set of non-critical ECUs involved in the candidate production process; and

determining the process similarity based on comparing the number of critical ECUs shared in the first and second sets of critical ECUs and the number of non-critical ECUs shared in the first and second sets of critical ECUs, wherein the number of critical ECUs shared are weighted higher relative to the number of non-critical ECUs shared;

in response to the process similarity being greater than a first threshold, correlating an energy consumption similarity between the target production process and the candidate production process based on a factor that has influence on energy consumption of at least one of the ECUs; and

in response to the energy consumption similarity being greater than a second threshold, identifying, by utilizing a benchmark identifying module in the computing device, the candidate production process as a benchmark for assessing energy consumption of the target production process.

7. The computer system of claim 6, wherein determining the energy consumption similarity comprises:

obtaining a first value of the factor in the target production process;

obtaining a second value of the factor in the candidate production process;

determining a weight for the factor in association with the target production process; and

determining the energy consumption similarity by comparing the first value and the second value based on the determined weight.

8. The computer system of claim 7, wherein determining the weight for the factor in association with the target production process comprises:

determining reference values of the factor in a plurality of reference production processes;

dividing the plurality of reference production processes into a plurality of segments according to the reference values of the factor; and

determining the weight based on the dividing of the plurality of reference production processes.

9. The computer system of claim 8, wherein determining the weight based on the dividing of the plurality of reference production processes comprises:

obtaining reference metrics of energy consumption related to the factor in the plurality of reference production processes;

calculating a first average of the reference metrics;

determining one of the segments to which the target production process belongs;

calculating a second average of the reference metrics in the determined segment;

calculating a deviation of the reference metrics among the plurality of segments; and

determining the weight based on the first average, the second average and the deviation.

10. The computer system of claim 6, wherein the factor includes at least one of:

a design variable associated with the least one of the ECUs; and

an operational variable associated with the at least one of the ECUs.

11. A computer program product tangibly stored on a non-transient machine-readable medium and comprising machine-executable instructions, the instructions, when executed on a device, causing the device to:

determine a process similarity between a target production process and a candidate production process based on energy consumption units (ECUs) involved in the target production process and the candidate production process, wherein determining the process similarity comprises;

determining, from a pool of critical ECUs, a first set of critical ECUs involved in the target production process, the pool of the critical ECUs being obtained based on a plurality of reference production processes, wherein obtaining the pool of critical ECUs by;

creating, by utilizing a computing device, a topology for each of the plurality of reference production processes, and

identifying an ECU as a critical ECU, wherein the topology for each of the plurality of reference production processes is broken without the ECU;

determining, from the pool of critical ECUs, a second set of critical ECUs involved in the candidate production process, wherein one or more identified critical ECUs are automatically added into the pool of critical ECUs;

determining, from a pool of non-critical ECUs, a first set of non-critical ECUs involved in the target production process, the pool of the non-critical ECUs being obtained based on the plurality of reference production processes;

determining, from the pool of non-critical ECUs, a second set of non-critical ECUs involved in the candidate production process; and

determining the process similarity based on comparing the number of critical ECUs shared in the first and second sets of critical ECUs and the number of non-critical ECUs shared in the first and second sets of critical ECUs, wherein the number of critical ECUs shared are weighted higher relative to the number of non-critical ECUs shared;

in response to the process similarity being greater than a first threshold, correlating an energy consumption similarity between the target production process and the candidate production process based on a factor that has influence on energy consumption of at least one of the ECUs; and

in response to the energy consumption similarity being greater than a second threshold, identify, by utilizing a benchmark identifying module in the computing device, the candidate production process as a benchmark for assessing energy consumption of the target production process.

12. The computer program product of claim 11, wherein the instructions, when executed on a device, further cause the device to:

obtain a first value of the factor in the target production process;

obtain a second value of the factor in the candidate production process;

determine a weight for the factor in association with the target production process; and

determine the energy consumption similarity by comparing the first value and the second value based on the determined weight.

13. The computer program product of claim 12, wherein the instructions, when executed on a device, further cause the device to:

determine reference values of the factor in a plurality of reference production processes;

divide the plurality of reference production processes into a plurality of segments according to the reference values of the factor; and

determine the weight based on the dividing of the plurality of reference production processes.

14. The computer program product of claim 13, wherein the instructions, when executed on a device, further cause the device to:

obtain reference metrics of energy consumption related to the factor in the plurality of reference production processes;

calculate a first average of the reference metrics;

determine one of the segments to which the target production process belongs;

calculate a second average of the reference metrics in the determined segment;

calculate a deviation of the reference metrics among the plurality of segments; and

determine the weight based on the first average, the second average and the deviation.