Operational energy consumption anomalies in intelligent energy consumption systems

Patent metadata

Field	Value
Publication number	US-11669757-B2
Application number	US-201916262464-A
Country	US
Kind code	B2
Filing date	Jan 30, 2019
Priority date	Jan 30, 2019
Publication date	Jun 6, 2023
Grant date	Jun 6, 2023

Abstract

Embodiments for detection of energy consumption anomalies in one or more energy consumption systems in a cloud computing environment by a processor. Energy consumption anomalies associated with a selected facility, a selected object, or a combination thereof may be detected and diagnosed according to feedback and simulation data generated from a scenario-based simulation operation.

First claim

The invention claimed is:

1. A method for anomaly detection of energy consumption in one or more energy consumption systems by one or more processors, comprising:
initiating a scenario-based simulation operation using simulated energy consumption data from a historical data of a database;
executing machine learning logic to receive simulated data from the scenario-based simulation operation and generate an energy classification model using the simulated data;
detecting one or more anomalies of energy consumption associated with a selected facility, a selected object, or a combination thereof according to feedback and the simulation data generated from the scenario-based simulation operation and analyzed using the energy classification model; and
outputting an indication, on a user interface, of the detected one or more anomalies.

2. The method of claim 1 , further including collecting sensor data from one or more Internet of Things (IoT) devices, sensor devices, or a combination thereof associated with the selected facility, the selected object, or a combination thereof.

3. The method of claim 1 , wherein executing the machine learning logic includes training the energy classification model using uncontaminated data.

4. The method of claim 1 , further including applying the energy classification model, a classifier, a decision tree, a natural language processing (“NLP”) operation, or a combination thereof to one or more defined anomaly scenarios during the scenario-based simulation operation.

5. The method of claim 1 , further including distinguishing between a data anomaly and an operational anomaly associated with the selected facility, the selected object, or a combination thereof using an active learning operation.

6. The method of claim 1 , further including ranking the one or more anomalies of energy consumption according to a priority score, an assigned confidence level, a predicted energy efficiency cost saving, or a combination thereof.

7. The method of claim 1 , further including generating a list of anomalies according to an assigned rank.

8. A system for anomaly detection of energy consumption in one or more energy consumption systems, comprising:
one or more computers with executable instructions that when executed cause the system to:
initiate a scenario-based simulation operation using simulated energy consumption data from a historical data of a database;
execute machine learning logic to receive simulated data from the scenario- based simulation operation and generate an energy classification model using the simulated data;
detect one or more anomalies of energy consumption associated with a selected facility, a selected object, or a combination thereof according to feedback and the simulation data generated from the scenario-based simulation operation and analyzed using the energy classification model; and
output an indication, on a user interface, of the detected one or more anomalies.

9. The system of claim 8 , wherein the executable instructions further collect sensor data from one or more Internet of Things (IoT) devices, sensor devices, or a combination thereof associated with the selected facility, the selected object, or a combination thereof.

10. The system of claim 8 , wherein executing the machine learning logic includes training the energy classification model using uncontaminated data.

11. The system of claim 8 , wherein the executable instructions further apply the energy classification model, a classifier, a decision tree, a natural language processing (“NLP”) operation, or a combination thereof to one or more defined anomaly scenarios during the scenario-based simulation operation.

12. The system of claim 8 , wherein the executable instructions further distinguish between a data anomaly and an operational anomaly associated with the selected facility, the selected object, or a combination thereof using an active learning operation.

13. The system of claim 8 , wherein the executable instructions further rank the one or more anomalies of energy consumption according to a priority score, an assigned confidence level, a predicted energy efficiency cost saving, or a combination thereof.

14. The system of claim 8 , wherein the executable instructions further generate a list of anomalies according to an assigned rank.

15. A computer program product for anomaly detection of energy consumption in one or more energy consumption systems by a processor, the computer program product comprising a non-transitory computer-readable storage medium having computer- readable program code portions stored therein, the computer-readable program code portions comprising:
an executable portion that initiates a scenario-based simulation operation using simulated energy consumption data from a historical data of a database;
an executable portion that executes machine learning logic to receive simulated data from the scenario-based simulation operation and generate an energy classification model using the simulated data;
an executable portion that detects one or more anomalies of energy consumption associated with a selected facility, a selected object, or a combination thereof according to feedback and the simulation data generated from the scenario-based simulation operation and analyzed using the energy classification model; and
an executable portion that outputs an indication, on a user interface, of the detected one or more anomalies.

16. The computer program product of claim 15 , further including an executable portion that collects sensor data from one or more Internet of Things (IoT) devices, sensor devices, or a combination thereof associated with the selected facility, the selected object, or a combination thereof.

17. The computer program product of claim 15 , wherein executing the machine learning logic includes training the energy classification model using uncontaminated data.

18. The computer program product of claim 15 , further including an executable portion that applies the energy classification model, a classifier, a decision tree, a natural language processing (“NLP”) operation, or a combination thereof to one or more defined anomaly scenarios during the scenario-based simulation operation.

19. The computer program product of claim 15 , further including an executable portion that distinguishes between a data anomaly and an operational anomaly associated with the selected facility, the selected object, or a combination thereof using an active learning operation.

20. The computer program product of claim 15 , further including an executable portion that:
ranks the one or more anomalies of energy consumption according to a priority score, an assigned confidence level, a predicted energy efficiency cost saving, or a combination thereof; and
generates a list of anomalies according to the rank.

Assignees

• IBM

Inventors

• Botea Adi
• Buesser Beat
• Kishimoto Akihiro
• Chen Bei

Classifications

• G06N5/048 Primary

  Fuzzy inferencing · CPC title

• G01R21/133

  by using digital technique · CPC title

• G06F30/20

  Design optimisation, verification or simulation (optimisation, verification or simulation of circuit designs G06F30/30) · CPC title

• G01R19/2513

  Arrangements for monitoring electric power systems, e.g. power lines or loads; Logging · CPC title

• G06N20/00 Primary

  Machine learning · CPC title