Method and device for facilitating storage of data from an industrial automation control system or power system

Patent metadata

Field	Value
Publication number	US-12130778-B2
Application number	US-202017616392-A
Country	US
Kind code	B2
Filing date	Jun 5, 2020
Priority date	Jun 5, 2019
Publication date	Oct 29, 2024
Grant date	Oct 29, 2024

Abstract

To facilitate storage of data from plural data sources of an industrial automation control system, power distribution system or power generation system, a decision making device executes a machine learning algorithm to determine a compression technique in dependence on the data source from which data originates.

First claim

The invention claimed is:

1. A method of facilitating storage of data from plural data sources of a system, the system being an industrial automation control system (IACS), power distribution system, or power generation system, the method comprising:
determining, using at least one integrated circuit of a decision making device, a compression technique that is to be applied to the data, wherein the decision making device executes a machine learning algorithm to determine the compression technique in dependence on a data source from which the data originates, wherein determining the compression technique comprises executing the machine learning algorithm to generate an update of a data model or profile associated with the data source;
causing, by the decision making device, the compression technique determined for the data source to be applied to data from that data source by generating update information relating to the update of the data model or profile, and transmitting the update information to the data source for which the update of the data model or profile has been determined;
updating, by the data source, a compression model or profile stored locally at the data source based on received update information to thereby generate an updated compression model or profile; and
performing, by the data source, a compression based on the updated compression model or profile.

2. The method of claim 1 , wherein information on changes in a compression technique that is to be employed is provided by the decision making device to the respective data source and/or to storage devices via a push mechanism.

3. The method of claim 2 , wherein the information on changes in a compression technique is transmitted as incremental updates, indicating a change in compression profile or data model.

4. The method of claim 1 , wherein determining the compression technique comprises executing the machine learning algorithm to determine which one of several candidate compression techniques is to be applied.

5. The method of claim 1 , wherein determining the compression technique comprises executing the machine learning algorithm to determine at least one parameter of the compression technique.

6. The method of claim 1 , further comprising automatically repeating the steps of determining the compression technique and causing the compression technique to be applied, wherein the steps of determining the compression technique and causing the compression technique to be applied are repeated in a regular manner.

7. The method of claim 1 , wherein the data source to which the update information is transmitted comprises a sensor device or a merging unit.

8. The method of claim 1 , further comprising transmitting, by the decision making device, the update information to at least one storage device that stores the data from the data source.

9. The method of claim 1 , wherein the machine learning algorithm determines the compression technique under a data-source dependent constraint.

10. The method of claim 1 , further comprising:
training the machine learning algorithm during operation of the IACS, power distribution system or power generation system,
wherein training the machine learning algorithm comprises learning whether a compression in the time domain or a compression in the frequency domain is more beneficial.

11. The method of claim 1 , wherein
the determined compression technique determines correlations of time-series data of different data sources, wherein the method further comprises a transmission and/or storage of information that depends on the determined correlations, and/or
wherein the determined compression technique comprises a classification or clustering technique, wherein the method further comprises a transmission and/or storage of information that indicates a class or cluster, and/or wherein the classification or clustering is time-dependent.

12. A decision making device adapted to facilitate storage of data from plural data sources of an industrial automation control system (IACS), power distribution system or power generation system, the decision making device comprising:
at least one interface adapted to be communicatively coupled to the plural data sources; and
at least one integrated circuit operative to
determine a compression technique that is to be applied to the data, wherein the decision making device executes a machine learning algorithm to determine the compression technique in dependence on a data source, from among the plural data sources, from which the data originates, wherein determining the compression technique comprises executing the machine learning algorithm to generate an update of a data model or profile associated with the data source, and
cause the compression technique determined for the data source to be applied to data from that data source by generating update information relating to the update of the data model or profile, and transmitting the update information to the data source for which the update of the data model or profile has been determined, such that the data source
updates a compression model or profile stored locally at the data source based on received update information to thereby generate an updated compression model or profile, and
performs a compression based on the updated compression model or profile.

13. The decision making device of claim 12 , wherein the decision making device is adapted to provide information on changes in a compression technique that is to be employed to the respective data source and/or to storage devices via a push mechanism.

14. The decision making device of claim 13 , wherein the decision making device is adapted to transmit the information on changes in a compression technique as incremental updates, indicating a change in compression profile or data model.

15. The decision making device of claim 12 , wherein the at least one integrated circuit is operative to generate control information that causes the compression technique determined for a data source to be applied to the data originating from that data source before storing the data.

16. A system that is an industrial automation control system (IACS), power distribution system or power generation system, comprising:
a plurality of data sources;
at least one storage device to store compressed data originating from the plurality of data sources; and
a decision making device adapted to facilitate storage of data from the plurality of data sources, the decision making device comprising
at least one interface adapted to be communicatively coupled to the plurality of data sources, and
at least one integrated circuit operative to
determine a compression technique that is to be applied to the data, wherein the decision making device executes a machine learning algorithm to determine the compression technique in dependence on a data source, from among the plurality of data sources, from which the data originates, wherein determining the compression technique comprises executing the machine learning algorithm to generate an update of a data model or profile associated with the data source, and
cause the compression technique determined for the data source to be applied to data from that data source by generating update information relating to the update of the data model or profile, and transmitting the update information to the data source for which the update of the data model or profile has been determined, such that the data source
updates a compression model or profile stored locally at the data source based on received update information to thereby generate an updated

Assignees

• Hitachi Energy Ltd

Inventors

• Ferranti Ettore
• Franke Carsten
• Locher Thomas
• Pignolet Yvonne-Anne
• Schoenborn Sandro
• Sivanthi Thanikesavan
• Widmer Theo

Classifications

• H03M7/3068

  Precoding preceding compression, e.g. Burrows-Wheeler transformation · CPC title

• H03M7/70

  Type of the data to be coded, other than image and sound · CPC title

• H03M7/6064

  Selection of Compressor · CPC title

• H03M7/3059 Primary

  Digital compression and data reduction techniques where the original information is represented by a subset or similar information, e.g. lossy compression · CPC title

• H03M7/30

  Compression (speech analysis-synthesis for redundancy reduction G10L19/00; for image communication H04N); Expansion; Suppression of unnecessary data, e.g. redundancy reduction · CPC title