Adaptive telemetry based on in-network cross domain intelligence

• US 9,998,805 B2
• Filed: 07/26/2017
• Issued: 06/12/2018
• Est. Priority Date: 07/20/2016
• Status: Active Grant

• Current Assignee: Cisco Technology, Inc. (Cisco Systems, Inc.)
• Original Assignee: Cisco Technology, Inc. (Cisco Systems, Inc.)
• Inventors: Friel, Joseph, Latapie, Hugo, Surcouf, Andre, Fenoglio, Enzo
• Primary Examiner(s): Garcia, Santiago
• Application Number:
  US15/660,882
• Publication Number:
  US 20180027309A1
• Time in Patent Office: 321 Days
• Field of Search: 34087001
• CPC Class Codes: G08C 25/00 Arrangements for preventing or correcting errors; Monitoring arrangements
• CPC Class Codes: H04Q 9/00 Arrangements in telecontrol or telemetry systems for selectively calling a substation from a main station, in which substation desired apparatus is selected for applying a control signal thereto or for obtaining measured values therefrom

Abstract

Disclosed are systems, methods, and computer-readable storage media for adaptive telemetry based on in-network cross domain intelligence. A telemetry server can receive at least a first telemetry data stream and a second telemetry data stream. The first telemetry data stream can provide data collected from a first data source and the second telemetry data stream can provide data collected from a second data source. The telemetry server can determine correlations between the first telemetry data stream and the second telemetry data stream that indicate redundancies between data included in the first telemetry data stream and the second telemetry data stream, and then adjust, based on the correlations between the first telemetry data stream and the second telemetry data stream, data collection of the second telemetry data stream to reduce redundant data included in the first telemetry data stream and the second telemetry data stream.

Claims

1. A method comprising:

identifying, by a telemetry server, a telemetry signal from a data source, the telemetry signal indicating that a telemetry data stream will include redundant data for a time period following an occurrence of the telemetry signal; and

adjusting, upon detection of the telemetry signal, data collection of the telemetry data stream to reduce redundant data included in the telemetry data stream and another telemetry data stream from another data source;

wherein the adjusting comprises at least one of the following;

reducing a sampling rate at which data is collected from a data source for inclusion in the telemetry data stream;

adjusting a compression method applied to data collected from a data source for inclusion in the telemetry data stream; and

/or

reducing a reconstruction rate for data included in the telemetry data stream.

2. The method of claim 1, wherein adjusting data collection of the telemetry data stream comprises:

reducing a sampling rate at which data is collected from a data source for inclusion in the telemetry data stream.

3. The method of claim 1, wherein adjusting data collection of the telemetry data stream comprises:

adjusting a compression method applied to data collected from a data source for inclusion in the telemetry data stream.

4. The method of claim 1, wherein adjusting data collection of the telemetry data stream comprises:

reducing a reconstruction rate for data included in the telemetry data stream.

5. The method of claim 1, further comprising:

after adjusting data collection of the telemetry data stream;

determining that the time period following occurrence of the telemetry signal has lapsed, and

readjusting data collection of a data stream to a previous state.

6. The method of claim 1, further comprising:

determining correlations between the telemetry data stream and the another telemetry data stream indicating redundancies between data included in the telemetry data stream and the another telemetry data stream using multimodal deep learning.

7. A system comprising:

one or more computer processors; and

a memory storing instructions that, when executed by the one or more computer processors, cause the system to;

identify a telemetry signal from a data source, the telemetry signal indicating that a telemetry data stream will include redundant data for a time period following an occurrence of the telemetry signal; and

adjusting, upon detection of the telemetry signal, data collection of the telemetry data stream to reduce redundant data included in the telemetry data stream and another telemetry data stream from another data source;

wherein the adjusting comprises at least one of the following;

reducing a sampling rate at which data is collected from a data source for inclusion in the telemetry data stream;

adjusting a compression method applied to data collected from a data source for inclusion in the telemetry data stream; and

/or

reducing a reconstruction rate for data included in the telemetry data stream.

8. The system of claim 7, wherein adjusting data collection of the telemetry data stream comprises:

reducing a sampling rate at which data is collected from a data source for inclusion in the telemetry data stream.

9. The system of claim 7, wherein adjusting data collection of the telemetry data stream comprises:

adjusting a compression method applied to data collected from a data source for inclusion in the telemetry data stream.

10. The system of claim 7, wherein adjusting data collection of the telemetry data stream comprises:

reducing a reconstruction rate for data included in the telemetry data stream.

11. The system, of claim 7, wherein the instructions further cause the system to:

after adjusting data collection of the telemetry data stream;

determine that the time period following occurrence of the telemetry signal has lapsed, and

readjust data collection of a data stream to a previous state.

12. The system of claim 7, further comprising:

determining correlations between the telemetry data stream and the another telemetry data stream indicating redundancies between data included in the telemetry data stream and the another telemetry data stream using multimodal deep learning.

13. A non-transitory computer-readable medium storing instructions that, when executed by one or more computer processors of a computing device, cause the computing device to:

identify a telemetry signal from a data source, the telemetry signal indicating that a telemetry data stream will include redundant data for a time period following an occurrence of the telemetry signal; and

adjust, upon detection of the telemetry signal, data collection of the telemetry data stream to reduce redundant data included in the telemetry data stream and another telemetry data stream from another data source;

wherein the adjust comprises at least one of the following;

reduce a sampling rate at which data is collected from a data source for inclusion in the telemetry data stream;

adjust a compression method applied to data collected from a data source for inclusion in the telemetry data stream; and

/or

reduce a reconstruction rate for data included in the telemetry data stream.

14. The non-transitory computer-readable medium of claim 13, wherein adjusting data collection of the telemetry data stream comprises:

reducing a sampling rate at which data is collected from a data source for inclusion in the telemetry data stream.

15. The non-transitory computer-readable medium of claim 13, wherein adjusting data collection of the telemetry data stream comprises:

adjusting a compression method applied to data collected from a data source for inclusion in the telemetry data stream.

16. The non-transitory computer-readable medium of claim 13, wherein adjusting data collection of the telemetry data stream comprises:

reducing a reconstruction rate for data included in the telemetry data stream.

17. The non-transitory computer-readable medium, of claim 13, wherein the instructions further cause the computing device to:

after adjusting data collection of the telemetry data stream;

determine that the time period following occurrence of the telemetry signal has lapsed, and

readjust data collection of a data stream to a previous state.