DYNAMICALLY ADJUSTING A SET OF MONITORED NETWORK PROPERTIES USING DISTRIBUTED LEARNING MACHINE FEEBACK

• US 20140222996A1
• Filed: 07/12/2013
• Published: 08/07/2014
• Est. Priority Date: 02/05/2013
• Status: Active Grant

• Current Assignee: Cisco Technology, Inc. (Cisco Systems, Inc.)
• Original Assignee: Cisco Technology, Inc. (Cisco Systems, Inc.)
• Inventors: Vasseur, Jean-Philippe, Mermoud, Grgory, Dasgupta, Sukrit
• Granted Patent: US 9,860,140 B2
• Time in Patent Office: Days
• US Class Current: 709/224
• CPC Class Codes: H04L 41/16 using machine learning or artificial intelligence
• CPC Class Codes: H04L 43/02 Capturing of monitoring data
• CPC Class Codes: H04L 43/103 with adaptive polling, i.e. dynamically adapting the polling rate
• CPC Class Codes: Y04S 40/00 Systems for electrical power generation, transmission, distribution or end-user application management characterised by the use of communication or information technologies, or communication or information technology specific aspects supporting them

Abstract

In one embodiment, techniques are shown and described relating to dynamically adjusting a set of monitored network properties using distributed learning machine feedback. In particular, in one embodiment, a learning machine (or distributed learning machines) determines a plurality of monitored network properties in a computer network. From this, a subset of relevant network properties of the plurality of network properties may be determined, such that a corresponding subset of irrelevant network properties based on the subset of relevant network properties may also be determined. Accordingly, the computer network may be informed of the irrelevant network properties to reduce a rate of monitoring the irrelevant network properties.

Claims

1. A method, comprising:

determining a plurality of monitored network properties in a computer network;

determining a subset of relevant network properties of the plurality of network properties;

determining a corresponding subset of irrelevant network properties based on the subset of relevant network properties; and

informing the computer network of the irrelevant network properties to reduce a rate of monitoring the irrelevant network properties.

2. The method as in claim 1, wherein reducing the rate is ceasing monitoring the irrelevant network properties.

3. The method as in claim 1, wherein informing further comprises:

indicating a period of time for which the rate of monitoring is to be reduced.

4. The method as in claim 1, wherein informing the computer network comprises:

informing, by a learning machine, a network management server (NMS) responsible for informing the computer network.

5. The method as in claim 1, wherein determining the subset of relevant network properties comprises:

determining one or more network properties used to compute a regression function mapping a network performance metric to a corresponding set of monitored network properties.

6. The method as in claim 1, wherein determining the subset of relevant network properties comprises:

determining one or more network properties used in a learning machine inference algorithm.

7. The method as in claim 6, wherein the inference algorithm is a Variational Bayes Least Square (VBLS) algorithm.

8. The method as in claim 6, wherein the determined subset of irrelevant network properties comprises network properties not used in the inference algorithm.

9. The method as in claim 6, wherein the determined subset of irrelevant network properties comprises network properties assigned a weight below a particular threshold for the inference algorithm.

10. The method as in claim 9, wherein the weight is zero.

11. The method as in claim 1, wherein determining the subset of relevant network properties comprises:

determining one or more network properties that have a value measure of variability above a given threshold, wherein irrelevant network properties have a value measure of variability below the given threshold.

12. An apparatus, comprising:

one or more network interfaces to communicate within a computer network;

a processor coupled to the network interfaces and adapted to execute one or more processes; and

a memory configured to store a process executable by the processor, the process when executed operable to;

determine a plurality of monitored network properties in a computer network;

determine a subset of relevant network properties of the plurality of network properties;

determine a corresponding subset of irrelevant network properties based on the subset of relevant network properties; and

inform the computer network of the irrelevant network properties to reduce a rate of monitoring the irrelevant network properties.

13. The apparatus as in claim 12, wherein reducing the rate is ceasing monitoring the irrelevant network properties.

14. The apparatus as in claim 12, wherein the process when executed to inform is further operable to:

indicate a period of time for which the rate of monitoring is to be reduced.

15. The apparatus as in claim 12, wherein the process when executed to inform the computer network is further operable to:

inform a network management server (NMS) responsible for informing the computer network.

16. The apparatus as in claim 12, wherein the process when executed to determine the subset of relevant network properties is further operable to:

determine one or more network properties used to compute a regression function mapping a network performance metric to a corresponding set of monitored network properties.

17. The apparatus as in claim 12, wherein the process when executed to determine the subset of relevant network properties is further operable to:

determine one or more network properties used in a learning machine inference algorithm.

18. The apparatus as in claim 17, wherein the determined subset of irrelevant network properties comprises network properties not used in the inference algorithm.

19. The apparatus as in claim 18, wherein the determined subset of irrelevant network properties comprises network properties assigned a weight below a particular threshold for the inference algorithm.

20. The apparatus as in claim 12, wherein the process when executed to determine the subset of relevant network properties is further operable to:

determine one or more network properties that have a value measure of variability above a given threshold, wherein irrelevant network properties have a value measure of variability below the given threshold.

21. Logic encoded in one or more non-transitory tangible media for execution and when executed by a machine operable to:

determine a plurality of monitored network properties in a computer network;

determine a subset of relevant network properties of the plurality of network properties;

determine a corresponding subset of irrelevant network properties based on the subset of relevant network properties; and

inform the computer network of the irrelevant network properties to reduce a rate of monitoring the irrelevant network properties.