TRAFFIC-BASED INFERENCE OF INFLUENCE DOMAINS IN A NETWORK BY USING LEARNING MACHINES

• US 20140222748A1
• Filed: 07/19/2013
• 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: Mermoud, Grgory, Vasseur, Jean-Philippe, Dasgupta, Sukrit
• Granted Patent: US 10,540,605 B2
• Time in Patent Office: Days
• US Class Current: 706/52
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: H04L 41/142 using statistical or mathematical methods
• CPC Class Codes: H04L 41/16 using machine learning or artificial intelligence
• CPC Class Codes: H04L 43/0852 Delays

Abstract

In one embodiment, techniques are shown and described relating to traffic-based inference of influence domains in a network by using learning machines. In particular, in one embodiment, a management device computes a time-based traffic matrix indicating traffic between pairs of transmitter and receiver nodes in a computer network, and also determines a time-based quality parameter for a particular node in the computer network. By correlating the time-based traffic matrix and time-based quality parameter for the particular node, the device may then determine an influence of particular traffic of the traffic matrix on the particular node.

Claims

1. A method, comprising:

computing a time-based traffic matrix indicating traffic between pairs of transmitter and receiver nodes in a computer network;

determining a time-based quality parameter for a particular node in the computer network; and

determining an influence of particular traffic of the traffic matrix on the particular node by correlating the time-based traffic matrix and time-based quality parameter for the particular node.

2. The method as in claim 1, wherein correlating comprises:

performing a linear regression between the traffic matrix and the quality parameter for a given time.

3. The method as in claim 2, wherein the linear regression uses a Variational Bayes Least Square (VBLS) regression algorithm.

4. The method as in claim 1, further comprising:

reducing a dimensionality of possible pairs in the traffic matrix that are to be correlated with the particular node by limiting possible pairs to only transmitter or receiver nodes within communication range of the particular node.

5. The method as in claim 1, further comprising:

reducing a dimensionality of possible pairs in the traffic matrix that are to be correlated with the particular node by limiting possible pairs to only those having a transmitter or receiver node belonging to a path involving the particular node.

6. The method as in claim 5, wherein the quality parameter is a number of retransmissions on the path involving the particular node.

7. The method as in claim 6, further comprising:

including a retransmission counter in a transmitted packet, wherein the retransmission counter is incremented for each retransmission by nodes along the path.

8. The method as in claim 1, further comprising:

probing for the quality parameter.

9. The method as in claim 8, further comprising:

determining when to probe for the quality parameter based on determining a confidence of the quality parameter.

10. The method as in claim 8, wherein probing comprises:

instructing the particular node to timestamp transmitted packets.

11. The method as in claim 1, wherein the influence is based on one of either a per transmitter node influence or a per transmitter and receiver node pair.

12. The method as in claim 1, wherein the quality parameter is one of either a scalar having a single quality metric or a vector having a plurality of quality-based information metrics.

13. The method as in claim 1, wherein the quality parameter is selected from a group consisting of:

a delay; and

a number of retransmissions.

14. An apparatus, comprising:

one or more network interfaces to communicate with 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;

compute a time-based traffic matrix indicating traffic between pairs of transmitter and receiver nodes in the computer network;

determine a time-based quality parameter for a particular node in the computer network; and

determine an influence of particular traffic of the traffic matrix on the particular node by correlating the time-based traffic matrix and time-based quality parameter for the particular node.

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

perform a linear regression between the traffic matrix and the quality parameter for a given time.

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

reduce a dimensionality of possible pairs in the traffic matrix that are to be correlated with the particular node by limiting possible pairs to only transmitter or receiver nodes within communication range of the particular node.

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

reduce a dimensionality of possible pairs in the traffic matrix that are to be correlated with the particular node by limiting possible pairs to only those having a transmitter or receiver node belonging to a path involving the particular node;

wherein the quality parameter is a number of retransmissions on the path involving the particular node.

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

probe for the quality parameter.

19. The apparatus as in claim 18, wherein the process when executed to correlate is further operable to:

determine when to probe for the quality parameter based on determining a confidence of the quality parameter.

20. A tangible, non-transitory, computer-readable media having software encoded thereon, the software when executed by a processor operable to:

compute a time-based traffic matrix indicating traffic between pairs of transmitter and receiver nodes in a computer network;

determine a time-based quality parameter for a particular node in the computer network; and

determine an influence of particular traffic of the traffic matrix on the particular node by correlating the time-based traffic matrix and time-based quality parameter for the particular node.