DYNAMICALLY DETERMINING NODE LOCATIONS TO APPLY LEARNING MACHINE BASED NETWORK PERFORMANCE IMPROVEMENT

• US 20140222983A1
• 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: Dasgupta, Sukrit, Vasseur, Jean-Philippe, Mermoud, Grgory
• Granted Patent: US 9,553,772 B2
• Time in Patent Office: Days
• US Class Current: 709/223
• CPC Class Codes: H04L 41/0677 Localisation of faults
• CPC Class Codes: H04L 41/12 Discovery or management of network topologies
• CPC Class Codes: H04L 41/16 using machine learning or artificial intelligence
• CPC Class Codes: H04L 43/10 Active monitoring, e.g. heartbeat, ping or trace-route

Abstract

In one embodiment, techniques are shown and described relating to dynamically determining node locations to apply learning machine based network performance improvement. In particular, a degree of significance of nodes in a network, respectively, is calculated based on one or more significance factors. One or more significant nodes are then determined based on the calculated degree of significance. Additionally, a nodal region in the network of deteriorated network health is determined, and the nodal region of deteriorated network health is correlated with a significant node of the one or more significant nodes.

Claims

1. A method, comprising:

calculating a degree of significance of nodes in a network, respectively, based on one or more significance factors;

determining one or more significant nodes based on the calculated degree of significance;

determining a nodal region in the network of deteriorated network health; and

correlating the nodal region of deteriorated network health with a significant node of the one or more significant nodes.

2. The method according to claim 1, further comprising:

applying a Learning Machine (LM) technique on nodes of the nodal region of deteriorated network health to improve the network health thereof.

3. The method according to claim 1, further comprising:

probing the significant node in the nodal region of deteriorated network health to determine the network health thereof; and

determining the network health of the nodal region based on the determined network health of the significant node.

4. The method according to claim 1, wherein the one or more significance factors includes a location-based characteristic defining an amount of nodes surrounding a particular node.

5. The method according to claim 4, wherein the location-based characteristic is selected from a group consisting of:

a number of child nodes of the particular node, a number of sibling nodes of the particular node, and a number of child nodes of the number of sibling nodes.

6. The method according to claim 1, wherein the one or more significance factors includes a centrality-based characteristic defining a degree of centrality within the network of a particular node.

7. The method according to claim 1, wherein the one or more significance factors includes a routing-based characteristic defining a degree of transience within the network of a particular node.

8. The method according to claim 7, wherein the routing-based characteristic is selected from a group consisting of:

an amount of unique parent nodes over a period of time of the particular node, and an amount of time by which the particular node has a particular parent node.

9. The method according to claim 1, wherein the determining of the one or more significant nodes comprises:

determining a first node set with a high degree of significance based on one of;

a location-based characteristic, a centrality-based characteristic, and a routing-based characteristic;

determining a second node set with a high degree of significance based on another one of;

the location-based characteristic, the centrality-based characteristic, and the routing-based characteristic; and

calculating an intersection of the first node set and the second node set.

10. The method according to claim 1, wherein the determining of the nodal region of deteriorated network health comprises:

determining network health of nodes in a network;

calculating geo-coordinates of a node with deteriorated network health based on results of the network health determination; and

calculating a nodal region surrounding the node with deteriorated network health, according to a predetermined nodal region size.

11. The method according to claim 10, further comprising:

determining whether a significant node of the one or more significant nodes resides in the nodal region surrounding the node with deteriorated network health;

when the significant node resides in the nodal region, correlating the nodal region with the significant node; and

when the significant node does not reside in the nodal region, increasing the predetermined nodal region size.

12. An apparatus, comprising:

one or more network interfaces that communicate with a network;

a processor coupled to the one or more network interfaces and configured to execute a process; and

a memory configured to store program instructions which contain the process executable by the processor, the process comprising;

calculating a degree of significance of nodes in the network, respectively, based on one or more significance factors;

determining one or more significant nodes based on the calculated degree of significance;

determining a nodal region in the network of deteriorated network health; and

correlating the nodal region of deteriorated network health with a significant node of the one or more significant nodes.

13. The apparatus according to claim 12, wherein the process further comprises:

applying a Learning Machine (LM) technique on nodes of the nodal region of deteriorated network health to improve the network health thereof.

14. The apparatus according to claim 12, wherein the process further comprises:

probing the significant node in the nodal region of deteriorated network health to determine the network health thereof; and

determining the network health of the nodal region based on the determined network health of the significant node.

15. The apparatus according to claim 12, wherein the one or more significance factors includes a location-based characteristic defining an amount of nodes surrounding a particular node.

16. The apparatus according to claim 15, wherein the location-based characteristic is selected from a group consisting of:

a number of child nodes of the particular node, a number of sibling nodes of the particular node, and a number of child nodes of the number of sibling nodes.

17. The apparatus according to claim 12, wherein the one or more significance factors includes a centrality-based characteristic defining a degree of centrality within the network of a particular node.

18. The apparatus according to claim 12, wherein the one or more significance factors includes a routing-based characteristic defining a degree of transience within the network of a particular node.

19. The apparatus according to claim 18, wherein the routing-based characteristic is selected from a group consisting of:

an amount of unique parent nodes over a period of time of the particular node, and an amount of time by which the particular node has a particular parent node.

20. The apparatus according to claim 12, wherein the determining of the one or more significant nodes comprises:

determining a first node set with a high degree of significance based on one of;

a location-based characteristic, a centrality-based characteristic, and a routing-based characteristic;

determining a second node set with a high degree of significance based on another one of;

the location-based characteristic, the centrality-based characteristic, and the routing-based characteristic; and

calculating an intersection of the first node set and the second node set.

21. The apparatus according to claim 12, wherein the determining of the nodal region of deteriorated network health comprises:

determining network health of nodes in a network;

calculating geo-coordinates of a node with deteriorated network health based on results of the network health determination; and

calculating a nodal region surrounding the node with deteriorated network health, according to a predetermined nodal region size.

22. The apparatus according to claim 21, wherein the process further comprises:

determining whether a significant node of the one or more significant nodes resides in the nodal region surrounding the node with deteriorated network health;

when the significant node resides in the nodal region, correlating the nodal region with the significant node; and

when the significant node does not reside in the nodal region, increasing the predetermined nodal region size.

23. A tangible non-transitory computer readable medium storing program instructions that cause a computer to execute a process, the process comprising:

calculating a degree of significance of nodes in a network, respectively, based on one or more significance factors;

determining one or more significant nodes based on the calculated degree of significance;

determining a nodal region in the network of deteriorated network health; and

correlating the nodal region of deteriorated network health with a significant node of the one or more significant nodes.