Method and system for controlling an operation of an application by classifying an application type using data bearer characteristics

Patent metadata

Field	Value
Publication number	US-9780997-B2
Application number	US-201514610598-A
Country	US
Kind code	B2
Filing date	Jan 30, 2015
Priority date	Jan 30, 2015
Publication date	Oct 3, 2017
Grant date	Oct 3, 2017

Abstract

An application type of a bearer is classified by computing statistics vectors of bearer metrics and locating points on a label map corresponding to the statistics vectors to obtain application type information. The application type information is exported to a network node to control an operation of application. The bearer metrics include bearer identifier information and bearer condition information, where the bearer condition information includes channel condition information and cell congestion level information. The bearers are paired, such that uplink and downlink bearers for a same application are identified, so that paired bearers are classified together. The label map is produced using previously classified bearer information to calculate cluster centroids and cluster regions that define portions of the map for particular application types. The bearer is classified by determining which cluster region is closest to points on the label map that are associated with the statistics vectors for a particular bearer.

First claim

What is claimed is:

1. A method of controlling an operation of an application in a communication network by classifying an application type, comprising:
obtaining, by one or more processors of at least one network node, bearer metrics for one or more bearers in the communication network;
computing, by the one or more processors, statistics vectors for the bearer metrics;
classifying, by the one or more processors, the application type by locating points on a label map corresponding to the statistics vectors to obtain application type information that is associated with the one or more bearers; and
exporting, by the one or more processors, the application type information to a node processor of a network node to control an operation of an application by adjusting a scheduling of data communications for the one or more bearers.

2. The method of claim 1 , wherein the exporting includes exporting the application type information to at least one of a node processor running an application function, a node processor of an e-Node B, and a node processor of a user equipment, and a node processor of a management entity node in order to control the operation of the application.

3. The method of claim 1 , wherein the obtaining includes obtaining per bearer metrics that are at least one of a radio link control (RLC) buffer size, a physical resource block (PRB) utilization, a transmission burst interval and an idle time interval.

4. The method of claim 3 , wherein the obtaining further includes obtaining bearer condition information and bearer identifier information, the bearer condition information including at least one of bearer channel condition information and cell congestion level information.

5. The method of claim 1 , wherein the computing further includes,
identifying pairs of bearers associated with the obtained bearer metrics, wherein each pair of bearers belongs to a same application and includes a first bearer carrying uplink transmissions and a second bearer carrying downlink transmissions,
computing the statistics vectors for bearer metrics for each of the identified pairs of bearers.

6. The method of claim 1 , further comprising:
obtaining the label map by,
obtaining bearer reports on previously classified bearers,
calculating cluster centroids and defined cluster regions for at least one particular application type,
the label map including the calculated cluster centroids and defined cluster regions for the at least one particular application type.

7. The method of claim 6 , wherein the bearer reports include previously determined bearer information on a per-bearer basis for the previously classified bearers including at least one of bearer identifiers, previously identified application types, previously computed statistics vectors, previously determined bearer conditions, and previously determined information on pairings of the bearers.

8. The method of claim 6 , wherein the classifying further includes,
locating points on or near the defined cluster regions of the label map that correspond to the statistics vectors, wherein the defined cluster region associated with the at least one particular application type that is closest to each located point is determined to be the classified application type.

9. The method of claim 8 , wherein the steps associated with the obtaining of the label map is repeated as application types for additional bearers are classified into one of the particular application types.

10. A network node in a communication network, comprising:
one or more processors configured to,
obtain bearer metrics for one or more bearers in the communication network,
compute statistics vectors for the bearer metrics,
classify the application type by locating points on a label map corresponding to the statistics vectors to obtain application type information that is associated with the one or more bearers, and
export the application type information to a processor network node to control an operation of an application by adjusting a scheduling of data communications for the one or more bearers.

11. The network node of claim 10 , wherein the one or more processors is further configured to export the application type information by exporting the application type information to at least one of a node processor running an application function, a node processor of an e-Node B, and node processor of a user equipment, and a node processor of a management entity node in order to control the operation of the application.

12. The network node of claim 10 , wherein the one or more processors is further configured to obtain the bearer metrics by obtaining per bearer metrics that are at least one of a radio link control (RLC) buffer size, a physical resource block (PRB) utilization, a transmission burst interval and an idle time interval.

13. The network node of claim 12 , wherein the one or more processors is further configured to obtain the bearer metrics by obtaining bearer condition information and bearer identifier information, the bearer condition information including at least one of bearer channel condition information and cell congestion level information.

14. The network node of claim 10 , wherein the one or more processors is further configured to compute statistics vectors by,
identifying pairs of bearers associated with the obtained bearer metrics, wherein each pair of bearers belongs to a same application and includes a first bearer carrying uplink transmissions and a second bearer carrying downlink transmissions,
computing the statistics vectors for bearer metrics for each of the identified pairs of bearers.

15. The network node of claim 10 , wherein the one or more processors is further configured to,
obtain the label map by,
obtaining bearer reports on previously classified bearers,
calculating cluster centroids and defined cluster regions for at least one particular application type,
the label map including the calculated cluster centroids and defined cluster regions for the at least one particular application type.

16. The network node of claim 15 , wherein the bearer reports include previously determined bearer information on a per-bearer basis for the previously classified bearers including at least one of bearer identifiers, previously identified application types, previously computed statistics vectors, previously determined bearer conditions, and previously determined information on pairings of the bearers.

17. The network node of claim 15 , wherein the one or more processors is further configured to classify the application type by,
locating points on or near the defined cluster regions of the label map that correspond to the statistics vectors, wherein the defined cluster region associated with the at least one particular application type that is closest to each located point is determined to be the classified application type.

18. The network node of claim 17 , wherein the one or more processors is further configured to repeat the steps associated with the obtaining of the label map as application types for additional bearers are classified into one of the particular application types.

Assignees

• Grinshpun Edward
• Liao Qi
• Faucher David
• Sayeed Zulfiquar
• Sharma Sameer
• Alcatel Lucent

Inventors

• Grinshpun Edward
• Liao Qi
• Faucher David
• Sayeed Zulfiquar
• Sharma Sameer

Classifications

• H04W24/10

  Scheduling measurement reports {; Arrangements for measurement reports} · CPC title

• H04L41/0803 Primary

  Configuration setting · CPC title

• H04W76/021

  Electricity · mapped topic

• H04W24/08 Primary

  Testing, {supervising or monitoring} using real traffic · CPC title

• H04L47/2441

  relying on flow classification, e.g. using integrated services [IntServ] · CPC title