SYSTEMS AND METHODS FOR TRAFFIC MANAGEMENT

• US 20130223207A1
• Filed: 08/07/2012
• Published: 08/29/2013
• Est. Priority Date: 02/24/2012
• Status: Active Grant

• Current Assignee: PNI Canada Acquireco Corp. (Francisco Partners Management LLC)
• Original Assignee: Sandvine Incorporated ULC (Sandvine Corp.)
• Inventors: Dolson, David Cameron, Bouchard, Felix-Antoine R., Olyjnik, Peter M., Bowman, Donald, Flatt, Steven J.
• Granted Patent: US 8,904,025 B2
• Time in Patent Office: Days
• US Class Current: 370/229
• CPC Class Codes: H04L 47/26 using explicit feedback to the source, e.g. choke packets

Abstract

The present disclosure provides a system and a method for managing network traffic. The traffic management system has a quality of experience (QoE) measurement module configured to monitor a QoE metric in real-time. A control module is configured to periodically receive the QoE metric and determine a traffic management action based on the QoE metric. A traffic management module is configured to apply the traffic management action to the network traffic.

Claims

1. A system for managing network traffic comprising:

a quality of experience (QoE) measurement module configured to monitor a QoE metric in real-time;

a control module configured to periodically receive the QoE metric and determine a traffic management action based on the QoE metric; and

a traffic management module configured to apply the traffic management action to the network traffic.

2. A system for managing network traffic according to claim 1, wherein the control module comprises:

a data store for storing QoE metric data;

an analysis module for analyzing the stored QoE metric data and preparing an output action; and

an output module for outputting the output action to the traffic management module.

3. A system according to claim 2, wherein the analysis module is configured to calculate a variable related to the QoE metric over a time interval.

4. A system according to claim 3, wherein the variable related to the QoE metric is selected from a group consisting of:

a change of the QoE metric, a rate of change of the QoE metric, and a function of the change in the QoE metric and a rate of change of the QoE metric.

5. A system according to claim 2, wherein the analysis module is configured to use one or more previous results in analyzing the stored QoE metric data via a feedback loop.

6. A system according to claim 1, wherein the control module comprises a classification module that is configured to receive classification information related to a characteristic of the network traffic and the traffic management action is also based on the classification information.

7. A system according to claim 1, wherein the traffic management action is selected from a group consisting of:

shaping traffic flow, reprioritizing traffic flows using PacketCable multimedia, reprioritizing traffic flows using Diameter Gx, reprioritizing traffic flows based on subscriber driven traffic, reprioritizing traffic flows based on machine driven traffic, reprioritizing traffic flows via tunnel endpoint identification rewrites, reprioritizing traffic flows via a bearer creation, receiving a lower priority for downstream enforcement for traffic flows, and packet marking.

8. A system according to claim 1, wherein the control system uses logic selected from a group consisting of:

adaptive approximation, fuzzy logic, neural networks, genetic algorithms, linear time invariant (LTI) control, and proportional-integral-derivative (PID) control.

9. A system according to claim 1, wherein the QoE metric is selected from a group consisting of:

an access round trip time, a number of measured retransmitted packets, a number of measured duplicate transmission control protocol (TCP) acknowledgments (ACKS), a measured voice over internet protocol (VOIP) mean opinion score (MOS) value, a time to render a hypertext transfer protocol (HTTP) page, a mean time to HTTP load, a video gaming jitter value, a video gaming latency, a ping response time, a domain name system (DNS) response time, a throughput of bulk transfers, a video quality of experience metric, a third party quality of experience metric, and a result of a speed test.

10. A system according to claim 1, wherein determining the traffic management action comprises classifying a traffic flow based on at least one of:

a destination cell of a mobile network;

a destination node of a mobile network;

a destination radio network controller (RNC) of a Third Generation Partner Program (3GPP) mobile network;

a destination service general packet radio service support node (SGSN) of a 3GPP mobile network;

a destination quadrature amplitude modulation (QAM) of a cable network;

a destination Digital Subscriber Line Access Multiplexer (DSLAM) of a Digital Subscriber Line (DSL) network; and

a protocol type.

11. A method for managing network traffic comprising:

monitoring a quality of experience (QoE) metric in real-time;

determining a traffic management action based on the QoE metric; and

applying the traffic management action in real-time to the network traffic.

12. A method according to claim 11, wherein the determining a traffic management action comprises:

storing QoE metric data;

analyzing the stored QoE metric data and preparing an output action; and

outputting the output action to the traffic management module.

13. A method according to claim 12, wherein the analyzing the stored QoE metric data comprises calculating a variable related to the QoE metric data over a time interval.

14. A method according to claim 13, wherein the variable related to the QoE metric is selected from a group consisting of:

a change of the QoE metric, a rate of change of the QoE metric, and a function of the change in the QoE metric and a rate of change of the QoE metric.

15. A method according to claim 12, wherein the analyzing the stored QoE metric data comprises using one or more past results via a feedback loop.

16. A method according to claim 11, further comprising receiving classification information related to a characteristic of the network traffic and wherein the determining the traffic management action is also based on the classification information.

17. A method according to claim 11, wherein the traffic management action is selected from the group consisting of:

shaping traffic flow, reprioritizing traffic flows using PacketCable multimedia, reprioritizing traffic flows using Diameter Gx, reprioritizing traffic flows based on subscriber driven traffic, reprioritizing traffic flows based on machine driven traffic, reprioritizing traffic flows via tunnel endpoint identification rewrites, reprioritizing traffic flows via a bearer creation, receiving a lower priority for downstream enforcement for traffic flows, and packet marking.

18. A method according to claim 11, wherein the determining the traffic management action comprises using logic selected from the group consisting of:

adaptive approximation, fuzzy logic, neural networks, genetic algorithms, linear time invariant (LTI) control, and proportional-integral-derivative (PID) control.

19. A method according to claim 11, wherein the quality of experience metric is selected from the group consisting of:

an access round trip time, a number of measured retransmitted packets, a number of measured duplicate TCP ACKs, a measured VOIP MOS value, a time to render an HTTP page, a mean time to HTTP load, a video gaming jitter value, a video gaming latency, a ping response time, a DNS response time, a throughput of bulk transfers, a video QoE metric, a third party QoE metric, and a result of a speed test.

20. A method according to claim 11, wherein determining the traffic management action comprises classifying a traffic flow based on at least one of:

a destination cell of a mobile network, a destination node of a mobile network, a destination RNC of a 3GPP mobile network, a destination SGSN of a 3GPP mobile network, a destination QAM of a cable network, a destination DSLAM of a DSL network; and

a protocol type.

21. A system for managing network traffic comprising:

a quality of experience (QoE) measurement module configured to monitor a QoE metric in real-time;

a control module configured to periodically receive the QoE metric and report a traffic management action based on the QoE metric; and

a traffic management module configured to receive and apply an adjusted traffic management action to the network traffic.