Processing

Please wait...

Settings

Settings

Goto Application

1. WO2021001085 - ESTIMATING QUALITY METRIC FOR LATENCY SENSITIVE TRAFFIC FLOWS IN COMMUNICATION NETWORKS

Note: Text based on automatic Optical Character Recognition processes. Please use the PDF version for legal matters

[ EN ]

CLAIMS

What is claimed is:

1. A method (100), in a mobile communication network, of estimating a quality metric for a packet flow associated with an application and carrying latency sensitive content, the method characterized by:

obtaining (102) one or more algorithms for estimating a late loss and the quality metric for the packet flow; and

monitoring (104) network traffic;

classifying (106) packets belonging to the packet flow;

analyzing (108) network traffic parameters for the packets belonging to the packet flow;

based on the obtained late loss algorithm, predicting (1 10) a late loss for the packet flow;

based on the obtained quality metric algorithm and the predicted late loss, predicting (112) a quality metric for the packet flow; and

reporting (1 12) the predicted quality metric.

2. The method (100) of claim 1 wherein the latency sensitive content is voice, and wherein the quality metric is a Quality of Experience, QoE.

3. The method (100) of claim 1 wherein the monitoring (104), classifying (106), analyzing (108), predicting (1 10), predicting (1 12), and reporting (1 12) steps are performed iteratively over two or more of a plurality of monitoring periods.

4. The method (100) of claim 1 wherein obtaining one or more algorithms for estimating late loss and quality metric for the packet flow comprises obtaining the algorithms from an Operations and Maintenance, OAM, function in the mobile network.

5. The method (100) of claim 4 wherein obtaining (102) the algorithms from an OAM, function in the mobile network comprises obtaining the algorithms from the application as part of a Service Level Agreement, SLA, between the application and the network.

6. The method (100) of claim 5 wherein the late loss algorithm describes the maximum allowed jitter before decoder will consider a data frame lost.

7. The method (100) of claim 5 wherein the quality metric algorithm specifies the criteria for late loss statistics and characteristics that are allowed during a specified duration to maintain a determined quality level for one session.

8. The method (100) of claim 7 wherein the quality metric algorithm further specifies one or more mappings between quality levels and network latency or throughput.

9. The method (100) of claim 7 further comprising obtaining from the application packet flow information that facilitates the identification of packet flows carrying latency sensitive content.

10. The method (100) of claim 1 wherein obtaining (102) one or more algorithms for estimating late loss and quality metric for the packet flow comprises training one or more machine learning functions based on network traffic metrics including measured latency, throughput, and packet loss.

1 1. The method (100) of claim 10 wherein the training is based on feedback from the application of the late loss and quality metric as calculated by the application.

12. The method (100) of claim 1 1 wherein the packet flow comprises a QUIC transport protocol connection, and wherein training of a machine learning function for the late loss estimating algorithm is based on QUIC packet characteristics and unencrypted header information, including one or more of QUIC Connection ID, spin bit, and IP header information.

13. The method (100) of claim 12 wherein the application has provided decryption information, and wherein training of the machine learning function for the late loss estimating algorithm is further based on information in encrypted headers.

14. The method (100) of claim 13 further comprising executing a trusted QUIC proxy operative to at least read encrypted QUIC header information in the packet flow, based on the received decryption information.

15. The method (100) of claim 1 wherein the method is performed by a Network Data Analytics Function, NWDAF, in the mobile network, and wherein the packet flow is generated by a Web Real-Time Communication, WebRTC, speech connection traversing the mobile network.

16. The method (100) of claim 15 wherein the NWDAF receives, from a device in the WebRTC connection, end point observed statistics including one or more of late loss, throughput, Round Trip Time, RTT, packet loss, and quality metric.

17. The method (100) of claim 1 wherein analyzing (108) network traffic parameters for the packets belonging to the packet flow comprises, where one or more desired network traffic parameters are not available or visible in the packet flow:

establishing side car network traffic between a probe server and a probe application on a device, the side car network traffic sharing at least part of the packet flow’s path through the mobile network;

monitoring network traffic parameters exposed in the side car network traffic that are not available or visible in the packet flow; and

analyzing network traffic parameters for the packets belonging to the packet flow by analogy to the network traffic parameters in the side car network traffic.

18. The method (100) of claim 17 wherein network traffic parameters exposed in the side car network traffic that are not available or visible in the packet flow include a QUIC spin bit, enabling analysis of downstream Round Trip Timing, RTT.

19. The method (100) of claim 17 wherein network traffic parameters exposed in the side car network traffic that are not available or visible in the packet flow include packet sequence, enabling analysis of packet loss and reordering.

20. A computer program (18) comprising instructions which, when executed on at least a processing circuitry (14) of a node (10), cause the node (10) to carry out steps of the method (100) according to any preceding claim.

21. A computer readable storage medium (16) comprising the computer program according to claim 20.

22. A network node (10) operative in a mobile communication network, and implementing an access gateway, AccessGw, operative to estimate a quality metric for a packet flow associated with an application and carrying latency sensitive content, the network node (10) characterized by:

communication circuitry (12); and

processing circuitry (14) operatively coupled to the communication circuitry (12) and adapted to:

obtain (102) one or more algorithms for estimating a late loss and the quality metric for the packet flow; and

monitor (104) network traffic;

classify (106) packets belonging to the packet flow;

analyze (108) network traffic parameters for the packets belonging to the packet flow;

based on the obtained late loss algorithm, predict (1 10) a late loss for the packet flow;

based on the obtained quality metric algorithm, predict (1 12) a quality metric for the packet flow; and

report (1 14) the predicted quality metric.

23. The network node (10) of claim 22 wherein the latency sensitive content is voice, and wherein the quality metric is a Quality of Experience, QoE.

24. The network node (10) of claim 22 wherein processing circuitry is further operative to perform the monitoring (104), classifying (106), analyzing (108), predicting (1 10), predicting (1 12), and reporting (1 12) steps iteratively over two or more of a plurality of monitoring periods.

25. The network node (10) of claim 22 wherein the processing circuitry (14) is operative to obtain (102) one or more algorithms for estimating late loss and quality metric for the packet flow by obtaining the algorithms from an Operations and Maintenance, OAM, function in the mobile network.

26. The network node (10) of claim 25 wherein the processing circuitry (14) is operative to obtain the algorithms from an OAM function in the mobile network by obtaining the algorithms from the application as part of a Service Level Agreement, SLA, between the application and the network.

27. The network node (10) of claim 26 wherein the late loss algorithm describes the maximum allowed jitter before decoder will consider a data frame lost.

28. The network node (10) of claim 26 wherein the quality metric algorithm specifies the criteria for late loss statistics and characteristics that is allowed during a specified duration to maintain a determined quality level for one session.

29. The network node (10) of claim 28 wherein the quality metric algorithm further specifies one or more mappings between quality levels and network latency or throughput.

30. The network node (10) of claim 28 wherein the processing circuitry (14) is further characterized by being adapted to obtain from the application packet flow information that facilitates the identification of packet flows carrying latency sensitive content.

31. The network node (10) of claim 22 wherein the processing circuitry (14) is operative to obtain (102) one or more algorithms for estimating late loss and quality metric for the packet flow by training one or more machine learning functions based on network traffic metrics including measured latency, throughput, and packet loss.

32. The network node (10) of claim 31 wherein the training is based on feedback from the application of the late loss and quality metric as calculated by the application.

33. The network node (10) of claim 32 wherein the packet flow comprises a QUIC transport protocol connection, and wherein training of a machine learning function for the late loss estimating algorithm is based on QUIC packet characteristics and unencrypted header information, including one or more of QUIC Connection ID, spin bit, and IP header information.

34. The network node (10) of claim 32 wherein the application has provided decryption information, and wherein training of the machine learning function for the late loss estimating algorithm is further based on information in encrypted headers.

35. The network node (10) of claim 34 wherein the processing circuitry (14) is further characterized by being adapted to execute a trusted QUIC proxy operative to at least read encrypted QUIC header information in the packet flow, based on the received decryption information.

36. The network node (10) of claim 22 wherein the network node (10) comprises a Network Data Analytics Function, NWDAF, and wherein the packet flow is generated by a Web Real-Time Communication, WebRTC, speech connection traversing the mobile network.

37. The network node (10) of claim 36 wherein the NWDAF receives, from a device in the WebRTC connection, end point observed statistics including one or more of late loss, throughput, Round Trip Time, RTT, packet loss, and quality metric.

38. The network node (10) of claim 22 wherein the processing circuitry (14) is operative to analyze (108) network traffic parameters for the packets belonging to the packet flow by, where one or more desired network traffic parameters are not available or visible in the packet flow:

establishing side car network traffic between a probe server and a probe application on a device, the side car network traffic sharing at least part of the packet flow’s path through the mobile network;

monitoring network traffic parameters exposed in the side car network traffic that are not available or visible in the packet flow; and

analyzing network traffic parameters for the packets belonging to the packet flow by analogy to the network traffic parameters in the side car network traffic.

39. The network node (10) of claim 38 wherein network traffic parameters exposed in the side car network traffic that are not available or visible in the packet flow include a QUIC spin bit, enabling analysis of downstream Round Trip Timing, RTT.

40. The network node (10) of claim 38 wherein network traffic parameters exposed in the side car network traffic that are not available or visible in the packet flow include packet sequence, enabling analysis of packet loss and reordering.