Measurement of Network Performance in Transporting Packet Streams

• US 20080239974A1
• Filed: 03/28/2007
• Published: 10/02/2008
• Est. Priority Date: 03/28/2007
• Status: Active Grant

• Current Assignee: Keysight Technologies Singapore (Holdings) Pte. Limited. (Keysight Technologies, Inc.)
• Original Assignee: Ixia (Keysight Technologies, Inc.)
• Inventors: Cattell, Kevin M., Chew, Earl, Choy, Laura
• Granted Patent: US 8,009,687 B2
• Time in Patent Office: Days
• US Class Current: 370/252
• CPC Class Codes: H04L 41/5009 Determining service level performance parameters or violations of service level contracts, e.g. violations of agreed response time or mean time between failures [MTBF]
• CPC Class Codes: H04L 41/509 wherein the managed service relates to media content delivery, e.g. audio, video or TV
• CPC Class Codes: H04L 43/00 Arrangements for monitoring or testing data switching networks
• CPC Class Codes: H04L 43/0829 Packet loss
• CPC Class Codes: H04L 43/0852 Delays
• CPC Class Codes: H04L 43/087 Jitter

Abstract

A method and apparatus for measuring network performance. A packet from a stream of multimedia data packets is received from across a network during a measurement interval. The time interval from the start of the measurement interval to receiving the packet is measured. The response of a buffer to the received packet is determined. The level of the buffer just before the packet arrives is calculated, based on the time interval. The level of the buffer just after the packet arrives is calculated, based on the previous level. A performance measure for the network is determined based on at least one of the two levels.

Claims

1. A method, comprising:

receiving a packet from a stream of multimedia data packets from across a network;

measuring a time interval from the start of a measurement interval to receiving the packet;

determining a response of a buffer to the packet;

calculating a first buffer level just before the packet arrives, wherein the first buffer level is based on the time interval;

calculating a second buffer level just after the packet arrives, wherein the second buffer level is based on the first buffer level; and

determining a performance measure for the network based on at least one of the first and second buffer levels.

2. A method as in claim 1, further comprising:

calculating a third buffer level at the end of the measurement interval; and

determining the performance measure for the network based on at least one of the first, second, and third buffer levels.

3. A method as in claim 2, wherein the buffer is a virtual buffer.

4. A method as in claim 2, wherein the buffer is a physical buffer.

5. A method as in claim 1, wherein the multimedia data packets are encoded according to the International Standard ISO/IEC 13818-1.

6. A method as in claim 1, wherein the performance measure is a measure of packet jitter in the network.

7. A method as in claim 1, wherein the multimedia data packets carry data for a streaming video service.

8. A method as in claim 7, wherein the streaming video service is selected from the group consisting of Internet Protocol television (IPTV), video conferencing, and video-on-demand.

9. A method as in claim 1, further comprising:

determining a loss count of packets that are lost across the network from the stream of multimedia data packets; and

calculating a packet loss rate by dividing the loss count by a specified rate.

10. A method for measuring performance of a network that transports a packet stream, comprising:

receiving a packet from the packet stream at an arrival time in a measurement interval;

determining a packet response of a buffer to the packet;

determining a final response of the buffer when the measurement interval ends;

determining a performance measure for the network based on the packet response and the final response.

11. A method as in claim 10, wherein determining the performance measure is also based on the arrival time, wherein the arrival time is measured relative to the start of the measurement interval.

12. A method as in claim 10, wherein

the measurement interval is one of a sequence of measurement intervals, and

the arrival time is determined in the same manner for the first measurement interval in the sequence as it is for subsequent measurement intervals in the sequence.

13. A method as in claim 10, further comprising:

determining the performance measure during an empty measurement interval in which no packets are received.

14. A method as in claim 10, wherein the performance measure is limited by the length of the measurement interval.

15. A method as in claim 10, further comprising:

determining a loss count of packets that are lost across the network; and

calculating a packet loss rate by dividing the loss count by a specified rate.

16. A system that measures performance of a network that transports a packet stream, comprising:

a packet parser that parses the packet from the packet stream during a measurement interval;

a local clock that determines a packet arrival time measured from the start of the measurement interval; and

a processor that determines a response of a virtual buffer to the packet based on the packet arrival time, and further determines a performance measure for the network based on the response of the virtual buffer.

17. A system as in claim 16, wherein

the processor determines a final response of the virtual buffer when the measurement interval ends, and

the processor determines the performance measure based on the final response.

18. A system as in claim 16, wherein the packet stream is encoded according to the International Standard ISO/IEC 13818-1.

19. A system as in claim 16, wherein the performance measure is a measure of packet jitter in the network.

20. A system as in claim 16, wherein the packet stream carries data for a streaming video service.

21. A system as in claim 20, wherein the streaming video service is selected from the group consisting of Internet Protocol television (IPTV), video conferencing, and video-on-demand.

22. A system as in claim 16, wherein

the processor determines a loss count of packets that are lost across the network from the packet stream, and

the processor calculates a packet loss rate by dividing the loss count by a specified rate.