Congestion control mechanism for streaming media

• US 20040001691A1
• Filed: 06/27/2002
• Published: 01/01/2004
• Est. Priority Date: 06/27/2002
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Li, Zhen, Li, Shipeng, Shen, Goubin
• Granted Patent: US 7,099,954 B2
• Time in Patent Office: Days
• US Class Current: 386/46
• CPC Class Codes: H04L 47/10 Flow control; Congestion control
• CPC Class Codes: H04L 47/193 at the transport layer, e.g. TCP related
• CPC Class Codes: H04L 47/283 in response to processing delays, e.g. caused by jitter or round trip time [RTT]
• CPC Class Codes: H04L 47/36 by determining packet size, e.g. maximum transfer unit [MTU]

Abstract

Streaming media applications, e.g., sent over the Internet with TCP, can suffer from various fluctuations and low utilization due to TCP'"'"'s Additive Increase Multiplicative Decrease (AIMD) congestion control mechanism. Improved methods and apparatuses are provided in which Logarithm-based Rate Control algorithms are employed to better utilize available bandwidth and/or control and smooth the sending rate of the streaming media.

Claims

1. A method for estimating throughput over at least one network connection, the method comprising:

determining packet size information for data to be sent over at least one network connection;

determining round trip time information associated with said network connection;

determining packet loss information associated with said network connection; and

estimating throughput for said network connection using a logarithmic function that considers said packet size information, said round trip time information, and said packet loss information.

2. The method as recited in claim 1, wherein said logarithmic function includes:

3. The method as recited in claim 2, wherein said p represents a packet loss ratio.

4. The method as recited in claim 1, further comprising:

determining a rate change based on said estimated throughput.

5. The method as recited in claim 4, wherein said rate change is based on a derivative of said estimated throughput represented by p and said derivative is proportional to 1/p.

6. The method as recited in claim 4, wherein said logarithmic function includes at least one adjustable parameter that establishes a sharpness of said rate of change.

7. The method as recited in claim 6, wherein said at least one adjustable parameter establishes at least one class of fairness selected from a group comprising a TCP-friendly class of fairness, a bounded-friendly class of fairness, and a streaming-oriented class of fairness.

8. The method as recited in claim 2, wherein said logarithmic function includes a first order logarithmic function of:

9. The method as recited in claim 1, wherein said network connection is configured to support a transmission control protocol (TCP).

10. The method as recited in claim 1, wherein said data includes video data configured using at least one scheme selected from a group comprising Fine Granularity Scale (FGS) and Progressive FGS (PFGS).

11. A computer-readable medium having computer-executable instructions for causing at least one processing unit to perform acts comprising:

determining packet size information for data to be sent over at least one network connection;

determining round trip time information associated with said network connection;

determining packet loss information associated with said network connection; and

estimating throughput for said network connection using a logarithmic function that considers said packet size information, said round trip time information, and said packet loss information.

12. The computer-readable medium as recited in claim 11, wherein said logarithmic function includes:

13. The computer-readable medium as recited in claim 12, wherein said p represents a packet loss ratio.

14. The computer-readable medium as recited in claim 11, further comprising:

determining a rate change based on said estimated throughput.

15. The computer-readable medium as recited in claim 14, wherein said rate change is based on a derivative of said estimated throughput represented by p and said derivative is proportional to 1/p.

16. The computer-readable medium as recited in claim 14, wherein said logarithmic function includes at least one adjustable parameter that establishes a sharpness of said rate of change.

17. The computer-readable medium as recited in claim 16, wherein said at least one adjustable parameter establishes at least one class of fairness selected from a group comprising a TCP-friendly class of fairness, a bounded-friendly class of fairness, and a streaming-oriented class of fairness.

18. The computer-readable medium as recited in claim 12, wherein said logarithmic function includes a first order logarithmic function of:

19. The computer-readable medium as recited in claim 11, wherein said network connection is configured to support a transmission control protocol (TCP).

20. The computer-readable medium as recited in claim 11, wherein said data includes video data configured using at least one scheme selected from a group comprising Fine Granularity Scale (FGS) and Progressive FGS (PFGS).

21. An apparatus comprising:

at least one network interface configurable to operatively couple to at least one network resource through at least one network connection; and

logic operatively coupled to said network interface and configurable to determine packet size information for data to be sent over said network connection, determine round trip time information associated with said network connection, determine packet loss information associated with said network connection, and estimate throughput for said network connection using a logarithmic function that considers said packet size information, said round trip time information, said packet loss information.

22. The apparatus as recited in claim 21, wherein said logarithmic function includes:

23. The apparatus as recited in claim 22, wherein said p represents a packet loss ratio.

24. The apparatus as recited in claim 21, wherein said logic is further configured to determine a rate change based on said estimated throughput.

25. The apparatus as recited in claim 24, wherein said rate change is based on a derivative of said estimated throughput represented by p and said derivative is proportional to 1/p.

26. The apparatus as recited in claim 24, wherein said logarithmic function includes at least one adjustable parameter that establishes a sharpness of said rate of change.

27. The apparatus as recited in claim 26, wherein said at least one adjustable parameter establishes at least one class of fairness selected from a group comprising a TCP-friendly class of fairness, a bounded-friendly class of fairness, and a streaming-oriented class of fairness.

28. The apparatus as recited in claim 22, wherein said logarithmic function includes a first order logarithmic function of:

29. The apparatus as recited in claim 21, wherein said network connection is configured to support a transmission control protocol (TCP).

30. The apparatus as recited in claim 21, wherein said data includes video data configured using at least one scheme selected from a group comprising Fine Granularity Scale (FGS) and Progressive FGS (PFGS).