1 / 15

# MPEG-TFRCP: Video Transfer with TCP-friendly Rate Control Protocol - PowerPoint PPT Presentation

MPEG-TFRCP: Video Transfer with TCP-friendly Rate Control Protocol. Department of Informatics and Mathematical Science, Graduate School of Engineering Science, Osaka University, Japan Masaki Miyabayashi E-mail: [email protected] Use of multimedia apps. increases. Introduction.

I am the owner, or an agent authorized to act on behalf of the owner, of the copyrighted work described.

## PowerPoint Slideshow about ' MPEG-TFRCP: Video Transfer with TCP-friendly Rate Control Protocol' - dore

Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.

- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -
Presentation Transcript

### MPEG-TFRCP: Video Transfer with TCP-friendly Rate Control Protocol

Department of Informatics and Mathematical Science,

Graduate School of Engineering Science, Osaka University, Japan

Masaki Miyabayashi

E-mail: [email protected]

ICC2001

Introduction

• Unfairness: TCP vs.UDP

• Congestion control

• UDP: real-time multimedia applications

• No control mechanisms

TCP，UDP co-exist

10

UDP

9

TCP

8

7

6

Rate [Mbps]

5

4

3

TCP performance

2

1

0

0

10

20

30

40

50

60

Time [sec]

“A non-TCP connection should receive the

same share of bandwidth as a TCP connection

if they traverse the same path.”

• TFRCP (TCP-friendly Rate Control Protocol)

• Equation-based control

• Estimate TCP throughput

• AIMD control

ICC2001

r

i

I

-

i

2

r

-

i

2

r

=

r

+

2

i

1

i

MTU

=

r

+

i

1

2

p

3

p

2

+

+

RTT

min(

1

,

3

)

p

(

1

32

)

p

T

0

3

8

MPEG-TFRCP mechanisms

Lossestimation

determine

I

i

control interval

I

I

I

+

-

1

i

i

1

i

sending rate

r

r

r

sender

+

-

i

1

i

1

i

• Estimate network condition from feedback information

• Derive TCP throughput

• Regulate the sending rate

time

lost

lost

• Estimation of RTT, Loss

• how to get feedback information?

• applicability for real system?

• No loss,

• Loss,

• perceived video quality?

Ref [10]： Naoki Wakamiya, Masayuki Murata, and Hideo Miyahara, “On TCP-friendly video transfer,” in Proceedings of SPIE International Symposium on Information Technologies 2000, November 2000.

• Demonstrate applicability of

MPEG-TFRCP to real system

• Perceived video quality at receiver

• MOS (Mean Opinion Score)

• Observation of traffic on the link

• Average throughput

• Rate variation

• Improve MPEG-TFRCP

• Rate control algorithm

• Control interval

ICC2001

TCP

TFRCP/UDP

Senders

ICC2001

mitter

Quantizer

Sender

QoS

Hard

Manager

Report

Report

Scale

Disk

Sender-side

Camera

Encoder

Monitor

video data

RTP

RTP

Decoder

UDP

UDP

target rate

Estimator

RTCP

RTCP

ICC2001

25

1

loss

MPEG-TFRCP

target rate

TCP

video rate

8

20

6

15

packet loss probability

Rate [Mbps]

Rate [Mbps]

0.1

4

10

2

5

0

0

0.01

0

50

100

150

200

0

50

100

150

200

GoP times

= 1.001 sec

GoP times

Original MPEG-TFRCP

Drastic rate variation

• Increasing exponentially, decreasing extremely

Average throughput： TCP 4.4 [Mbps]，TFRCP 2.0 [Mbps]

• Not TCP-friendly

Lower subjective video quality: MOS 1.25

ICC2001

20

15

Average rate [Mbps]

10

MTU

=

r

+

i

1

2

p

3

p

2

+

+

RTT

min(

1

,

3

)

p

(

1

32

)

p

T

5

0

3

8

0

0

10

20

30

40

50

60

Quantizer scale

Improving rate control algorithm

• Quantizer-scale-based Additive Increase algorithm (QAI)

• When no loss occurs,

• Increase sending rate with regard to quantizer scale

Decrease quantizer scale by two

Initially set at 60

• When loss occurs,

• Original algorithm

TCP

MPEG-TFRCP

8

6

Rate [Mbps]

4

2

0

0

50

100

150

200

GoP times

Evaluation of QAI MPEG-TFRCP

Rate variation becomes relatively smaller

Not TCP-friendly

• TCP : 4.3 [Mbps]

• TFRCP : 2.3 [Mbps]

Not attain high-quality video transfer (MOS)

• UDP : 4.25

• Original : 1.25

• QAI : 2.50

Rate variation (QAI)

ICC2001

• Original

• React so quickly against short-term congestion

Extreme rate fluctuation

• Cumulative packet Loss probability (CL)

Number of Lost packets

, within

each control interval

Loss =

Number of transmitted packets

Total number of Lost packets

Loss =

Total number of transmitted packets

, from beginning of the session

ICC2001

0.1

loss

TCP

MPEG-TFRCP

8

0.01

6

packet loss probability

Rate [Mbps]

4

0.001

2

0

0

50

100

150

200

GoP times

Evaluation of QAI-CL

Rate and packet loss probability

variations (QAI-CL)

Rate variation becomes relatively small

Improve video quality

• Original : 1.25

• QAI : 2.50

• QAI-CL : 3.00

accomplish reasonable TCP-friendly control

• TCP : 3.7 [Mbps]

• QAI-CL : 3.0 [Mbps]

ICC2001

• When interval is too short,

• Perceived video quality becomes unstable

• Cannot estimate network condition precisely

• When interval is too long,

• Cannot follow changes of network condition

32-RTT: proposal

é

ù

32

RTT

=

Interval

GoPtime

8-RTT:

ê

ú

GoPtime

ê

ú

shorter

16-RTT:

64-RTT:

longer

96-RTT:

ICC2001

16-RTT or 32-RTT control interval is appropriate

Several settings of control interval

Throughput [Mbps]

MOS

value

Friendliness

TFRCP

TCP

8-RTT

3.10

3.53

0.878

2.25

16-RTT

2.87

3.71

0.774

3.25

32-RTT

2.97

3.70

0.802

3.00

64-RTT

2.51

4.06

0.618

3.33

96-RTT

2.33

4.29

0.543

2.50

ICC2001

• Conclusions

• Evaluated applicability of proposed method to real system

• Improving the TCP-friendliness and perceived video quality by our method (QAI-CL MPEG-TFRCP)

• Future work

• Larger scale network

• Consider RTT variation

ICC2001