G REEN IPTV

41
GREEN IPTV A Resource and Energy Efficient Network for IPTV

description

G REEN IPTV. A R esource and E nergy E fficient N etwork for IPTV. Main objectives of this lecture. General Illustrate the usual route taken to make good computer science research Specific Exemplify with a resource and energy efficient network for IPTV. Outline. - PowerPoint PPT Presentation

Transcript of G REEN IPTV

Page 1: G REEN IPTV

GREEN IPTV

A Resource and Energy Efficient Network for IPTV

Page 2: G REEN IPTV

Main objectives of this lecture

General Illustrate the usual route taken to make good computer science research

SpecificExemplify with a resource and energy efficient network for IPTV

Page 3: G REEN IPTV

Outline

• Route to make good computer science research

• IPTV today• Research example 1: resource and energy

consumption in IPTV• Research example 2: zapping delay in IPTV• Take-home message

Page 4: G REEN IPTV

Outline

• Route to make good computer science research

• IPTV today• Research example 1: resource and energy

consumption in IPTV• Research example 2: zapping delay in IPTV• Take-home message

Page 5: G REEN IPTV

1. Look for an opportunity

Page 6: G REEN IPTV

2. Identify a problem

Page 7: G REEN IPTV

3. Analyse state of the art

Page 8: G REEN IPTV

4. Propose solution

Page 9: G REEN IPTV

5. Evaluate solution

Page 10: G REEN IPTV

6. Assess relevance

Page 11: G REEN IPTV

Outline

• Route to make good computer science research

• IPTV today• Research example 1: resource and energy

consumption in IPTV• Research example 2: zapping delay in IPTV• Take-home message

Page 12: G REEN IPTV

What is IPTV?

Page 13: G REEN IPTV

A typical IPTV network

STB

PC

TV

DSLAM

Customer Premises

Internet IP Network

TV Head End

.

.

.

Page 14: G REEN IPTV

More details

• All TV channels transmitted always everywhere

• IP multicast used– PIM-SM– Static multicast trees– No traffic engineering

Page 15: G REEN IPTV

Outline

• Route to make good computer science research

• IPTV today• Research example 1: resource and energy

consumption in IPTV• Research example 2: zapping delay in IPTV• Take-home message

Page 16: G REEN IPTV

Why IPTV?

• New service on top of an IP network– Still an infant: around 5 years old

• The sum of all forms of video (IPTV, VoD, P2P) will account for over 91% of global consumer traffic by 2013 [Cisco]

• In the US there are already more than 5 million subscribers, and this number is expected to increase to 15.5 million by 2013 [Piper]

1. opportunities 2. problem 3. state of the art 4. solution 5. evaluation 6. relevance

Page 17: G REEN IPTV

Resource inefficiencies

• 90% of all TV viewing is restricted to a small selection of channels [Cha et al.][Qiu et al.]

1. opportunities 2. problem 3. state of the art 4. solution 5. evaluation 6. relevance

10 100 1000 10000 1000000

20

40

60

80

100

120

140

160

Channels with viewers

Channels broadcasted

Number of users

Num

ber o

f cha

nnel

s

access

metro/core

Page 18: G REEN IPTV

Selective pre-fetching of TV channels

• Instead of each node pre-fetching all TV channels, pre-fetch only a selection of channels

• Pre-fetch active channels (channels for which there are viewers) + a small number of inactive channels

• Room size = number of inactive channels pre-fetched

1. opportunities 2. problem 3. state of the art 4. solution 5. evaluation 6. relevance

Page 19: G REEN IPTV

Trace-driven simulation

• Using huge dataset from a nationwide IPTV provider:– 255k users, 6 months, 150 TV channels, 622

DSLAMs, 11 regions

1. opportunities 2. problem 3. state of the art 4. solution 5. evaluation 6. relevance

Page 20: G REEN IPTV

Results – bandwidth savings

1. opportunities 2. problem 3. state of the art 4. solution 5. evaluation 6. relevance

r = 0 (access)

r = 5 (access)

r = 10 (access)

r = 15 (access)

r = 20 (access)

r = 25 (access)

r = 0 (metro)

All channels

0

20

40

60

80

100

120

140

160

Num

ber o

f cha

nnel

s pre

join

ed 50% bandwidth reduction

33% bandwidth reduction

Page 21: G REEN IPTV

Results – requests affected

1. opportunities 2. problem 3. state of the art 4. solution 5. evaluation 6. relevance

r = 0 (a

ccess)

r = 5 (a

ccess)

r = 10 (a

ccess)

r = 15 (a

ccess)

r = 20 (a

ccess)

r = 25 (a

ccess)

r = 0 (m

etro)

All channels

0%

1%

2%

3%

4%

5%

6%

7%

8%

9%

% o

f req

uest

s

< 2% requests affected

< 0.1% requests affected

Page 22: G REEN IPTV

Is it worth it?

1. opportunities 2. problem 3. state of the art 4. solution 5. evaluation 6. relevance

ConclusionToday probably not, in the future probably yes

Page 23: G REEN IPTV

What about energy savings?

Page 24: G REEN IPTV

Router power consumption model

1. opportunities 2. problem 3. state of the art 4. solution 5. evaluation 6. relevance

Load

Pow

er co

nsum

ption

Max capacity

Max power

DpDl

• We assume the router can turn off ports not in use• Δl and Δp based on real measurements [Chabarek et al.]• 250 edge routers + 50 core routers

Page 25: G REEN IPTV

Is it worth it? (2)

1. opportunities 2. problem 3. state of the art 4. solution 5. evaluation 6. relevance

today 2-4 years 10-15 years0.0

500000.0

1000000.0

1500000.0

2000000.0

2500000.0

3000000.0

€0

€50,000

€100,000

€150,000

€200,000

€250,000

€300,000

€350,000

€400,000

€450,000

€500,000

cost savings (€)

energy savings(kWh)

Ener

gy sa

ving

s pe

r yea

r

Cost

savi

ngs p

er y

ear

ConclusionToday not, in the future maybe

Page 26: G REEN IPTV

Outline

• Route to make good computer science research

• IPTV today• Research example 1: resource and energy

consumption in IPTV• Research example 2: zapping delay in IPTV• Take-home message

Page 27: G REEN IPTV

Zapping delay

• In IPTV this delay can add up to two seconds or more– should be below 430ms[Kooji et al.]

1. opportunities 2. problem 3. state of the art 4. solution 5. evaluation 6. relevance

Page 28: G REEN IPTV

Several solutions proposed

• Video coding and processing techniques• Network level

• Problems of existing solutions:– Complexity– Additional video servers needed

1. opportunities 2. problem 3. state of the art 4. solution 5. evaluation 6. relevance

Page 29: G REEN IPTV

Most zapping is linear...

1. opportunities 2. problem 3. state of the art 4. solution 5. evaluation 6. relevance

Page 30: G REEN IPTV

IPTV today

1. opportunities 2. problem 3. state of the art 4. solution 5. evaluation 6. relevance

IPTV NETWORK

Requesting channel 3

Sending channel 3

Page 31: G REEN IPTV

IPTV with channel smurfing

1. opportunities 2. problem 3. state of the art 4. solution 5. evaluation 6. relevance

IPTV NETWORK

Requesting channel 3

Sending channel 2,3,4

Requesting channel 2,3,4

Page 32: G REEN IPTV

Channel smurfing

• Besides the channel requested, send N neighbouring channels concurrently for C seconds.

1. opportunities 2. problem 3. state of the art 4. solution 5. evaluation 6. relevance

Page 33: G REEN IPTV

Trace-driven simulation

• Using huge dataset from a nationwide IPTV provider:– 255k users, 6 months, 150 TV channels, 622

DSLAMs, 11 regions

1. opportunities 2. problem 3. state of the art 4. solution 5. evaluation 6. relevance

Page 34: G REEN IPTV

Results – requests with no delay

1. opportunities 2. problem 3. state of the art 4. solution 5. evaluation 6. relevance

10 seconds 30 seconds 1 minute 2 minutes Always0%

10%

20%

30%

40%

50%

60%

70%

80%

90%

100%

2 neighbours4 neighbours6 neighbours8 neighbours10 neighboursideal predictor

Concurrent channel time

% o

f sw

itchi

ng re

ques

ts w

ith n

o d

elay

Page 35: G REEN IPTV

10 seconds 30 seconds 1 minute0%

10%

20%

30%

40%

50%

60%

70%

80%

90%

100%

2 neighbours4 neighbours6 neighbours8 neighbours10 neighboursideal predictor

Concurrent channel time

% o

f sw

itchi

ng re

ques

ts w

ith n

o d

elay

Results – requests with no delay (zapping

periods only)

1. opportunities 2. problem 3. state of the art 4. solution 5. evaluation 6. relevance

Page 36: G REEN IPTV

Results – average bandwidth

1. opportunities 2. problem 3. state of the art 4. solution 5. evaluation 6. relevance

10 seconds 30 seconds 1 minute 2 minutes Always0

5

10

15

20

25

30

35

40

2 neighbours4 neighbours6 neighbours8 neighbours10 neighboursideal predictor

Concurrent channel time

Aver

age

band

wid

th co

nsum

ption

(Mbp

s)

Page 37: G REEN IPTV

Is it worth it?

1. opportunities 2. problem 3. state of the art 4. solution 5. evaluation 6. relevance

10 seconds 30 seconds 1 minute 2 minutes Always0%

5%

10%

15%

20%

25%

30%

35%

40%

45%

2 neighbours4 neighbours6 neighbours8 neighbours10 neighbours

Concorrent channel time

Dist

ance

to id

eal p

redi

ctor

• Very simple to implement– Small software upgrade– No additional video servers needed– Performance close to optimal predictor

Page 38: G REEN IPTV

Outline

• Route to make good computer science research

• IPTV today• Research example 1: resource and energy

consumption in IPTV• Research example 2: zapping delay in IPTV• Take-home message

Page 39: G REEN IPTV

Take-home message1. Computer science knowledge can be used in

novel, practical, useful ways2. It is important to build realistic scenarios to

evaluate our ideas3. It is fundamental to accept that any technical

solution has limitations and that these should not be concealed

4. Be aware that a solution to a problem is only relevant if the benefits clearly outweigh the disadvantages

Page 40: G REEN IPTV

Interested in these matters?Any idea what the “G” in GREEN could stand for?

Feel free to contact me:[email protected]

Page 41: G REEN IPTV

References[Cisco] Cisco visual networking index: Forecast and methodology 2008-2013,

2008.[Piper] B. Piper. United states IPTV market sizing: 2009-2013. Technical report,

Strategy Analytics, 2009.[Cha et al.] M. Cha, P. Rodriguez, J. Crowcroft, S. Moon, and X. Amatriain.

Watching television over an IP network. In Proc. ACM IMC, 2008. [Qiu et al.] T. Qiu, Z. Ge, S. Lee, J. Wang, Q. Zhao, and J. Xu. Modeling channel

popularity dynamics in a large IPTV system. In Proc. ACM SIGMETRICS, 2009.[Chabarek et al.] J. Chabarek, J. Sommers, P. Barford, C. Estan, D. Tsiang, and S.

Wright. Power awareness in network design and routing. In Proc. IEEE INFOCOM, 2008.

[Kooji et al.] R. Kooij, K. Ahmed, K. Brunnstr¨om, and K. Acreo. Perceived quality of channel zapping. In proceedings of the IASTED , 2006.