Charting a Path to Sustainable and Scalable ICT Networks :

Rod Tucker, Rob Ayre, Kerry Hinton Centre for Energy-Efficient Telecommunications University of Melbourne

Po

we

r C

on

su

mp

tio

n (

W)

Year

40% p.a. Data growth

10% p.a. Growth in user numbers

Power Consumption of the Global Internet

2010 2015 2020

109

1011

1010

1012

Global electricity supply

1013

Power Consumption of Internet

(Including servers)

15% p.a. Improvement

in all technology

1.5 billion users

Inside the Network

Ethernet

Switch

OLT Splitter

Metro/Edge Network Core Network

Edge Routers

FTTP

Fiber Core Router

Content Distribution Network

Storage

Server

Server

Storage

Fiber

Access Network

DSL

DSLAM Cu

OLT

ONU

Cabinet

FTTN

DSLAM

Cu

Broadband Network Gateways

Hot

spots

PON

Data Center

Access Network

• Customer home terminal

– ADSL modem, ONU, wireless/cable modem,.

• Access network field equipment

– PON splitter, DSLAM, RF amps,..

• Central office equipment

– OLT, gateway, switch, base station,..

Splitter GPON

PtP

Edge

Node

Cabinet

FTTN

VDSL2Cu

Fiber

Fiber

RF Gateway

HFC

Cu

RF Amp

Node

WiMAXFiber

Splitter

DSLAM

Switch

Base

stationLTE

Data Centers and Content Servers

Racks of Servers

Aggregation Switches

Load-Balancing Switches

Border Routers

Racktop Switches

80% of traffic stays in data center

5% of traffic to other data centers

15% of traffic to users

Energy Efficiency of Key Equipment

Year

Source: O. Tamm et al. 2010

2005 2007 2009 2011 2013 2015 2017 2019 0

2

4

6

8

10

12

14

16

18

20

Ene

rgy

per

Bit

(n

J)

Router

Packet switch

SDH Cross-connect

OTN Cross-connect

Router Energy Consumption Trends

1

10

100

1000

10000

1985 1990 1995 2000 2005 2010 2015

nan

o-J

ou

les

pe

r b

it

Year

Router Energy Efficiency

Cisco AGS

Wellfleet BCN

Cisco GSR 12000

Cisco GSR 12000b

Avici TSR

Cisco CRS 1

Cisco CRS-3

ALU7750

Actual improvement

may be declining

Linear fit gives

~25% improvement pa

Source: Nielsen, ECOC 2011

Transport Energy Consumption Trends

First Trans- Atlantic

Marconi

Trans-Atlantic

Fessenden

Trans-Atlantic

NY - Paris

Key West - Havana

TAT-1

TAT-3

TAT-5 TAT-8

TAT-9

TAT-10

TAT-11

TAT-12/13

Newhaven - Azores

10 - 6

1840 1860 1880 1900 1920 1940 1960 1980 2000 2020

Year

En

erg

y/B

it/1

000 k

m (

mJ)

Wireless

Telegraphy

Coax

Optical + Regen

Optical + EDFA

10 - 4

10 4

10 - 2

10 2

10 6

10 8

1

~15% improvement p.a.

Source: Tucker 2011

Internet Traffic Growth Trends

Co

mp

ou

nd

Ave

rage

Gro

wth

Rat

e (%

)

Source: Kilper et al., JSTQE 2011

Source : Cisco Cloud Index 2011

0

1000

2000

3000

4000

5000

2010 2011 2012 2013 2014 2015

Exab

yte

s/an

nu

m

Year

Data Centre Traffic 2010-2015

Datacentre to user

Between Datacentres

Within Datacentres

Exab

ytes

/an

nu

m

Data Center to User

Between Data

Centers

Within Data

Centers

Cisco Projections of Data Centre Traffic

Access Network Energy Consumption 30

Peak Access Rate (Mb/s)

Po

wer

Per

User

(W)

1 1000

0

FTTP (PON)

100

20

10

10

FTTN

Wireless

HFC

PON is “greenest”

Source: Baliga et al., OFC 2009

Power Consumption of the Global Internet

Year

Po

we

r C

on

su

mp

tio

n (

W)

109

1011

1010

108

1012

2010 2015 2020

Access (PON)

Global electricity supply (3% p.a.)

Total Total (2010 Technology)

15% p.a. technology

improvement

Network Energy per User Bit

Year

Energ

y p

er

User

bit (m

J)

1.0

100

0.1

10

0.01

2010 2015 2020

Total

PON

Core and Metro

Networking

Optical Transport

0.1

1

10

100

Ave

rag

e A

cce

ss R

ate

(M

b/s

)

Gap Between Theory and Practice

Source: Tucker, JSTQE 2011

Year

Routers and

Switches 10-6

10-9

10-10

10-8

10-11

10-7

10-5

10-12

Current

Trends

Lower Bounds

x 104

2010 2015 2020 2025

Ne

two

rk E

ne

rgy p

er

bit (

J)

Transport

X

X X

X

Switches

Transport

X 103

X 102

X 102

Wireline

Access

• Technologies

• Architectures

• Protocols

A Path to Sustainable ICT Networks :

A. Technologies

• Fundamental physical technologies for telecommunications:

– Electronics: primarily CMOS

• Used for signal and data processing and storage

– Optics/photonics

• Primarily used to transport data

• Interface between electronics & optics is evolving as these technologies develop

• Advances are needed in

– Optical and electronic switch technologies

– Optical and electronic interconnects at all levels

– Low-power access technologies, especially wireless

B. Architectures

• Architectures that reduce the number of network hops

– Optical bypass

• Layer 2 rather than Layer 3 where possible

• Dedicated content-delivery networks

Bypass options

1. No bypass:

– All traffic goes to IP layer for processing • All packets processed by IP router

• 10 nJ per bit

• Allows aggregation of incoming traffic flows

• Statistical multiplexing increases utilisation of paths

WDM

Links WDM

Links

IP

Patch

panel

IP Time

Pa

cke

ts

Time

Pa

cke

ts

Time

Pa

cke

ts

Time

Pa

cke

ts

Peak rate

(channel

capacity)

Bypass options (cont’d)

2. Bypass

– TDM layer (electronic cross connect, OTN) • Some traffic streams processed at TDM level

• 1 nJ per bit

– WDM layer (optical cross connect) • Some traffic switched at WDM layer

• < 0.1 nJ per bit

• Switching wavelengths

WDM

OXC

IP

TDM TDM layer

bypass

WDM layer

bypass

TDM

WDM

OXC

C. Protocols

• Service transactions and protocols

• Efficiency of multi-layer protocol suite

• Sleep and standby states

• Energy-efficient Ethernet

• Dynamic rate adaption

Energy-efficient protocols

• Sleep & standby states – Network devices enter low power state when not in use

– Can apply to systems and sub-systems

– Need to ensure network presence is retained

• Use Network Connection Proxy with sleep protocol

– Need to account for state transition energy and time

– May have multiple lower energy states

• IEEE Energy Efficient Ethernet (802.3az) – Low power idle mode when no packets are being sent

– Approved Sept. 2010

– Currently applies to copper interface only; not optical

Energy-efficient protocols

• Dynamic rate adaptation – Modify capacity of network devices in response to traffic demands

– Change clock frequency, processor voltage

– Slower speed to reduce power consumption

– 100 Mbit/s uses 10-20 W less than 10 GE, 4 W less than 1 GE

– Need to allow transition time between rates

• Dynamic rate adaptation and standby states can be combined

Power =C ´Voltage2 frequency

Power

Packets time

time

time

No protocol

Sleep state

Adaptation

Both

Source: Bolla et al., 2011

time

Thank You