Energy Consumption in Energy Consumption in IP Networks IP - - PowerPoint PPT Presentation

Energy Consumption in Energy Consumption in IP Networks IP Networks

Rodney S. Tucker, Jayant Baliga, Robert Ayre, Kerry Hinton, Wayne V. Sorin ARC Special Research Centre for Ultra-Broadband Information Networks (CUBIN) University of Melbourne r.tucker@ee.unimelb.edu.au

Energy Consumption of the Network Energy Consumption of the Network

• Greenhouse Impact
• Managing “Hot Spots”
• Getting the energy in
• Getting the heat out
• Energy-limited capacity bottlenecks

Why should we be interested in energy?

• OPEX

Hot spot

• Enabling energy efficiencies in other sectors

Power In

Energy Consumption Grows Energy Consumption Grows

• More users
• More data-intensive applications, e.g. video
• More often and for longer periods
• Increasing demand → operators provide faster access

and increased core capacity

• New applications enabled by faster access

Where are We Heading ? Where are We Heading ?

Summary Summary

• Modeling energy consumption of the Internet
• Core, metro, and access networks
• Energy in network routers
• Energy in optical transmission
• Will (can) optical switching technologies help to reduce

energy consumption?

What is the Carbon Footprint of Telecoms?

Adapted from “SMART 2020: Enabling the low carbon economy in the information age,” GeSI, 2008 www.gesi.org

Global Telecoms Footprint (devices & infrastructure)

Mobile Network

1450+% growth

100 200 300 400 2020 2002

Footprint (MtCO2 p.a.)

Fixed Narrowband Broadband Modems Fixed Broadband Mobile handsets

20X increase

Metro Core Edge Edge Curb Curb Curb Curb Core Core Access Core

ONU ~ 5-10W OLT - 100W 12816 Edge ~ 4 kW CRS-1 ~ 10 kW / rack 0.1 - 1000 Mb/s to the user Fibre Amps WDM Passive Optical Network Packet

• ver

Sonet

Energy Model of Simple IP Network Energy Model of Simple IP Network

Baliga et al., 2007

Core Core Core

OLT - 100W

Number of Hops in the Internet Number of Hops in the Internet

5 10 15 20 25 0.02 0.04 0.06 0.08 0.1 Number of Hops, k

[ ]

Pr H k =

Source: P. Van Mieghem, “Performance Analysis of Computer Systems and Networks”, Cambridge (2006)

2006 Data

AT&T: 20 hops

250 Power (W/user) % of Electricity Supply

Baliga et al., 2007

20 0.5 25 5 Peak Access Rate (Mb/s) 15 100 200 150 50 1.0 10

Power Consumption of IP Network Power Consumption of IP Network

Total Routers Access (PON) SDH/WDM Links

Today’s Internet (~ 2.5 Mb/s)

2007 Technology 20 router hops Contention ratio = 25

Power (W/user) % of Electricity Supply

Baliga et al., 2007

Total

Ultra Ultra-

• Broadband Access

Broadband Access

2007 Technology Peak Access Rate (Mb/s) 2.5 50 100 5.0

Routers Access (PON) SDH/WDM

1000 500 20 router hops Contention ratio = 25

Efficiency Improvement Rate = 0% p.a 5% p.a

Peak Access Rate (Mb/s)

1 100 200 300 400

Total Power Per User (W)

40 60 20

% of Electricity Consumption

1.0 2.0 3.0 10% p.a 20% p.a

Baliga, et al, 2008, unpublished

Technology Improvements Technology Improvements

Energy Consumption in Access Networks Energy Consumption in Access Networks

NEC CM7710T

Splitter PON PtP WiMAX Cabinet Edge Node

Cisco 12816 NEC CM7700S Zyxel VES-1616F-34 Cisco 4503 NEC VF200F6 NEC GM100 Axxcelera ExcelMax CPE Axxcelera ExcelMax BTS

Cabinet Access N/W FTTN with VDSL2

Power Per User (W) Peak Access Rate (Mb/s)

1 100 WiMAX FTTN 40 PtP PON 10 250 Oversubscription = 10

Power Consumption in Access Networks Power Consumption in Access Networks

• Wireless access consumes more energy than optical access
• PON FTTH is “greener” than FTTN

25 20

Total Access (PON) Routers 2.5 25 250 2500 Energy per bit (J) 10-6 10-3 10-8 10-5 10-7 10-4 20 hops ~1 μJ/b WDM Links Peak Access Rate (Mb/s)

Network Network Energy Energy Consumption per Bit Consumption per Bit

~100 μJ/b

• Optical transport (WDM) consumes relatively little energy

< 5% of energy > 25% of CAPEX

• Access network dominates at low rates

– Standby/Sleep mode needed

• Network routers dominate at higher rates

– Need to

• reduce hop count
• improve router efficiency
• manage distribution and replication of content (IPTV)

Observations Observations

Router Throughput Power consumption (W)

Source: METI, 2006, Nordman, 2007

Power Consumption in Routers Power Consumption in Routers

10 100 1,000 10,000 100,000 1,000,000

P = C2/3

where P is in Watts where C is in Mb/s

10 nJ/bit 100 nJ/bit 1

1 Pb/s P ~ 10 1 Tb/s 1 Gb/s 1 Mb/s

?

High-end router: Cisco CRS-1 Linecard Chassis Capacity: 0.64 Tb/s Power: 13.6 kW Switch Fabric Chassis: Power: 8 kW Fully equipped: Multi-rack router Capacity: 41 Tb/s Power ~ 1 MW

Source: Neilsen, 2006; Deutche Telekom, 2007

Per Rack X2 every 18 months

Energy Bottleneck Energy Bottleneck

Optics Electronics Switch Fabrics Buffers Demutiplexers Multiplexers Fibers Forwarding Engine J Switch Fabric O/E Converters Reduced bit rate (i.e. parallel processing)

Electronic Routers Electronic Routers

Line Card

Energy in Electronic and Optical Routers Energy in Electronic and Optical Routers

• G. Epps, Cisco, 2007, ITRS, 2005, R. Tucker, JLT, 2006

Buffer

I/O

Data Plane Control Plane Routing Engine Routing Tables Power supply inefficiency Fans and blowers O/E O/E Forwarding Engine Forwarding Engine

Energy/bit 0.7 nJ 1.0 nJ 0.5 nJ 3.2 nJ 3.5 nJ 1.1 nJ Electronic (2008) Optical Packet Switching is not a promising alternative

Buffer Switch Fabric Buffer

10 nJ Total Electronic (2018) 50 pJ 20 pJ 10 pJ 65 pJ 80 pJ 25 pJ 250 pJ

Switch Control

Optical (2018) 15 pJ 15 pJ 65 pJ 80 pJ 25 pJ 200 pJ ?

Contention Resolution in the Wavelength Domain Contention Resolution in the Wavelength Domain

Switch Fabric Forwarding Engine Forwarding Engine Forwarding Engine

1

λ

n

λ

Fatal Flaw: Require large n for low blocking probability (n ~3 -10 x) Power (W/user)

Total (Conventional router) Peak Access Rate (Mb/s) 50 100 Routers Access WDM 1000 500 WDM 5 X Routers 1.2 X Total (Wavelength-domain contention resolution )

Wong, JLT 2006 Pathiban et al., JLT 2009

Efficiency Improvement Rate = 0% p.a 5% p.a

Peak Access Rate (Mb/s)

1 100 200 300 400

Total Power Per User (W)

40 60 20

% of Electricity Consumption

1.0 2.0 3.0 10% p.a 20% p.a

Baliga, et al, 2008, unpublished

The Challenge The Challenge

10 % - 20 % p.a. continuous improvement in efficiency

Target

Summary Summary

• Energy consumption currently dominated by the access network
• The energy bottleneck in routers is looming
• More significant than the so-called “electronic speed bottleneck”
• Key strategies for efficient network design
• Control energy in the access network (e.g. sleep mode in modems)
• Reduce the hop count (i.e. “agile” optical bypass)
• Caching and content distribution networks
• Continuous improvement in router efficiency