How Universities can play leadership role in helping reduce global warming and building future zero carbon economy Bill St. Arnaud CANARIE Inc – www.canarie.ca [email_address] Unless otherwise noted all material in this slide deck may be reproduced, modified or distributed without prior permission of the author
Cooling and power issues now a major factor in CI design
But academic CI is often too small: departmental closets and server huggers
Energy use of departmental facilities is growing exponentially creating crises of space, power, and cooling
Unfortunately, almost nothing is known about how to make these shared virtual clusters energy efficient, since there has been no financial motivation to do so
*Sourrce: Tom Deafnti GreenLight
Why ICT and Internet is critical to reducing CO2
Direct emissions of Internet and ICT are important at 2-3% of world emissions but, in order of impact, the most significant contribution we can make is through leveraged, or indirect, emissions reductions.
According to SMART 2020 these represent as much as a 15% reduction opportunity in global emissions.
(And SMART 2020 is one of the most conservative reports on the topic. Others identify even higher potential for savings).
Virtualization and De-materialization Source: European Commission Joint Research Centre, “The Future Impact of ICTs on Environmental Sustainability”, August 2004
Universities and regional optical networks are key
Bits and optical bandwidth are virtually carbon free
Optical networks (as opposed to electronic routed networks) have much smaller carbon footprint
Significant reduced CO2 impacts are possible through use of cyber-infrastructure tools like virtualization, clouds, SOA, grids, Web 2.0, etc.
Research needed in new “zero carbon” computer and network architectures needed to connect remote computers, databases and instruments will be essential
Green IT is best achieved through the collaboration of IT and campus facilities management – power, heat and real estate
Most researchers are not aware of true costs of computation such as power, cooling, and specialized buildings.
Increased energy and computing costs can be offset by technologies such as grid computing and virtualisation.
"Eighty to 90% of a computer's capacity is wasted.
Cardiff University solution to the cost of running super computers for research projects by centralising departments' IT budgets and transferring byte-hungry number-crunching to clusters of smaller high-performance computers.
Sensors and data available via Web Services integrated into Service Oriented Architecture
Architectural Instrumentation for Power/Temperature
Each data center will have 7 rack spaces devoted to 1 type of cluster plus one rack for switches.
Hardware Platform And Software Tools For Hosting Alternative Architectures:
Clusters With Multi-core Processors, Processor/Arithmetical Logic Unit (ALU) Arrays, Specialized Processing Units Such As Graphics Processing Units (Gpgpus), Reconfigurable Co-processing Units Using Field-programmable Gate Arrays (Fpgas), And Hybrid Processing Options Tbd
Instrumented Process Units, Memory, Disk Drives, and Network Interfaces
On January 22-23, Calit2 will co-host with the California Public Utilities Commission a two-day workshop to bring together policy makers, industry, and academics to discuss opportunities for collaboration to use ICT to meet AB32 goals.
Topics to be addressed:
California’s AB 32 and ICT
Power Hungry and Greening Data Center
Reducing Your ICT Footprint
Advances in Energy Sector and Emerging Technology
ICT and Smart Buildings
ICT Based Intelligent Transportation
PROMPT – Next Generation Internet to Reduce Global Warming
Research on router, optical, W/W-less and distributed computing architectures, applications, grids, clouds, Web services, virtualization, dematerialization, remote instrumentation and sensors, etc.
Share infrastructure & maximize lower cost power by “following wind & sun” networks.
Providing free download music, video, and electronic textbooks in exchange for carbon fees on assessed on student parking
Free distant learning courses rather than telecommuting
Free campus wide advanced tele-presence systems in exchange for carbon fees assessed on researcher’s travel
Free mobile cell phone using femto cell and Wifi on public transportation
Free off campus broadband
Other sectors (40%) (e.g. manufacturing, coal mining, export transport) Emissions under direct consumer control (35%) Consumer influenced sectors (25%) (e.g. retail, food and drink, wholesale, agriculture, public sector) Heating Private cars Electricity Other transport Consumers control or influence 60 per cent of emissions http://www.cbi.org.uk/pdf/climatereport2007full.pdf
In general, there are two types of emission trading schemes:
Cap and Trade
Baseline and Credit
Emission trading schemes can be:
Regulated (mandated by a government or regional authority)
Voluntary (entered into on an individual transaction basis, or though ongoing contractual arrangements)
Cap and Trade Regulated Markets – Closed System Source: ClimateCheck Company A Company B Total Before Carbon Trading (Baseline year) Company A Company B Total After Carbon Trading (Future year) Company B implements an internal GHG reduction activity and sells permits to Company A, which uses the permits to meet its cap Net Emission Reduction due to Trade
Baseline and Credit Voluntary and Regulated Markets – Open System Source: ClimateCheck Year 1 Year 2 Year 3 GHG emission reduction calculated as the difference between the actual emissions from an activity (the GHG project) and the emissions of the projects baseline scenario Project GHG Emissions Baseline GHG Emissions Time