SlideShare uma empresa Scribd logo
1 de 28
Bottomline Benefits: Finding the
‘Quick Wins’ for Short-Term ROI
November 10 and 11, 2009
Green IT Expo


Presented by Pat Tiernan / Chris Bullock
Climate Savers Computing Initiative
Agenda



• Climate Savers Computing Overview
• The Problem: IT Energy Waste
• Energy-Efficient Computing: Hardware Advances and Power
  Management
• Business Case for Energy-Efficient Computing
• Case Studies
• Next Steps
Climate Savers Computing Initiative’s Mission
Objectives                                                     Board Members

• Increase the energy efficiency of new computing equipment
• Promote the use of power management to make an impact now
• Shift user base to smart computing practices

Desired results                                                Sponsor Members
• By 2010, improve computing energy efficiency by 50%
       $5.5B savings
• Reduce global CO2 emissions from computing platforms by 54
  million tons per year



       Vision: smart computing practices - highest efficiency possible
Today’s Environment


 • The average desktop PC wastes
                                                                                          30 Watts    20 Watts
   nearly half the power it consumes                                     100 Watts
                                                                         AC power                    50 Watts
 • Servers lose approximately one-                                                          DC        Voltage
   third of their power as heat                                                            Power
                                                                                           Supply
                                                                                                     Regulation
                                                                                                      Module
                                                                                                                    CPU
 • 90 percent of desktops do not
   utilize power management                                                                       Computer
                                                                                                                  motherboard


   settings1




Addressing the problem makes fiscal sense!
   1   Source: US EPA, http://enduse.lbl.gov/info/LBNL­53729_REV.pdf; see also 
       http://www.energystar.gov/ia/products/power_mgt/North_Thurston_Case_Study.pdf and 
       http://www.energystar.gov/ia/partners/prod_development/revisions/downloads/computer/Comp
       uter­PowerMnmt.pdf for additional comments on the extent of power management usage
The Problem: IT Energy Waste


•   Every day 156 million employees in the US, the UK and Germany decide
    whether or not to shut down their PCs
•   1.3 million tonnes of unnecessary CO2 was emitted by UK businesses in
    2009 by not turning off idle PCs wasting nearly £300 million
•   A UK company with 10,000 PCs wastes £168,000 and 828 tonnes of CO2
    annually through not shutting down PCs
•   67 percent of UK employees feel that their companies should be doing more
    to reduce power consumption
•   Only 2 percent of UK employees shut down their PCs at night because they
    were directed by their company to do so
•   50 percent of those who use a PC at work typically choose not to shut down
    their PC at the end of the day
•   PC power costs are the biggest contributory factor to IT costs and can
    account for 25 percent of overall building costs
Energy Demand is Changing the Challenge
    for Data Center Operators


                                                                  Increasing Power Density is
                                                                  Shifting the Balance of Cost

                                                              Yearly
                                                              Cost


                                                                                      2010–2015




28x2U Servers 42x1U Servers 6 BladeCenters   6 BladeCenters
2kW Heat Load 6kW Heat Load 24kW Heat Load   30kW Heat Load
                                                                                           Time
                                                                                       Source: IDC
    Source: Emerson Network Power/Liebert


       Increasing energy demand, and increasing server rack power density, are
                            shifting the sources of cost
Where Data Center Power Goes




7
Portfolio of Energy Savings Actions Available
to Data Center Operators


                                      27% facility
                                      related                Lower Power
                                                             Processors
                                                             High Efficiency Power
                                                             Supplies
                                                             Power Management
                                                             Features
                                                             Blade Servers
                                                             Server Virtualization
  73% IT                                                     Supplemental Cooling
                                                             415V Power Distribution
  related                                                    Architecture
                                                             Cooling Best Practices
                                                             Variable Speed Fan
                                                             Drives
                                                             Monitoring and Optimiz -
                                                             ing Cooling Controls




                                           Source: Emerson Network Power, “Energy Logic”



 73 percent of savings potential comes from
        IT equipment improvements
Energy Savings by Replacing 4-Year-Old,
Inefficient Servers with Fewer New Servers




 2005          184 servers with single­                                               2009                              21 new servers 
vintage                                                                              vintage                            with quad­core 
               core CPUs.  4 years old                                                                                           CPUs




By replacing 4­year­old,                                            Up to                               Annual energy cost
                                                                    9X                                          92%
   relatively inefficient 
servers with new servers
                                                     Reduction in # of 
                                                     servers required                                  estimated reduction


          Source: Intel estimates as of Nov 2008. Performance comparison using SPECjbb2005 bops (business operations per second). Results 
          have been estimated based on internal Intel analysis and are provided for informational purposes only. Any difference in system
          hardware or software design or configuration may affect actual performance. For detailed calculations, configurations and 
          assumptions refer to the legal information slide in backup. 
Desktop Infrastructure Energy Efficiency Improvements


                                               Estimated Annual Energy Consumption

                                                               Four­year­old PC, 
                                                               Switch from CRT 
                                                                                                            Replacing 
                                    1015                        to LCD Display
KWh Consumed per Year




                                                                                                           Old Desktop 
                                                                                                           PC with New 
                                                                           938                             Desktop PC
   (lower is better)




                                                                                                               655                                  New, 
                                                                                                                                                   Power­
                                                                                                                                                  Managed 
                                                                                                                                                  Desktop
                                                                                                                                                                                         New, 
                                                                                                                                                                                        Power­
                                                                                                                                                     229                               Managed 
                                                                                                                                                                                        Laptop

                                                                                                                                                                                           38 

                        Unmanaged Pentium® D                   Unmanaged Pentium® D                   Unmanaged Intel®                     Managed Intel® Core™2  Managed Intel® Core™2 Duo 
                        Processor 945 with CRT                 Processor 945 with LCD               Core™2 Duo Processor                    Duo Processor E6550    Processor T9400 mobile
                               display                                display                       E6550 with LCD display                    with LCD display             platform
                        For system configuration details, please see Appendix. Performance tests/ratings are provided assuming specific computer systems and/or components and reflect the approximate performance
                           of Intel products as measured by those tests. Any difference in system hardware or software design or configuration may affect actual performance. This data may vary from other material
                                                                                                   generated for specific marketing requests.
The business case for PC power management



                  No power mgt. (-) With power mgt. =     Annual savings

Total assets           1              1          1
                       x              x          x
Hours of
operation             24              8         16           +60%
                       x              x          x          savings!
Energy draw
per hour (W)          89             89          5
                       =                   =
kWh/day
(1,000 W = 1kW)      2.13                 .79        =   489 kWh/yr
£/day
(£0.073/kWh)        £0.155             £0.057        =   £35.69/yr
CO2/day
(0.55 kg./kWh)       1.17                 0.43       =   269 Kg CO2/yr
CPM Offers a Compelling ROI

• Labor costs: ~ £3 per seat
   o Identifying appropriate solutions
   o Testing & troubleshooting exceptions
   o Ensuring that sleeping computers do not interfere with
     administrative software updates
• Software costs: ~ £0- 12 per seat
   o Some solutions are free
   o Commercial solutions range from roughly £2-12 per PC
• Vs. benefits of ~ £24 per seat


    Assumptions: 1000 seats; labor costs = 2 weeks of work for one
    network administrator @ £1,508.60 per week
UK Case Studies: Significantly reduced energy
consumption, less emissions, improved profitability


UK Gov Department for Children, Schools and Families
• 53,960 kWhr of electricity and reduction of 35,290 kg of CO2 emissions


ADT
• 36,200 KWhr, 23530 kg of CO2 emissions per month .


Cadbury
• in process of global rollout: 30% energy savings thus far!


The UK Opportunity
• Estimated: 2M Government PCs: 140,000 tonnes CO2 saved per year.
     + UK business: 700,000 tonnes: 10% of UK Carbon committment
Next Steps


1. Join Climate Savers Computing
   in their mission to reduce global
   CO2 emissions from the
   operation of computers by 54
   million tons by 2010
   −   www.climatesaverscomputing.org/
2. For more information and
   additional resources
   −   www.climatesaverscomputing.org/lear
       n/information-and-resources/
3. Also on the Climate Savers
   Computing site
   −   Check out our Toolkit
   −   Browse the Climate Savers
       Computing Product Catalog
   −   Power Management Design
       Guide – coming in
       December
Thank you.

Contact

Pat Tiernan
Executive Director, Climate Savers Computing
admin@climatesaverscomputing
Backup
Energy Waste: Industry Level


This waste adds up quickly.
• The global information and                                               LAN & Office Printers (6%)
                                                                         Telecoms (7%)
  communications technology industry
  accounts for approximately 2 percent of                        Mobile
  global CO2 emissions1                                          Telecoms (9%)                                 PCs and
                                                                                                               Monitors
• Energy costs will be 50 percent of the                                                                       (39%)
  average IT budget in just a few years2
• By 2010, about half of the Forbes                                    Fixed-Line
                                                                       Telecoms
  Global 2000 will spend more on energy
                                                                       (15%)
  than on hardware3                                                                     Servers,
• There are 1 billion+ PCs worldwide,                            Source: Gartner        including cooling
                                                                                        (23%)
  projected to be 2.25 billion by 20154




            1 Source: Gartner, May 2007
            2 Source: Mark, Roy, House Green Lights EPA Data Centers Study, Internetnews.com (July 13, 2006)
            3 Source: Source: Businessweek.com: CEO Guide To Green Computing. From Gartner
            4 Source: Forrester Research
What We are Working to Achieve

Objectives
• Increase the energy efficiency of new computing equipment
• Promote the use of power management to make an impact now
• Shift user base to smart computing practices


Desired results
• Improve computing energy efficiency by 50 percent
   −   $5.5B savings
• Reduce global CO2 emissions from computing platforms by 54 million
  tons per year
Vision: smart computing practices - highest efficiency possible
Taking Action: The CSCI Approach

                                        System, Software &
                                       Component Providers
             IT Departments &
             Consumers                 • High-efficiency
                                         components and
             • Drive policy &
                                         products
               implementation
                                       • Energy management
             • Embed in procurement
                                         capabilities
             • Turn on power
                                       • Product availability &
               management
                                         services
             • Drive savings
                                       • Power management
                                         solutions




             Climate Savers
             Computing Initiative
             • Create awareness and    Alliances
               preference
                                       • Complementary
             • Recruit change agents
                                         programs
             • Drive demand and
                                       • Global influence
               deployment
                                       • Facilitate results
             • Develop and eliminate
               inhibitors
             • Harmonize globally
Defining PC Power Management




►   Actively reducing the energy consumption of operating PCs and monitors
    by enabling lower power states during periods of inactivity — where the PC
    and monitor are drawing energy but no useful work is being performed
    (e.g., nights, weekends, holidays, and workday breaks).
Reducing Energy Costs Drives Green IT
Reducing Facilities Costs Is a Priority
PC Energy Consumption Is Just as Important


Global Carbon Dioxide Emissions
                                          Printers (6%)
        LAN & Office
        Telecoms (7%)
                                                                                                              “Data centers  receive a 
     Mobile                                                                                                   lot of attention because
     Telecoms                                                          PCs &                                    they are an obvious
     (9%)                                                              Monitors                                    concentration.” 
                                                                       (39%)
                                                                                                              “However, the real area 
                               Fixed-Line
                               Telecoms                                                                          where the greatest
                               (15%)                                                                            overall effect can be
                                                                                                               made is at the desktop
                                                 Servers,
                                                                                                              and with client devices.”
                                            including cooling
                                                  (23%)



Source Gartner Inc. “Tera­Architectures A Convergence of New Technologies” by Martin Reynolds July 26, 2007
Energy-Efficient PC Networks

Comparison of the Energy-Usage of PC’s, Based Upon Their Age and 
Technology




   Typical 4-year-old     Typical new Desktop PC,   Typical new Laptop PC,
desktop PC with a CRT,      both without and with         with power
 then with LCD display,     power management             management
   both without power
      management
Entry Points to Network Power Management


 Sensitive users     Less sensitive users   Combination
CPM Offers a Compelling ROI

• Labor costs: ~ $5 per seat
   o Identifying appropriate solutions
   o Testing & troubleshooting exceptions
   o Ensuring that sleeping computers do not interfere
     with administrative software updates
• Software costs: ~ $0-15 per seat
   o Many solutions are free
   o Commercial solutions range from roughly $3-15 per
     PC
• Vs. benefits of ~ $40 per seat

    Assumptions: 1000 seats; labor costs = 2 weeks of work for one
    network administrator @ $2,500 per week
Hardware Refresh ROI



•  Moore’s Law + Design Innovations enable continuous, 
   relatively rapid improvements in computer energy-efficiency
• As a consequence: “Vintage Does Matter.” Older computers 
  are highly wasteful of energy and very costly to run, compared
  to new models that might replace them – PCs as well as data
  center servers
• Power management technology should be used on old and
  new computers alike
Reducing Your Carbon Footprint

      •  For every 1,000 PCs your company begins using aggressive 
         power management, that equates to a savings of £9,000 per
         year, plus air conditioning costs.1
      • Savings will be even greater if you are currently committed to
        carbon neutrality or reduction because you will reduce the
        number of carbon offset credits needed by participating in
        CSCI.
      • Employing aggressive power management on 1,000 PCs can
        save approximately 118.26 tons CO2 per year.2
                           • 1 carbon credit = 1 ton of CO2
                           • 1 carbon credit costs ~ £11.12
                           • 118.26 tons X £11.12 ~ £1,315                                            savings in carbon offset credits
                             per year



1   Assumes system is powered on 2,000 hours per year (40 hrs/week X 50 weeks)
2Aggressive  power management can save 157.62 KW hours per year. 1 KW hour is equivalent to 0.00075 tons CO2.
3$19.42  USD according to current rate as of 8/15/2007 from www.carbonplanet.com

Mais conteúdo relacionado

Mais procurados

Alinean whitepaper: Server Consolidation for Oracle E-Business Suite with IBM...
Alinean whitepaper: Server Consolidation for Oracle E-Business Suite with IBM...Alinean whitepaper: Server Consolidation for Oracle E-Business Suite with IBM...
Alinean whitepaper: Server Consolidation for Oracle E-Business Suite with IBM...IBM India Smarter Computing
 
Eco friendly hd-ds_wp_final
Eco friendly hd-ds_wp_finalEco friendly hd-ds_wp_final
Eco friendly hd-ds_wp_finalGirish Narkar
 
Vamsi :Cloud Progression pulse 2010
Vamsi :Cloud Progression pulse 2010Vamsi :Cloud Progression pulse 2010
Vamsi :Cloud Progression pulse 2010Shanker Sareen
 
Utilities Datapower.2
Utilities Datapower.2Utilities Datapower.2
Utilities Datapower.2David White
 
Coldset Case Study
Coldset Case StudyColdset Case Study
Coldset Case StudyTalyam
 
Power-Grid Load Balancing by Using Smart Home Appliances
Power-Grid Load Balancing by Using Smart Home AppliancesPower-Grid Load Balancing by Using Smart Home Appliances
Power-Grid Load Balancing by Using Smart Home AppliancesValerio Aisa
 
Epcos Capacitors Dealers In India-System controls switchgear
Epcos Capacitors Dealers In India-System controls switchgearEpcos Capacitors Dealers In India-System controls switchgear
Epcos Capacitors Dealers In India-System controls switchgearsystemcontrols
 
Supporting Cloud Article
Supporting Cloud ArticleSupporting Cloud Article
Supporting Cloud Articleeuroamerican
 
Foothill College Energy System
Foothill College Energy SystemFoothill College Energy System
Foothill College Energy SystemRobert Cormia
 
Energen (Energy & Utilities,Oracle/SAP/Power,SUN)
Energen (Energy & Utilities,Oracle/SAP/Power,SUN)Energen (Energy & Utilities,Oracle/SAP/Power,SUN)
Energen (Energy & Utilities,Oracle/SAP/Power,SUN)IBM India Smarter Computing
 
Could you benefit from better Energy use?
Could you benefit from better Energy use?Could you benefit from better Energy use?
Could you benefit from better Energy use?None
 
The business value o f la ge scal e serve r consol i d a t i o n
The business value o f la ge  scal e serve r consol i d a t i o nThe business value o f la ge  scal e serve r consol i d a t i o n
The business value o f la ge scal e serve r consol i d a t i o nIBM India Smarter Computing
 
Energy Saving Tips for Irrigators
Energy Saving Tips for IrrigatorsEnergy Saving Tips for Irrigators
Energy Saving Tips for IrrigatorsElisaMendelsohn
 
Options For Energy Reduction In Data Centres.
Options For Energy Reduction In Data Centres.Options For Energy Reduction In Data Centres.
Options For Energy Reduction In Data Centres.byrnedixon
 
Altruent Offerings
Altruent OfferingsAltruent Offerings
Altruent OfferingsMJHeaden
 
How to enhance performance and reduce energy costs in the midmarket with ibm ...
How to enhance performance and reduce energy costs in the midmarket with ibm ...How to enhance performance and reduce energy costs in the midmarket with ibm ...
How to enhance performance and reduce energy costs in the midmarket with ibm ...IBM India Smarter Computing
 

Mais procurados (19)

Alinean whitepaper: Server Consolidation for Oracle E-Business Suite with IBM...
Alinean whitepaper: Server Consolidation for Oracle E-Business Suite with IBM...Alinean whitepaper: Server Consolidation for Oracle E-Business Suite with IBM...
Alinean whitepaper: Server Consolidation for Oracle E-Business Suite with IBM...
 
Eco friendly hd-ds_wp_final
Eco friendly hd-ds_wp_finalEco friendly hd-ds_wp_final
Eco friendly hd-ds_wp_final
 
Vamsi :Cloud Progression pulse 2010
Vamsi :Cloud Progression pulse 2010Vamsi :Cloud Progression pulse 2010
Vamsi :Cloud Progression pulse 2010
 
Utilities Datapower.2
Utilities Datapower.2Utilities Datapower.2
Utilities Datapower.2
 
Coldset Case Study
Coldset Case StudyColdset Case Study
Coldset Case Study
 
Power-Grid Load Balancing by Using Smart Home Appliances
Power-Grid Load Balancing by Using Smart Home AppliancesPower-Grid Load Balancing by Using Smart Home Appliances
Power-Grid Load Balancing by Using Smart Home Appliances
 
Epcos Capacitors Dealers In India-System controls switchgear
Epcos Capacitors Dealers In India-System controls switchgearEpcos Capacitors Dealers In India-System controls switchgear
Epcos Capacitors Dealers In India-System controls switchgear
 
Supporting Cloud Article
Supporting Cloud ArticleSupporting Cloud Article
Supporting Cloud Article
 
Foothill College Energy System
Foothill College Energy SystemFoothill College Energy System
Foothill College Energy System
 
Sustainable Energy Infrastructure, Transmission and Smart Grids
Sustainable Energy Infrastructure, Transmission and Smart GridsSustainable Energy Infrastructure, Transmission and Smart Grids
Sustainable Energy Infrastructure, Transmission and Smart Grids
 
Energen (Energy & Utilities,Oracle/SAP/Power,SUN)
Energen (Energy & Utilities,Oracle/SAP/Power,SUN)Energen (Energy & Utilities,Oracle/SAP/Power,SUN)
Energen (Energy & Utilities,Oracle/SAP/Power,SUN)
 
Could you benefit from better Energy use?
Could you benefit from better Energy use?Could you benefit from better Energy use?
Could you benefit from better Energy use?
 
Ss Sunoco C Cv
Ss Sunoco C CvSs Sunoco C Cv
Ss Sunoco C Cv
 
The business value o f la ge scal e serve r consol i d a t i o n
The business value o f la ge  scal e serve r consol i d a t i o nThe business value o f la ge  scal e serve r consol i d a t i o n
The business value o f la ge scal e serve r consol i d a t i o n
 
Energy Saving Tips for Irrigators
Energy Saving Tips for IrrigatorsEnergy Saving Tips for Irrigators
Energy Saving Tips for Irrigators
 
Options For Energy Reduction In Data Centres.
Options For Energy Reduction In Data Centres.Options For Energy Reduction In Data Centres.
Options For Energy Reduction In Data Centres.
 
Smarter Computing and Breakthrough IT Economics
Smarter Computing and Breakthrough IT EconomicsSmarter Computing and Breakthrough IT Economics
Smarter Computing and Breakthrough IT Economics
 
Altruent Offerings
Altruent OfferingsAltruent Offerings
Altruent Offerings
 
How to enhance performance and reduce energy costs in the midmarket with ibm ...
How to enhance performance and reduce energy costs in the midmarket with ibm ...How to enhance performance and reduce energy costs in the midmarket with ibm ...
How to enhance performance and reduce energy costs in the midmarket with ibm ...
 

Semelhante a IT Energy Waste - Green IT Expo 2009

Best Practices for Achieving Return on Investment through Energy Efficient Co...
Best Practices for Achieving Return on Investment through Energy Efficient Co...Best Practices for Achieving Return on Investment through Energy Efficient Co...
Best Practices for Achieving Return on Investment through Energy Efficient Co...Climate Savers Computing Initiative
 
An energy, memory, and performance analysis
An energy, memory, and performance analysisAn energy, memory, and performance analysis
An energy, memory, and performance analysisElisabeth Stahl
 
Optimize your infrastructure for better efficiency - Branko Avramovski, Micro...
Optimize your infrastructure for better efficiency - Branko Avramovski, Micro...Optimize your infrastructure for better efficiency - Branko Avramovski, Micro...
Optimize your infrastructure for better efficiency - Branko Avramovski, Micro...Metamorphosis
 
Energy-Efficient Infrastructures For Data Center
Energy-Efficient Infrastructures For Data CenterEnergy-Efficient Infrastructures For Data Center
Energy-Efficient Infrastructures For Data CenterKnurr USA
 
MRI Energy-Efficient Cloud Computing
MRI Energy-Efficient Cloud ComputingMRI Energy-Efficient Cloud Computing
MRI Energy-Efficient Cloud ComputingRoger Rafanell Mas
 
Trilogy - Henk Groenendijk
Trilogy - Henk GroenendijkTrilogy - Henk Groenendijk
Trilogy - Henk GroenendijkHPDutchWorld
 
Tpc Energy Publications July 2 10 B
Tpc Energy Publications July 2 10 BTpc Energy Publications July 2 10 B
Tpc Energy Publications July 2 10 BChris O'Neal
 
Implementing energy efficient data centers
Implementing energy efficient  data centersImplementing energy efficient  data centers
Implementing energy efficient data centersSchneider Electric India
 
Intel Node Manager Intro
Intel Node Manager IntroIntel Node Manager Intro
Intel Node Manager IntroDavid Jenkins
 
DataCenter:: Infrastructure Presentation
DataCenter:: Infrastructure PresentationDataCenter:: Infrastructure Presentation
DataCenter:: Infrastructure PresentationMuhammad Asad Rashid
 
An improved architecture for high efficiency, high-density data centers
An improved architecture for high efficiency, high-density data centersAn improved architecture for high efficiency, high-density data centers
An improved architecture for high efficiency, high-density data centersSchneider Electric India
 
2009 Itc Green It
2009 Itc Green It2009 Itc Green It
2009 Itc Green ItJayMNEA
 
Run-time power management in cloud and containerized environments
Run-time power management in cloud and containerized environmentsRun-time power management in cloud and containerized environments
Run-time power management in cloud and containerized environmentsNECST Lab @ Politecnico di Milano
 
Energy efficiency data center overview
Energy efficiency data center overviewEnergy efficiency data center overview
Energy efficiency data center overviewSchneider Electric
 
CIsco Energy Efficient Data Center
CIsco Energy Efficient Data CenterCIsco Energy Efficient Data Center
CIsco Energy Efficient Data CenterCisco
 
Comprenhensive Utilities & Energy Management
Comprenhensive Utilities & Energy ManagementComprenhensive Utilities & Energy Management
Comprenhensive Utilities & Energy Managementleswilliams93
 
2013-03-11-seminario-artecs-mzapater
2013-03-11-seminario-artecs-mzapater2013-03-11-seminario-artecs-mzapater
2013-03-11-seminario-artecs-mzapatergreendisc
 

Semelhante a IT Energy Waste - Green IT Expo 2009 (20)

Best Practices for Achieving Return on Investment through Energy Efficient Co...
Best Practices for Achieving Return on Investment through Energy Efficient Co...Best Practices for Achieving Return on Investment through Energy Efficient Co...
Best Practices for Achieving Return on Investment through Energy Efficient Co...
 
An energy, memory, and performance analysis
An energy, memory, and performance analysisAn energy, memory, and performance analysis
An energy, memory, and performance analysis
 
Optimize your infrastructure for better efficiency - Branko Avramovski, Micro...
Optimize your infrastructure for better efficiency - Branko Avramovski, Micro...Optimize your infrastructure for better efficiency - Branko Avramovski, Micro...
Optimize your infrastructure for better efficiency - Branko Avramovski, Micro...
 
Energy-Efficient Infrastructures For Data Center
Energy-Efficient Infrastructures For Data CenterEnergy-Efficient Infrastructures For Data Center
Energy-Efficient Infrastructures For Data Center
 
E3 s binghamton
E3 s binghamtonE3 s binghamton
E3 s binghamton
 
MRI Energy-Efficient Cloud Computing
MRI Energy-Efficient Cloud ComputingMRI Energy-Efficient Cloud Computing
MRI Energy-Efficient Cloud Computing
 
Trilogy - Henk Groenendijk
Trilogy - Henk GroenendijkTrilogy - Henk Groenendijk
Trilogy - Henk Groenendijk
 
Tpc Energy Publications July 2 10 B
Tpc Energy Publications July 2 10 BTpc Energy Publications July 2 10 B
Tpc Energy Publications July 2 10 B
 
Implementing energy efficient data centers
Implementing energy efficient  data centersImplementing energy efficient  data centers
Implementing energy efficient data centers
 
Intel Node Manager Intro
Intel Node Manager IntroIntel Node Manager Intro
Intel Node Manager Intro
 
DataCenter:: Infrastructure Presentation
DataCenter:: Infrastructure PresentationDataCenter:: Infrastructure Presentation
DataCenter:: Infrastructure Presentation
 
An improved architecture for high efficiency, high-density data centers
An improved architecture for high efficiency, high-density data centersAn improved architecture for high efficiency, high-density data centers
An improved architecture for high efficiency, high-density data centers
 
2009 Itc Green It
2009 Itc Green It2009 Itc Green It
2009 Itc Green It
 
Run-time power management in cloud and containerized environments
Run-time power management in cloud and containerized environmentsRun-time power management in cloud and containerized environments
Run-time power management in cloud and containerized environments
 
Gamatronics Solutions for Data Centers
Gamatronics Solutions for Data CentersGamatronics Solutions for Data Centers
Gamatronics Solutions for Data Centers
 
Energy efficiency data center overview
Energy efficiency data center overviewEnergy efficiency data center overview
Energy efficiency data center overview
 
CIsco Energy Efficient Data Center
CIsco Energy Efficient Data CenterCIsco Energy Efficient Data Center
CIsco Energy Efficient Data Center
 
Comprenhensive Utilities & Energy Management
Comprenhensive Utilities & Energy ManagementComprenhensive Utilities & Energy Management
Comprenhensive Utilities & Energy Management
 
2013-03-11-seminario-artecs-mzapater
2013-03-11-seminario-artecs-mzapater2013-03-11-seminario-artecs-mzapater
2013-03-11-seminario-artecs-mzapater
 
Kevin burke apc
Kevin burke apcKevin burke apc
Kevin burke apc
 

Último

Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Enterprise Knowledge
 
Unleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubUnleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubKalema Edgar
 
Artificial intelligence in cctv survelliance.pptx
Artificial intelligence in cctv survelliance.pptxArtificial intelligence in cctv survelliance.pptx
Artificial intelligence in cctv survelliance.pptxhariprasad279825
 
Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Mattias Andersson
 
Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 365Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 3652toLead Limited
 
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks..."LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...Fwdays
 
The Ultimate Guide to Choosing WordPress Pros and Cons
The Ultimate Guide to Choosing WordPress Pros and ConsThe Ultimate Guide to Choosing WordPress Pros and Cons
The Ultimate Guide to Choosing WordPress Pros and ConsPixlogix Infotech
 
SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024Lorenzo Miniero
 
Human Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsHuman Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsMark Billinghurst
 
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage CostLeverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage CostZilliz
 
Advanced Computer Architecture – An Introduction
Advanced Computer Architecture – An IntroductionAdvanced Computer Architecture – An Introduction
Advanced Computer Architecture – An IntroductionDilum Bandara
 
Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Commit University
 
H2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo Day
H2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo DayH2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo Day
H2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo DaySri Ambati
 
Story boards and shot lists for my a level piece
Story boards and shot lists for my a level pieceStory boards and shot lists for my a level piece
Story boards and shot lists for my a level piececharlottematthew16
 
How to write a Business Continuity Plan
How to write a Business Continuity PlanHow to write a Business Continuity Plan
How to write a Business Continuity PlanDatabarracks
 
DSPy a system for AI to Write Prompts and Do Fine Tuning
DSPy a system for AI to Write Prompts and Do Fine TuningDSPy a system for AI to Write Prompts and Do Fine Tuning
DSPy a system for AI to Write Prompts and Do Fine TuningLars Bell
 
Vertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering TipsVertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering TipsMiki Katsuragi
 
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024BookNet Canada
 
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek SchlawackFwdays
 

Último (20)

Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024
 
Unleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubUnleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding Club
 
Artificial intelligence in cctv survelliance.pptx
Artificial intelligence in cctv survelliance.pptxArtificial intelligence in cctv survelliance.pptx
Artificial intelligence in cctv survelliance.pptx
 
Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?
 
Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 365Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 365
 
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks..."LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
 
The Ultimate Guide to Choosing WordPress Pros and Cons
The Ultimate Guide to Choosing WordPress Pros and ConsThe Ultimate Guide to Choosing WordPress Pros and Cons
The Ultimate Guide to Choosing WordPress Pros and Cons
 
SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024
 
Human Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsHuman Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR Systems
 
DMCC Future of Trade Web3 - Special Edition
DMCC Future of Trade Web3 - Special EditionDMCC Future of Trade Web3 - Special Edition
DMCC Future of Trade Web3 - Special Edition
 
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage CostLeverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
 
Advanced Computer Architecture – An Introduction
Advanced Computer Architecture – An IntroductionAdvanced Computer Architecture – An Introduction
Advanced Computer Architecture – An Introduction
 
Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!
 
H2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo Day
H2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo DayH2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo Day
H2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo Day
 
Story boards and shot lists for my a level piece
Story boards and shot lists for my a level pieceStory boards and shot lists for my a level piece
Story boards and shot lists for my a level piece
 
How to write a Business Continuity Plan
How to write a Business Continuity PlanHow to write a Business Continuity Plan
How to write a Business Continuity Plan
 
DSPy a system for AI to Write Prompts and Do Fine Tuning
DSPy a system for AI to Write Prompts and Do Fine TuningDSPy a system for AI to Write Prompts and Do Fine Tuning
DSPy a system for AI to Write Prompts and Do Fine Tuning
 
Vertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering TipsVertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering Tips
 
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
 
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
 

IT Energy Waste - Green IT Expo 2009

  • 1. Bottomline Benefits: Finding the ‘Quick Wins’ for Short-Term ROI November 10 and 11, 2009 Green IT Expo Presented by Pat Tiernan / Chris Bullock Climate Savers Computing Initiative
  • 2. Agenda • Climate Savers Computing Overview • The Problem: IT Energy Waste • Energy-Efficient Computing: Hardware Advances and Power Management • Business Case for Energy-Efficient Computing • Case Studies • Next Steps
  • 3. Climate Savers Computing Initiative’s Mission Objectives Board Members • Increase the energy efficiency of new computing equipment • Promote the use of power management to make an impact now • Shift user base to smart computing practices Desired results Sponsor Members • By 2010, improve computing energy efficiency by 50%  $5.5B savings • Reduce global CO2 emissions from computing platforms by 54 million tons per year Vision: smart computing practices - highest efficiency possible
  • 4. Today’s Environment • The average desktop PC wastes 30 Watts 20 Watts nearly half the power it consumes 100 Watts AC power 50 Watts • Servers lose approximately one- DC Voltage third of their power as heat Power Supply Regulation Module CPU • 90 percent of desktops do not utilize power management Computer motherboard settings1 Addressing the problem makes fiscal sense! 1 Source: US EPA, http://enduse.lbl.gov/info/LBNL­53729_REV.pdf; see also  http://www.energystar.gov/ia/products/power_mgt/North_Thurston_Case_Study.pdf and  http://www.energystar.gov/ia/partners/prod_development/revisions/downloads/computer/Comp uter­PowerMnmt.pdf for additional comments on the extent of power management usage
  • 5. The Problem: IT Energy Waste • Every day 156 million employees in the US, the UK and Germany decide whether or not to shut down their PCs • 1.3 million tonnes of unnecessary CO2 was emitted by UK businesses in 2009 by not turning off idle PCs wasting nearly £300 million • A UK company with 10,000 PCs wastes £168,000 and 828 tonnes of CO2 annually through not shutting down PCs • 67 percent of UK employees feel that their companies should be doing more to reduce power consumption • Only 2 percent of UK employees shut down their PCs at night because they were directed by their company to do so • 50 percent of those who use a PC at work typically choose not to shut down their PC at the end of the day • PC power costs are the biggest contributory factor to IT costs and can account for 25 percent of overall building costs
  • 6. Energy Demand is Changing the Challenge for Data Center Operators Increasing Power Density is Shifting the Balance of Cost Yearly Cost 2010–2015 28x2U Servers 42x1U Servers 6 BladeCenters 6 BladeCenters 2kW Heat Load 6kW Heat Load 24kW Heat Load 30kW Heat Load Time Source: IDC Source: Emerson Network Power/Liebert Increasing energy demand, and increasing server rack power density, are shifting the sources of cost
  • 7. Where Data Center Power Goes 7
  • 8. Portfolio of Energy Savings Actions Available to Data Center Operators 27% facility related Lower Power Processors High Efficiency Power Supplies Power Management Features Blade Servers Server Virtualization 73% IT Supplemental Cooling 415V Power Distribution related Architecture Cooling Best Practices Variable Speed Fan Drives Monitoring and Optimiz - ing Cooling Controls Source: Emerson Network Power, “Energy Logic” 73 percent of savings potential comes from IT equipment improvements
  • 9. Energy Savings by Replacing 4-Year-Old, Inefficient Servers with Fewer New Servers 2005 184 servers with single­ 2009  21 new servers  vintage vintage with quad­core  core CPUs.  4 years old CPUs By replacing 4­year­old,  Up to Annual energy cost 9X 92% relatively inefficient  servers with new servers Reduction in # of  servers required estimated reduction Source: Intel estimates as of Nov 2008. Performance comparison using SPECjbb2005 bops (business operations per second). Results  have been estimated based on internal Intel analysis and are provided for informational purposes only. Any difference in system hardware or software design or configuration may affect actual performance. For detailed calculations, configurations and  assumptions refer to the legal information slide in backup. 
  • 10. Desktop Infrastructure Energy Efficiency Improvements Estimated Annual Energy Consumption Four­year­old PC,  Switch from CRT  Replacing  1015  to LCD Display KWh Consumed per Year Old Desktop  PC with New  938 Desktop PC (lower is better) 655 New,  Power­ Managed  Desktop New,  Power­ 229  Managed  Laptop 38  Unmanaged Pentium® D Unmanaged Pentium® D Unmanaged Intel® Managed Intel® Core™2  Managed Intel® Core™2 Duo  Processor 945 with CRT Processor 945 with LCD Core™2 Duo Processor  Duo Processor E6550 Processor T9400 mobile display display E6550 with LCD display with LCD display platform For system configuration details, please see Appendix. Performance tests/ratings are provided assuming specific computer systems and/or components and reflect the approximate performance of Intel products as measured by those tests. Any difference in system hardware or software design or configuration may affect actual performance. This data may vary from other material generated for specific marketing requests.
  • 11. The business case for PC power management No power mgt. (-) With power mgt. = Annual savings Total assets 1 1 1 x x x Hours of operation 24 8 16 +60% x x x savings! Energy draw per hour (W) 89 89 5 = = kWh/day (1,000 W = 1kW) 2.13 .79 = 489 kWh/yr £/day (£0.073/kWh) £0.155 £0.057 = £35.69/yr CO2/day (0.55 kg./kWh) 1.17 0.43 = 269 Kg CO2/yr
  • 12. CPM Offers a Compelling ROI • Labor costs: ~ £3 per seat o Identifying appropriate solutions o Testing & troubleshooting exceptions o Ensuring that sleeping computers do not interfere with administrative software updates • Software costs: ~ £0- 12 per seat o Some solutions are free o Commercial solutions range from roughly £2-12 per PC • Vs. benefits of ~ £24 per seat Assumptions: 1000 seats; labor costs = 2 weeks of work for one network administrator @ £1,508.60 per week
  • 13. UK Case Studies: Significantly reduced energy consumption, less emissions, improved profitability UK Gov Department for Children, Schools and Families • 53,960 kWhr of electricity and reduction of 35,290 kg of CO2 emissions ADT • 36,200 KWhr, 23530 kg of CO2 emissions per month . Cadbury • in process of global rollout: 30% energy savings thus far! The UK Opportunity • Estimated: 2M Government PCs: 140,000 tonnes CO2 saved per year. + UK business: 700,000 tonnes: 10% of UK Carbon committment
  • 14. Next Steps 1. Join Climate Savers Computing in their mission to reduce global CO2 emissions from the operation of computers by 54 million tons by 2010 − www.climatesaverscomputing.org/ 2. For more information and additional resources − www.climatesaverscomputing.org/lear n/information-and-resources/ 3. Also on the Climate Savers Computing site − Check out our Toolkit − Browse the Climate Savers Computing Product Catalog − Power Management Design Guide – coming in December
  • 15. Thank you. Contact Pat Tiernan Executive Director, Climate Savers Computing admin@climatesaverscomputing
  • 17. Energy Waste: Industry Level This waste adds up quickly. • The global information and LAN & Office Printers (6%) Telecoms (7%) communications technology industry accounts for approximately 2 percent of Mobile global CO2 emissions1 Telecoms (9%) PCs and Monitors • Energy costs will be 50 percent of the (39%) average IT budget in just a few years2 • By 2010, about half of the Forbes Fixed-Line Telecoms Global 2000 will spend more on energy (15%) than on hardware3 Servers, • There are 1 billion+ PCs worldwide, Source: Gartner including cooling (23%) projected to be 2.25 billion by 20154 1 Source: Gartner, May 2007 2 Source: Mark, Roy, House Green Lights EPA Data Centers Study, Internetnews.com (July 13, 2006) 3 Source: Source: Businessweek.com: CEO Guide To Green Computing. From Gartner 4 Source: Forrester Research
  • 18. What We are Working to Achieve Objectives • Increase the energy efficiency of new computing equipment • Promote the use of power management to make an impact now • Shift user base to smart computing practices Desired results • Improve computing energy efficiency by 50 percent − $5.5B savings • Reduce global CO2 emissions from computing platforms by 54 million tons per year Vision: smart computing practices - highest efficiency possible
  • 19. Taking Action: The CSCI Approach System, Software & Component Providers IT Departments & Consumers • High-efficiency components and • Drive policy & products implementation • Energy management • Embed in procurement capabilities • Turn on power • Product availability & management services • Drive savings • Power management solutions Climate Savers Computing Initiative • Create awareness and Alliances preference • Complementary • Recruit change agents programs • Drive demand and • Global influence deployment • Facilitate results • Develop and eliminate inhibitors • Harmonize globally
  • 20. Defining PC Power Management ► Actively reducing the energy consumption of operating PCs and monitors by enabling lower power states during periods of inactivity — where the PC and monitor are drawing energy but no useful work is being performed (e.g., nights, weekends, holidays, and workday breaks).
  • 21. Reducing Energy Costs Drives Green IT
  • 22. Reducing Facilities Costs Is a Priority
  • 23. PC Energy Consumption Is Just as Important Global Carbon Dioxide Emissions Printers (6%) LAN & Office Telecoms (7%) “Data centers  receive a  Mobile lot of attention because Telecoms PCs & they are an obvious (9%) Monitors concentration.”  (39%) “However, the real area  Fixed-Line Telecoms where the greatest (15%) overall effect can be made is at the desktop Servers, and with client devices.” including cooling (23%) Source Gartner Inc. “Tera­Architectures A Convergence of New Technologies” by Martin Reynolds July 26, 2007
  • 24. Energy-Efficient PC Networks Comparison of the Energy-Usage of PC’s, Based Upon Their Age and  Technology Typical 4-year-old Typical new Desktop PC, Typical new Laptop PC, desktop PC with a CRT, both without and with with power then with LCD display, power management management both without power management
  • 25. Entry Points to Network Power Management Sensitive users Less sensitive users Combination
  • 26. CPM Offers a Compelling ROI • Labor costs: ~ $5 per seat o Identifying appropriate solutions o Testing & troubleshooting exceptions o Ensuring that sleeping computers do not interfere with administrative software updates • Software costs: ~ $0-15 per seat o Many solutions are free o Commercial solutions range from roughly $3-15 per PC • Vs. benefits of ~ $40 per seat Assumptions: 1000 seats; labor costs = 2 weeks of work for one network administrator @ $2,500 per week
  • 27. Hardware Refresh ROI •  Moore’s Law + Design Innovations enable continuous,  relatively rapid improvements in computer energy-efficiency • As a consequence: “Vintage Does Matter.” Older computers  are highly wasteful of energy and very costly to run, compared to new models that might replace them – PCs as well as data center servers • Power management technology should be used on old and new computers alike
  • 28. Reducing Your Carbon Footprint •  For every 1,000 PCs your company begins using aggressive  power management, that equates to a savings of £9,000 per year, plus air conditioning costs.1 • Savings will be even greater if you are currently committed to carbon neutrality or reduction because you will reduce the number of carbon offset credits needed by participating in CSCI. • Employing aggressive power management on 1,000 PCs can save approximately 118.26 tons CO2 per year.2 • 1 carbon credit = 1 ton of CO2 • 1 carbon credit costs ~ £11.12 • 118.26 tons X £11.12 ~ £1,315 savings in carbon offset credits per year 1 Assumes system is powered on 2,000 hours per year (40 hrs/week X 50 weeks) 2Aggressive power management can save 157.62 KW hours per year. 1 KW hour is equivalent to 0.00075 tons CO2. 3$19.42 USD according to current rate as of 8/15/2007 from www.carbonplanet.com