LBNL research and demonstrations

1
(No Transcript)
2
Acknowledgement of LBNL sponsors

• California Energy Commission PIER program
• Pacific Gas and Electric Company
• New York State Energy and Development Agency
  (NYSERDA)
• US - Environmental Protection Agency
• US Department of Energy

3
LBNL data center activities

• Research Roadmap
• Benchmarking and 23 data center case studies
• Self-benchmarking protocol
• Power supply UPS efficiency studies
• Standby generation losses
• Performance metrics Computation/watt
• Demonstration projects
• EPA report to Congress
• DOE Save Energy Now program

4
Data center energy roadmap

• July, 2003 Research roadmap developed for the
  California Energy Commission
• The problem receded for several years as excess
  data center space was absorbed
• Now the concerns are back

5
Current LBNL CA focus

• Developing LEEDTM type criteria for data centers
• Evaluating modular and scalable cooling solutions
• Promoting use of air economizers
• study filtration options
• research failure modes
• collaborate with ASHRAE
• Demonstrating spray cool technology
• Continuing DC power initiative

6
Current LBNL internal focus

• Designing new supercomputing facility
• Goal - a model of energy efficiency
• Convened workshop of all supercomputer vendors
• Better projections of future power needs
• Pushing the envelop environmental conditions,
  power distribution
• Leading scientific computing facility
• First hand exposure to barriers

7
Current LBNL Federal focus

• EPA activities
• Report to Congress follow-on
• Energy Star server spec
• Energy Star buildings data center metric
• DOE activities
• EERE - Save Energy Now
• Pilot assessments
• Profiler tool
• Assessment tools
• FEMP Technical assistance

8
Why Data Centers?

• Highly energy-intensive and rapidly growing
• Consume 10 to 100 times more energy per square
  foot than a typical office building
• Large potential impact on electricity supplyand
  distribution
• Used about 45 billionkWh in 2005
• At current rate, powerrequirements coulddouble
  in 5 years.

9
Where do data centers fit in?

• Data centers are energy intensive facilities
• Server racks now designed to carry 25 kW or more
• Typical facility 1MW, but can be gt 20 MW
• Information factories
• Nationally 1.5 of US Electricity consumption in
  2006
• Could double in next 5 years
• Critical national and global infrastructure
• Few technology barriers to increased efficiency
• Good candidates for efficiency investments by
  utilities to reduce peak loads

10
IT equipment load density LBNL benchmark
results
11
Rising cost of ownership

• From 2000 2006, computing performance increased
  25x but energy efficiency only 8x
• Amount of power consumed per 1,000 of server
  spending has increased 4x
• Cost of electricity and supporting infrastructure
  now surpasses capital cost of IT equipment
• Perverse incentives --- IT and facilities costs
  separate

Source The Uptime Institute, 2007
12
IT Industry is taking action
www.climatesaverscomputing.org.
www.thegreengrid.com
13
What is US Governments role?

• EPA DOE want to be the catalyst
• Stimulate competition on energy efficiency
• Foster discussions between key stakeholders
• Provide key recommendations (EPA Report to
  Congress)
• Develop standardized protocols and metrics to
  measure energy consumption (e.g., ENERGY STAR)
• Take the lead on assessing and implementing best
  practices in federal datacenters
• Promote initiatives globally

14
Findings from EPA report to Congress

• Trends in data center energy use
• Sector consumed about 61 billion KWh in 2006
• Equates to 1.5 total U.S. electricity
  consumption and 4.5 billion
• Federal sector 6 billion kWh and 450 million
• Projected to increase to 100 billion kWh in 2011
• Equates to 2.5 of total U.S. electricity
  consumption and 7.4 billion

15
Projected electricity useVarious scenarios 2007
- 2011
16
Percentage of electricity delivered to IT
equipment
Average .57
Higher is better
Source LBNL Benchmarking
17
Data Center total electrical demand/ IT equipment
demand
Average 1.83
Lower is better
Source LBNL Benchmarking
18
LBNL design target
LBNLs new supercomputer facility is being
designed to achieve a ratio of 1.2
19
EPA report recommendations

• Standardized performance measurements for IT
  equipment and data centers
• Development of benchmark/metric for data centers
• ENERGY STAR label for servers
• Leadership by Federal Government
• Publicly report energy performance of datacenters
  
• Conduct energy efficiency assessments in all
  datacenters in 2-3 years
• Architect of the Capital, implement
  server-related recommendations in Greening of the
  Capital report

20
Recommendations cont.

• Private sector challenge
• CEOs conduct DOE Save Energy Now energy
  efficiency assessments, implement measures, and
  report performance
• Information on best practices
• Raise awareness and reduce perceived risk of
  energy efficiency improvements in datacenter
• Government partner with private industry case
  studies, best practices
• Research and development
• Develop technologies and practices for datacenter
  energy efficiency (e.g., hardware, software,
  power conversion)

21
DOE data center program objectives

• Build tools, expertise, and strategy in
  collaboration with industry
• Raise awareness of the opportunity
• Recognize industry leaders

22
DOE program strategy

• Build on Save Energy Now model
• DOE deployed software tools,training curriculum,
  and qualifiedexperts to train and work
  withstaff at large U.S. industrial plants.
• 65 of recommended actions nowcompleted, in
  progress, or planned.
• With industry input, develop appropriate tools,
  training, and qualified experts to improve data
  centers.
• Conduct pilots, peer reviewed by industry,
  promote and facilitate industry implementation.

23
Data center program

• Build on Save Energy Now model
• With industry input, develop appropriate tools,
  training, and qualified experts to improve data
  centers.
• Conduct pilots, peer reviewed by industry,
  promote and facilitate industry implementation.

24
DOE near term plan

• Build strong liaisons and partnerships with
  industry
• Develop robust new energy assessment program
• Begin to develop tools and info on best
  practices
• Assessment framework and energy profiling tool
• System level assessment protocol and analysis
  tools
• Partner with industry joint development/peer
  review
• Conduct pilot assessments
• Provide awareness training
• Screen for demonstration opportunities
• Update Federal procurement specifications

25
Energy efficiency opportunities are everywhere

• Better air management
• Move to liquid cooling
• Optimized chilled-water plants
• Use of free cooling

• Load management
• Server innovation

Cooling Equipment
Power Conversion Distribution
Server Load/ComputingOperations

• On-site generation
• Waste heat for cooling
• Use of renewable energy/fuel cells

• High voltage distribution
• Use of DC power
• Highly efficient UPS systems
• Efficient redundancy strategies

AlternativePower Generation
26
Potential benefits of improved data center energy
efficiency

• Save 20 billion kWh per year by 2015
• Worth 2 billion, annual electricity use in 1.8
  million American homes
• Potentially defer need to build 2,300 MW of new
  generating capacity
• Avoid 3.4 million metric tons of carbon emissions
  (like taking 675,000 cars off the road)
• Extend life and capacity of existing data center
  infrastructures

27
Typical data center energy end use
Power Conversions Distribution
100 Units
35 Units
Cooling Equipment
Server Load/ComputingOperations
33 UnitsDelivered
28
Performance varies
The relative percentages of the energy actually
doing computing varied considerably.
Source LBNL case studies
29
U.S. data centerenergy efficiency goal by 2011

• Industry, DOE and partners perform 1,000 Save
  Energy Now assessments using a common protocol
  and tool suite to yield savings of 5 billion kWh
  per year
• Industry-DOE energy efficiency campaign saves an
  additional 20 billion kWh per year
• Total energy savings of 25 billion kWh per year
  by 2011 25 below current trends, which yields
• 2 billion of electricity cost savings
• carbon emission reduction of 5 MTCEE equal to
  the emissions from 3.5 million cars
• All the electricity consumed in the state of Utah
  in one year

30
Web-based resources
http//hightech.lbl.gov/datacenters.html
Good starting point for those seeking efficiency
measures
Best Practices
Benchmark data
Self-benchmarking Guide
Case Studies
Other Reports (demonstrations)
Design Guidance
31
Additional resources
Guides available through PGEs Energy Design
Resources Website
http//hightech.lbl.gov/dctraining/TOP.html
32
How can industry participate?

• Participate in EPA and DOE workshops
• Participate in peer review of products, protocols
  and best practices
• Conduct self-benchmarking and report results
• Use tools from LBNL site and download protocol
  at http//hightech.lbl.gov/datacenters.html
• Participate in DOE data center energy efficiency
  program
• Register on web site to get regular updates

www.eere.energy.gov/datacenters/
33
Contacts
Paul Scheihing Paul.Scheihing_at_ee.doe.gov 202-586-7
234
Andrew Fanara Fanara.Andrew_at_epa.gov
Bill Tschudi wftschudi_at_lbl.gov 510-495-2417
34

• websites
• http//hightech.lbl.gov/datacenters/
• www.energystar.gov/datacenters
• www.eere.energy.gov/datacenters/