Dc energy efficiency presentation for psu lecture - ashok bhatla - final

442 views

Published on

Data Center Energy Efficiency - Concepts and Tools

Published in: Technology, Business
0 Comments
0 Likes
Statistics
Notes
  • Be the first to comment

  • Be the first to like this

No Downloads
Views
Total views
442
On SlideShare
0
From Embeds
0
Number of Embeds
2
Actions
Shares
0
Downloads
7
Comments
0
Likes
0
Embeds 0
No embeds

No notes for slide

Dc energy efficiency presentation for psu lecture - ashok bhatla - final

  1. 1. Data Centers – AHP Model Ashok Bhatla and Mohammad Mansour
  2. 2. What are Data Centers“A data center (or data centre ordatacenter or datacenter) is afacility used to house computersystems and associatedcomponents, such astelecommunications and storagesystems. It generally includesredundant or backup powersupplies, redundant datacommunications connections,environmental controls (e.g., airconditioning, fire suppression)and security devices.”(Source: WIKI Definition) Data Centers are Information Factories
  3. 3. Components of a Data Center Telecom Systems Electricity Systems Cooling Systems Humidity Control Systems Security Systems Compute Equipment
  4. 4. Facts about Data Centers Server racks now designed for more than 25+ kW Typical facility ~ 1MW, can be > 20 MW Cost of electricity equaling capital cost of IT equipment 1.5% of all electricity in the U.S. in 2006 ($4.5 Billion) Growing at 12% per year (will double in 5 years) Power and cooling constraints in existing facilities Source : http://www.doe.gov
  5. 5. Major Issues in Data Centers
  6. 6. Data Center Metrics  Power Usage Efficiency (PUE)  Water Usage Effectiveness (WUE)  Energy Reuse Effectiveness (ERE)  Data Center Compute Efficiency (DCcE)  D.C Performance per Watt (DCPpW)Source:http://www.thegreengrid.comhttp://www.hothardware.com
  7. 7. Data Centers in Remote LocationsGoogle in Dalles, OregonMicrosoft and Yahoo in Quincy, Washington.Facebook in Prineville, OregonAmazon in Boardman, OregonIntel in Sacramento
  8. 8. Data Center Map – North AmericaSource : http://www.datacentermap.com/
  9. 9. Purpose of the Study• Develop a Decision Model for data center site selection for companies settings up their own dedicated data centers.• Different Hosting Models like Co location, Managed hosting, Outsourcing etc. are also out of scope.
  10. 10. Goal of the Organization• Setup a modern energy efficient data center with minimum cost, high computing power, at a desired location with low chances of natural disasters – providing best value to the business it serves.
  11. 11. Data Center Infrastructure Standard ANSI/CSA/EIA/TIA 942 Provides standards for planning of data centers, computer rooms, co-location centers, trading floor equipment rooms, technology test labs and similar spaces. Standard for determining the quality of a data center and for comparing data centers with each other.
  12. 12. HDM Define Overall Key DecisionsMethodology Select Different Criteria and Factors Select Different Alternatives Gather Expert Opinion for Criteria & Factors Measure and Identify Relative weights Calculate Impact of criteria on overall decisions Conclude the best possible site for an IT Data Center
  13. 13. Data Center Site Selection – HDM ModelGeographical Financial Political Social Factors Factors Factors Factors (C1) (C2) (C3) (C4) Disaster Land Cost Tax Safety & Security, Crime Avoidance (F21) Structure, Incentives and (F41) (F11) Subsidies Transport Building Availability/ Construction (F31) Accessibility Cost Laws related (F12) (F22) Jobs Creation to Urban (F32) Planning Telecom Variable Costs (F42) – electricity Network cost, property Availability tax (F13) (F23) Power Availability (F14) Water Availability (F15)
  14. 14. Respondents Profile• Expert 1: IT Data Center Manager – responsible for operations of Data Center.•• Expert 2: Facilities Planner – responsible for design and construction of buildings•• Expert 3: IT Manager – responsible for infrastructure which includes all IT equipment•• Expert 4: Finance Analyst – responsible for the NPV and ROI Analysis and Budgeting etc.•• Expert 5: Electrical Engineer – responsible for Cooling and Power Issues in a Data Center
  15. 15. Steps
  16. 16. PCM Calculations y kAv = ∑∑ Cwi ∗ Fwij ∗ Dij i =1 j =1Av = Alternative final valueCwi = Weight of criterion i (i = 1- y )Fwij = Weight of factor j in C i ( j = 1-k )Dij = Alternative ranking for factor j in C iy = Number of criteria in the modelk = Number of factors under C i
  17. 17. Table 4: Ranking of alternatives against each factor Interpretation of the Data Criterion Factors Desirability Values (0-100) Alt1: Quincy, Alt2: Alt3: Alt4: Washington Sacramento, Charlotte, Dalles, California N. Carolina OregonC1: Geographical Factors F11: Disaster Avoidance 83 66 79 82 F12: Transport Availability/ Accessibility 66 85 85 71 F13: Telecom Network Availability 66 84 86 79 F14: Power Availability 87 73 83 83 F15: Water Availability 77 65 74 81C2: Financial Factors F21: Land Cost 85 65 70 85 F22: Building Construction Cost 81 74 72 86 F23: Variable Costs – electricity cost, 87 68 76 83 property taxC3: Political Factors F31: Tax Structure, Incentives and Subsidies 90 73 74 92 F32: Jobs Creation 74 77 75 67C4: Social Factors F41: Safety & Security, Crime 85 69 73 85 F42: Laws related to Urban Planning 84 62 63 83
  18. 18. Discussion
  19. 19. Conclusion
  20. 20. Questions

×