Dc energy efficiency presentation for psu lecture - ashok bhatla - final
1. Data Centers – AHP Model
Ashok Bhatla and
Mohammad Mansour
2. What are Data Centers
“A data center (or data centre or
datacenter or datacenter) is a
facility used to house computer
systems and associated
components, such as
telecommunications and storage
systems. It generally includes
redundant or backup power
supplies, redundant data
communications connections,
environmental controls (e.g., air
conditioning, fire suppression)
and security devices.”
(Source: WIKI Definition)
Data Centers are Information Factories
3. Components of a Data Center
Telecom
Systems
Electricity
Systems
Cooling
Systems
Humidity
Control
Systems Security
Systems
Compute Equipment
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
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.com
http://www.hothardware.com
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. Data Center Map – North America
Source : http://www.datacentermap.com/
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. 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. 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. HDM Define Overall Key
Decisions
Methodology 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. Data Center Site Selection – HDM Model
Geographical 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. 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
16. PCM Calculations
y k
Av = ∑∑ Cwi ∗ Fwij ∗ Dij
i =1 j =1
Av = Alternative final value
Cwi = 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 i
y = Number of criteria in the model
k = Number of factors under C i
17.
18.
19.
20. 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 Oregon
C1: 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 81
C2: 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 tax
C3: Political Factors
F31: Tax Structure, Incentives and Subsidies 90 73 74 92
F32: Jobs Creation 74 77 75 67
C4: Social Factors
F41: Safety & Security, Crime 85 69 73 85
F42: Laws related to Urban Planning 84 62 63 83