Liam Newcombe BCS Data Centre Specialist Group Secretary

1
Liam NewcombeBCS Data Centre Specialist Group
Secretary

• Modelling Data Centre Energy Efficiency and Cost

2
BCS Data Centre Simulator

• Background
• Overview of Tools
• Structure of the BCS Simulator
• Input Data
• Sample Output
• Development Path

3

• Background

4

• Power Loss Chain Fossil Fuel CPU Used

5
Data Centre Cost and Energy
For each or Watt my Data Centre consumes what
output do I get? vs. For each Service I deliver
what is the financial and energy cost?
6

• Overview of Tools

7
Tool Coverage

• Existing tools
• Computational Fluid Dynamics
• Server benchmarking
• Chiller technology comparisons
• Carbon calculators
• Device specific comparators

8
Tool Problem

• When the only tool you have
• is a hammer everything
• looks like a nail1

1) Abraham Maslow
9
Tool Problem

• The data centre is not a set of independent
  components that can be individually tuned
• The data centre is a complex and interdependent
  system
• Only a holistic tool can give useful answers

10
(No Transcript)
11
(No Transcript)
12
(No Transcript)
13
(No Transcript)
14
(No Transcript)
15
Framework Tool

• One tool to cover the entire system, allowing the
  simulation of components in a realistic context.
• No need to develop more partial tools, you can
  now contribute to the open, trusted tool instead.

16
Framework Tool

• Designed to facilitate the incorporation of new
  or enhanced component models and data
• Publish performance data in standard formats that
  we can use to compare devices

17

• Structure of the BCS Simulator

18
BCS Data Centre Model

• IT Workload

IT Device Load to Power Function
Data Centre Power Transfer Function
19
IT Device
20
IT Device Costs
21
IT Device in a Data Centre
22
IT Device in a Data Centre
23
Energy Costs
24
Per Device Costs
25

• Input Data

26
Fully Representative Data
27
Open XML Formats
28

• Sample Output

29
Simulator Output
Example Scenario

• Same Computing Workload
• 100 One App Per Server Servers
• 15 Virtualised Servers
• 10 HPC Grid Servers
• Old N1 Data Centre, Nameplate Provisioning

30
Simulator Output

• Old N1 Data Centre, Nameplate

31
Simulator Output

• Old N1 Data Centre, Nameplate

32
Simulator Output
Example Scenario

• Same Computing Workload
• 100 One App Per Server Servers
• 15 Virtualised Servers
• 10 HPC Grid Servers
• New N1 Data Centre, Free Cooling

33
Simulator Output

• New N1 Data Centre, Free Cooling 19C

34
Simulator Output

• New N1 Data Centre, Free Cooling 25C

35
Simulator Output

• New N1 Data Centre, Free Cooling 25C

36
Simulator Output

• New N1 Data Centre, Free Cooling 25C

37

• Development Path

38
Development Path
Data Centre energy use and cost is a complex
problem that we are only starting to
understand Deliver marginal and fair share, per
business service energy and financial costs to
enable holistic carbon management
39
Development Path
Individual component calculators are
ineffective without the context of a holistic
model Device level A-G style simple labelling is
not effective in a data centre environment
40
Development Path
As our understanding of the data centre grows we
will be able to use the more complex capabilities
of the simulator
41
Development Path

• Opportunities for Further Research and
  Development
• IT Device Performance
• Configuration
• Workload
• Generalised Metrics ( Performance / Energy )
• Networking
• Storage

42
Development Path

• Opportunities for Further Research and
  Development
• Application Performance
• Hardware interaction
• Impact of the working data set
• Optimisation

43
Development Path

• Opportunities for Further Research and
  Development
• Economics ( Cost and Energy )
• Intelligent task deployment
• Per task accounting
• Automated in-source / out-source decisions
• Real time cost management and reporting
• Policy based management

44
Development Path

• Opportunities for Further Research and
  Development
• Physics
• Integrated Computational Fluid Dynamics
• Chiller plant behaviour and management
• Workload assignment

45
Development Path

• Opportunities for Further Research and
  Development
• Electrical / Electronic Engineering
• Power infrastructure performance and loss
  characteristics
• Dynamic self provisioning electrical
  infrastructure