Power Management System - IBM - United States
Transcript of Power Management System - IBM - United States
Dynamic Power Management Dynamic Power Management in the Data Centerin the Data CenterIBM Power and Cooling SymposiumRaleigh, NC04 October 2007Bharat S. ShahEmerson Network [email protected]
04 Oct 2007 Slide 2
AgendaAgendaAgendaPower Management ChallengesIT Equipment Power Reduction SchemesFacility Infrastructure Power ImprovementsDynamic Power Management SystemSummary
04 Oct 2007 Slide 3
Power Management ChallengesPower Management ChallengesPower Management ChallengesOver the next five years, power failures and limits on power availability will halt data center operations at more than 90% of all companies (AFCOM (DCI))By 2008, 50% of data centers will have insufficient power and cooling capacity to meet the demands of higher density equipment (Gartner)Power and cooling spending will exceed server spending within 2 years (IDC, Gartner)Power associated with servers, storage and network equipment will increase from 1.5% of total US energy consumption to 2.5% by 2011 (EPA)
Source: EPA, Andrew Fanara
04 Oct 2007 Slide 4
Current Data Center Power ConsumptionCurrent Data Center Power ConsumptionCurrent Data Center Power Consumption
Source: Green Grid Feb 2007
Source: EYP Mission Critical Facilities Inc., Emerson estimate
Electricity Transformer
UPS10%
Air Movement
12%
Cooling25%
Lighting, etc.3%
Other IT Equipment
8%
Servers42%
04 Oct 2007 Slide 5
No System Linkage-Workflow Processes at Best-Typically E-Mail/Phone Communication-Reactive Mode at Worst
No System Linkage-Workflow Processes at Best-Typically E-Mail/Phone Communication-Reactive Mode at Worst
Current Data Center Power ManagementCurrent Data Center Power ManagementCurrent Data Center Power Management
CoolingUPSATS GenSets
3rd Party
FacilityManagement
System
ITManagement
System
RoutersServersStorage Switches
3rdParty
04 Oct 2007 Slide 6
AgendaAgendaAgendaPower Management ChallengesIT Equipment Power Reduction Schemes– Server Hardware– Virtualization Software– Dynamic Efficiency Control
04 Oct 2007 Slide 7
AC-DC / PFCPower Supply
IBC
POL Reg
POL Reg
POL Reg48
VdcPOL Reg
12Vdc
Dynamically optimize IBV
6-12
Dynamically optimize efficiency
Processor, memory and I/O loading
Server Hardware Architecture ExampleServer Hardware Architecture ExampleServer Hardware Architecture Example
DC-DC/VRM
DC-DC/VRM
DC-DC/VRM
DC-DC/VRM
04 Oct 2007 Slide 8
Source: NewsCorp IDC Virtualization Forum, Feb 2006
Virtualization SoftwareVirtualization SoftwareVirtualization Software
04 Oct 2007 Slide 9
Dynamic Efficiency ControlDigital Power SuppliesDynamic Efficiency ControlDynamic Efficiency ControlDigital Power SuppliesDigital Power Supplies
Dynamic efficiency enhancement based on load fluctuation thru virtualization (via digital power supplies)
Efficiency Curve Shaping: This is an optimized 760W 1+1 power supply for a data center application. It is optimized for efficiency at 20% to 50% load –the range in which it will operate for 98% of its service life.
Source: Emerson Internal
High Line (230V) Efficiency
7577798183858789919395
10 20 30 40 50 60 70 80 90 100
Percent Load
Effic
ienc
y
TodayOptimized
04 Oct 2007 Slide 10
Dynamic Efficiency ControlPMBus™ CommunicationDynamic Efficiency ControlDynamic Efficiency ControlPMBusPMBus™™ CommunicationCommunication
PMBus™ compliant power supplies provide in-band / out-of-band access to sensors, reporting power consumption data via SMBusGUI displays system power consumption reported by Digital Power Supply
AC/DC PSU
AC/DC PSU
MotherboardManagementController(s)
System Applications
Data Center Applications
WSMAN
ComponentsPMBusTM
Source: IntelIntel Developers Forum, Apr 2007
04 Oct 2007 Slide 11
AgendaAgendaAgendaPower Management ChallengesIT Equipment Power Reduction SchemesFacility Infrastructure Power Improvements– Digitally-Controlled Compressors– Scalable UPS Systems– Plug-and-Play Cooling Capacity
04 Oct 2007 Slide 12
Digitally-Controlled CompressorsDigitallyDigitally--Controlled CompressorsControlled Compressors
Continuously variable capacity compressors dramatically reduce the frequency of start/stop cycles –
saving energy and significantly increasing MTBF.
Average Compressor Cycles per Year
0
500010000
15000
20000
2500030000
35000
Sin
gle
com
pres
sor
Sin
gle
circ
uit
Two
com
pres
sor
Dua
l circ
uit
Two
com
pres
sor
(SH
)w
ith u
nloa
ding
Dua
l circ
uit
Sin
gle
com
pres
sor
(Dig
ital)
fully
var
iabl
eSi
ngle
circ
uit
Two
com
pres
sor
(Dig
ital)
fully
var
iabl
eD
ual c
ircui
t
System Type
Ann
ual C
ompr
esso
r C
ycle
s
04 Oct 2007 Slide 13
Scalable UPS SystemsScalable UPS SystemsScalable UPS Systems
Capacity added via software key (enables additional capacity without hardware addition/change)Examples: – Soft-Scale (fine adjustment)
• 40kVA → 60kVA → 80kVA• 80kVA → 100kVA → 120kVA• 120kVA → 160kVA → 200kVA
Scalable systems enable pay-as-you-go capacity without over-engineering for maximum capacity –
saving equipment capex and energy opex.
80 kVA – 100 kVA – 120 kVA
04 Oct 2007 Slide 14
Plug-and-Play Cooling CapacityPlugPlug--andand--Play Cooling CapacityPlay Cooling Capacity
Supplemental cooling can be added to hot-spotssaving energy and minimizing labor costs.
Pre-installed Piping Quick-Connect
SupplementalCooling
04 Oct 2007 Slide 15
AgendaAgendaAgendaPower Management ChallengesIT Equipment Power Reduction SchemesFacility Infrastructure Power ImprovementsDynamic Power Management System
04 Oct 2007 Slide 16
Open Bus
Power Management System-Centralized or Distributed Intelligence-Optimization Policies / Business Rule Engine-Manual or Auto-Pilot Operation
Power Management System-Centralized or Distributed Intelligence-Optimization Policies / Business Rule Engine-Manual or Auto-Pilot Operation
Dynamic Power Management SystemBridging/Optimizing IT and Facility SystemsDynamic Power Management SystemDynamic Power Management SystemBridging/Optimizing IT and Facility SystemsBridging/Optimizing IT and Facility Systems
CoolingUPSATS GenSets
3rd Party
FacilityManagement
SystemProprietary
orOpen
Open
ITManagement
System
RoutersServersStorage Switches
3rdParty
Open
Open Bus
04 Oct 2007 Slide 17
Dynamic Power Management SystemDynamic Power Management SystemDynamic Power Management SystemReduce Energy Costs– Equipment power control (on/off/standby) and
equipment provisioning in response to dynamic computing demand
Reduce Cooling Needs– Balanced cooling based on dynamic IT workload
conditions
Improve Capacity Planning– Scenario planning of power/cooling infrastructure
changes in response to computing load changes
04 Oct 2007 Slide 18
Dynamic Power Management SystemsReduce Energy CostsDynamic Power Management SystemsDynamic Power Management SystemsReduce Energy CostsReduce Energy Costs
Optimize energy consumption across the entire data center in response to IT workload variationsCapture additional savings based on utility availability or rate structureServers /
Digital Power Supplies
UPS Systems
ATS/Gen Sets
Cooling Systems
System Integration
Optimize power consumptionfrom CHIP to GRID.
04 Oct 2007 Slide 19
Dynamic Power Management SystemsReduce Cooling NeedsDynamic Power Management SystemsDynamic Power Management SystemsReduce Cooling NeedsReduce Cooling Needs
Set rules to adapt cooling to the load– Manage compressor load across units – Manage humidification & dehumidification– Cycle units, rotate standby units
Further reduce energy costs andextend life of cooling equipment.
04 Oct 2007 Slide 20
Dynamic Power Management SystemsImprove Capacity PlanningDynamic Power Management SystemsDynamic Power Management SystemsImprove Capacity PlanningImprove Capacity Planning
Match power / cooling capacity with computing resource consumption– Determine if additional
computing resources can be added within a specific power and cooling budget in the same physical space
– Or if new space is required to house these additional computing resources
Avoid reactive crises through proactive planning ofcomputing and infrastructure change scenarios.
04 Oct 2007 Slide 21
Now•Modular systems•Adaptive scalablearchitecture•Separate systems forpower, cooling,…..
2008,2009 - ----•Integrated, dynamically optimized adaptive systems
•Virtualization and load balancing linked to power and cooling
•Intelligent models for control and Optimization/Advance fault notification
With Power M
anagement
With Power M
anagement
Sepa
rate
Inte
grat
ed
2007-
Monitoring & LimitedConventional Controls
Adaptive Intelligent Controls
2008
Sensing &
Control
2007-2008
Real time monitoring
Prov
isio
ning
Dynamically Optimized Data CenterDynamically Optimized Data CenterDynamically Optimized Data Center
Type of Control
04 Oct 2007 Slide 22
AgendaAgendaAgendaPower Management ChallengesIT Equipment Power Reduction SchemesFacility Infrastructure Power ImprovementsDynamic Power Management SystemSummary
04 Oct 2007 Slide 23
SummarySummarySummaryIT and Facility equipment continue to evolve intelligently– Higher Efficiency, Digital Control and Virtualization
Current management, monitoring and control software optimize IT and Facility systems independentlyBridging the IT and Facility systems with an integrated Power Management solution dynamically optimizes efficiency across the entire Data Center
04 Oct 2007 Slide 24
Power Operating SystemConceptual Data FlowPower Operating SystemPower Operating SystemConceptual Data FlowConceptual Data Flow