Pramod Mandagere Prof. David Du Sandeep Uttamchandani (IBM Almaden)

Similar documents
Fundamentals of CFD and Data Center Cooling Amir Radmehr, Ph.D. Innovative Research, Inc.

Current Data Center Design. James Monahan Sept 19 th 2006 IEEE San Francisco ComSoc

Optimization in Data Centres. Jayantha Siriwardana and Saman K. Halgamuge Department of Mechanical Engineering Melbourne School of Engineering

Recapture Capacity for Existing. and Airflow Optimization

Smart Data Centres. Robert M Pe, Data Centre Consultant HP Services SEA

Using CFD Analysis to Predict Cooling System Performance in Data Centers Ben Steinberg, P.E. Staff Applications Engineer

Close Coupled Cooling for Datacentres

Estimating Data Center Thermal Correlation Indices from Historical Data

Where s the Heat Coming From. Leland Sparks Global Account Technical Consultant Belden

Avoidable Mistakes that Compromise Cooling Performance in Data Centers and Network Rooms

Power and Cooling for Ultra-High Density Racks and Blade Servers

Coordinating Liquid and Free Air Cooling with Workload Allocation for Data Center Power Minimization

DATA CENTER EFFICIENCY: Data Center Temperature Set-point Impact on Cooling Efficiency

Reducing Energy Consumption with

A Green Approach. Thermal

Green IT and Green DC

Reducing Data Center Cooling Costs through Airflow Containment

Efficiency of Data Center cooling

Schneider Electric Cooling Portfolio. Jim Tubbesing Heath Wilson APC/Schneider North Texas Rep Tubbesing Solutions

Dominick Lovicott Enterprise Thermal Engineering. One Dell Way One Dell Way Round Rock, Texas

Energy Efficient Data Centers

Temperature monitoring and CFD Analysis of Data Centre

Cooling. Highly efficient cooling products for any IT application. For More Information: (866) DATA CENTER SOLUTIONS

Data Center Enclosures Best Practices. Maximize the Efficiency of the Enclosure within a Data Center

Thermal management. Thermal management

Energy Efficient Data Center Design. Can Ozcan Ozen Engineering Emre Türköz Ozen Engineering

APC APPLICATION NOTE #74

Rittal Cooling Solutions A. Tropp

Optimizing Cooling Performance Of a Data Center

Future of Cooling High Density Equipment. Steve Madara Vice President and General Manager Liebert Precision Cooling Business Emerson Network Power

Moving Containment Inside the Enclosure. Jeff Markle Great Lakes Case & Cabinet

The Efficient Enterprise. All content in this presentation is protected 2008 American Power Conversion Corporation

Impact of Air Containment Systems

A LAYMAN S EXPLANATION OF THE ROLE OF IT RACKS IN COOLING YOUR DATA CENTER

Great Lakes Product Solutions for Cisco Catalyst and Catalyst Switches: ESSAB14D Baffle for Cisco Catalyst 9513 Switch

Data Centre Energy & Cost Efficiency Simulation Software. Zahl Limbuwala

MSYS 4480 AC Systems Winter 2015

Next Generation Cooling

84 kw, Tier 3, Direct Expansion, 937 ft 2

Energy Efficiency and WCT Innovations

Virtualization and consolidation

Ten Cooling Solutions to Support High- Density Server Deployment

Making Scheduling Cool : Temperature-Aware Workload Placement in Data Centers

Combining Cold Aisle Containment with Intelligent Control to Optimize Data Center Cooling Efficiency

Variable Density, Closed-Loop, Water-Cooled Data Center Solution

Close-coupled cooling

How Liquid Cooling Helped Two University Data Centers Achieve Cooling Efficiency Goals. Michael Gagnon Coolcentric October

ENCLOSURE THERMAL TESTING HEAT REMOVAL IN THE REAL WORLD

Evaporative free air cooling technology Providing evaporative free air cooling solutions.

Energy Logic: Emerson Network Power. A Roadmap for Reducing Energy Consumption in the Data Center. Ross Hammond Managing Director

Ten Cooling Solutions to Support High-density Server Deployment. Schneider Electric Data Center Science Center White Paper #42

LANL High Performance Computing Facilities Operations. Rick Rivera and Farhad Banisadr. Facility Data Center Management

Exploiting a Thermal Side Channel for Power Attacks in Multi-Tenant Data Centers

Capacity and Power Management: The Forgotten Factors in Disaster Recovery Planning Presented by: Clemens Pfeiffer CTO Power Assure, Inc.

Data Center Infrastructure Management (DCIM) By Jesse Zhuo

Application of TileFlow to Improve Cooling in a Data Center

One Stop Cooling Solution. Ben Tam Business Development Manager

Energy Efficient Cloud Computing: Challenges and Solutions

AisleLok Modular Containment vs. Legacy Containment: A Comparative CFD Study of IT Inlet Temperatures and Fan Energy Savings

Survey and Audit Service Schedule. Airflow and Thermal Imaging Survey Service Schedule. Data Centre Solutions Expertly Engineered

Mission Critical Facilities & Technology Conference November 3, 2011 Cooling 101. Nick Gangemi Regional Sales Manager Data Aire

Cooling on Demand - scalable and smart cooling solutions. Marcus Edwards B.Sc.

Optimizing data centers for high-density computing

Power consumption and efficiency of cooling in a Data Center

The Energy. David L. Moss Dell Data Center Infrastructure

CHILLED WATER. HIGH PRECISION AIR CONDITIONERS, FROM 7 TO 211 kw

High Tech Getting Too Hot? High Density Environments Require A Different Cooling Approach

Measurement and Management Technologies (MMT)

Hot vs Cold Energy Efficient Data Centers. - SVLG Data Center Center Efficiency Summit

Cost Model Energy Benefits DirectAire & SmartAire Overview & Explanation

Reclaim Wasted Cooling Capacity Now Updated with CFD Models to Support ASHRAE Case Study Data

Overcoming the Challenges of Server Virtualisation

Design and Installation Challenges: Aisle Containment Systems

CRITICAL FACILITIES ROUNDTABLE HEAT REMOVAL IN DATA CENTERS ENGINEERED SOLUTIONS

To Fill, or not to Fill Get the Most out of Data Center Cooling with Thermal Blanking Panels

Datacenter Efficiency Trends. Cary Roberts Tellme, a Microsoft Subsidiary

PROCESS & DATA CENTER COOLING. How and Why To Prepare For What s To Come JOHN MORRIS REGIONAL DIRECTOR OF SALES

) ) page 04. page 07. page 10. page 10. page 12. page 14. page 14. page 16. page 18. page 19. page 19. page 20. page 21. page 22

HIGHLY EFFICIENT COOLING FOR YOUR DATA CENTRE

Precision Cooling. Precision Cooling Advantages

Review on Performance Metrics for Energy Efficiency in Data Center: The Role of Thermal Management

Innovative Data Center Energy Efficiency Solutions

High Density Cooling Solutions that work from Knurr Kris Holla

MEASURE MONITOR UNDERSTAND

Improving Rack Cooling Performance Using Blanking Panels

Total Modular Data Centre Solutions

CFD Modeling of an Existing Raised-Floor Data Center

Rethinking Datacenter Cooling

LCP Hybrid Efficient performance with heat pipe technology

Partner Introduction

A) Differences between Precision and Comfort Cooling Here are the major differences exist between precision air conditioning and comfort systems.

ECOBAY: Closed loop water cooled server cabinet for data centers

3300 kw, Tier 3, Chilled Water, 70,000 ft 2

TRACE 700 Learning Series Module 2: Navigation

Product Brochure DENCO Close Control Units Row-DENCO. High Density Cooling for Data Centres

APC APPLICATION NOTE #126

ABB Automation & Power World: April 18-21, 2011 CLP CEU Myth Busting: The Truth behind Data Center Marketing Trends

IT Air Conditioning Units

<Insert Picture Here> Austin Data Center 6Sigma DC CFD Model

Green Sustainable Data Centres. Checklist - EU Code of Conduct on Data Centres. Annex

Transcription:

Pramod Mandagere Prof. David Du Sandeep Uttamchandani (IBM Almaden)

Motivation Background Our Research Agenda Modeling Thermal Behavior Static Workload Provisioning Dynamic Workload Provisioning Improving Data Center Efficiency by Fixing Existing inefficiencies/hotspots Layout Planning Current Status

Total US Data Center Power Consumption is about 1.5% of US total electricity consumption Total Cost for Data Center Electricity consumption ~ $5B in 2007 ($7.5B by 2011) Issue: Though it accounts for a very small percentage of overall consumption, the concentrated nature/density leads to supply issues (concentrated demand on power grids)

Data Center Power Consumption 50% Heating Ventilation & Air Conditioning (HVAC) 20-35% Servers 10-25% Storage 5% Networking Different Types of data centers Compute Centric (Ex: HPC) 35% Servers,10% Storage, 5% Networking Data Centric (Ex: Enterprise) 20% Servers, 25% Storage, 5% Networking Average Case 25% Servers, 20% Storage, 5% Networking

Almost all Energy consumed by all IT equipment is released as Heat Heat Extraction Process Fans suck in Cold Air from the vents at front of servers (inlets) As the cold air passes through the server, heat is extracted/absorbed and air exits the system at a higher temperature Q: Heat generated is a function of System Load Inlet temperatures should be kept below 25 0 C for safe operation (Thermal Redlining) : Failure rates increase non linearly above this threshold

Computer Room Air Conditioning Units (CRACs) extract out the heat generated by devices and supply cold air to the data center Higher the Supply Temperature -> Higher the CRAC Efficiency (Coefficient Of Performance) Q: Amount of Heat W: Work done is removing/extracting Q units of heat [HP Usenix 07] Device Inlet temperatures are a function of Supply temperature 25 0 C Supply temperature!= 25 0 C Server Inlet temperature Higher Supply Temp -> Higher Inlet Temp (Ideal setting: Highest Supply temp that leads to Max Inlet Temp < 25 0 C)

Heat Recirculation or Hot gas bypass Hot air generated by servers/storages does not completely travel across and reach the CRAC for extraction, a portion of it recirculates into cold isle. Cause Natural recirculation around the end of isles and top of racks or unused open spaces in racks in combination with flow rates of supplied cold air Effect With Supply temperature set to a given point, the Inlet temperatures at various servers tends to be higher that the supply temperature Factors that affect HR Data Center Layout/dimensions Workload distribution

Top View Profile View Typical Raised Floor Based Layout

Height:3ft Height:6ft Impact of Heat Recirculation Increases with height Temperatures at rack tops are higher than at rack bottom

Difference???? Difference???? Row Ends Row Middle Impact of Heat Recirculation Lesser at middle of rows/isles Increases towards row/isle ends

Objective Predict Temperatures Profile of Data Center Inlet temperatures of all Server & Storages as a function of Workload on all systems for a fixed layout and cooling system Given Power Usage of all equipment Physical Location of all equipment Physical Dimensions and Layout of the Data Center(fixed) Our Proposed Solution Use Supervised Machine learning techniques to build regression based predictors Support Vector Machines

Limitations of Related work (ASU) Modeling based approach & (HPLabs) Neural Net based approach Does not account for On/Off nature of server/fans (ASU) Does not provide any means of understanding/ verifying learnt functions (HPLabs) Parameter space has to be reduced for reasonable learning time (HPLabs) Assumes homogenous equipment (flow to power ratio) Our approach uses SVM based predictors Incorporates both Flows and Power profiles of servers Scalable & Verifiable Support Vectors Provides a means for understanding HR characteristics

Objective Determine relationship between Supply temperatures of Cooling Units and Server Inlet temperatures Given Power Usage of all equipment Physical Location of all equipment Physical Dimensions and Layout of the Data Center(fixed) Our Proposed Solution Profiling based approach to determine Zone Ownership Vary Supply temperature of each of the CRACs one by one and observe the corresponding change in Server Inlets Difficult to Model: Highly Dependent/Coupled with Server Workloads Zones of ownership more easier to determine and often adequate

Objective Minimize Data Center Power Consumption for a given Workload Set Assumptions Provisioning from scratch No deadlines all at once Constraints Server Inlet Temperatures < Threshold (25 0 C) CRAC loads < Maximum Capacity (100kW each) Given Physical Layout Information

Our Proposed Solution: Discrete non-linear optimization Objective function: Minimize overall Power Consumption Minimize Power consumption of Servers + Storages Minimize Peak Inlet temperature of devices (Zones) Basic Constraint: Inlet Temp < threshold Advanced Constraint: Connectivity + Policy based Solution Technique: Genetic Algorithms Workload distribution as the population string Challenges Trade off between Workload/platform efficiency and Cooling system efficiency Impact of Modeling accuracy on optimization process Incorporating Constraints

Objective Minimize Data Center Power Consumption for a given Workload on an running system/reprovisioning existing system to minimize inefficienies Assumptions System with pre running workloads and pre specified system state Constraints Server Inlet Temperatures < Threshold (25 0 C) CRAC loads < Maximum Capacity (100kW each) Given Physical Layout Information

Challenges Minimizing impact of reprovisioning on real time performance Trade off between repositioning one or more existing workloads vs performance/power gain by reprovisioning in the long run Accounting for power cost of reprovisioning Accounting for constraints

Objective Derive best practices for Floor Planning using the system models Temperature Profile as function of Data Center Dimensions Raised Floor Depth Ceiling Height Row Width CRAC placement Constraints Prevent thermal redlining Given Thermal Characteristics of devices Performance characteristics of devices

Layout Planning Designed simulations in Flovent CFD simulator Impact of Datacenter Characteristics on Thermal Profile Thermal Modeling as a function of Workload Collected Training Data for Supervised Learning Implement SVM based regression learners Thermal Modeling as a function of Variable Cooling Units Designed simulations in Flovent Impact of Cooling System variation on Thermal Profile Determined Zone based ownership

Raised Floor Depth 0.15m 0.3m 0.45m 0.6m # of Servers > 25C 37 28 25 6

Ceiling Height 2.2 2.4 2.6 2.8 3 3.2 3.4 3.6 3.8 # of Servers >25C 6 3 4 6 4 2 2 3 2

Layout EEWW NSEW NNSS # of Servers > 25C 4 15 6

Size 4ft 6ft 8ft # of Servers > 25C 4 23 30 *Room Size: 4ft = 2 floor tiles at any point between racks and walls

C R A C A Effect of 1 0 Change on CRAC Supply Temperature C R A C B Rack Bottom Rack Top

C R A C C Effect of 1 0 Change on CRAC Supply Temperature C R A C D Rack Bottom Rack Top