The Debate about Liquid Cooled Data Centers

I’ve been remiss in not posting for a couple of weeks, so I’m trying to get back in the saddle. I’ve been working on other things that have taken up a fair bit of time. One is a web seminar on heatsinks – Heatsink 201 – Even More about Heat Sinks which follows on from Alexandra Francois-Saint-Cyr’s very successful Heat Sink 101 web seminar.

Back in March I posted about IBM’s work on liquid cooling to take Moore’s Law to 2025. As a side note I observed that, one of the main benefits of liquid cooling in a data center is that the high grade waste heat generated can be used for heating purposes. This changes both the economics of deploying a liquid cooling solution and the environmental impact. The reason this is so important is that data centers are one of the fastest growing consumers of energy.

Last week Google posted about this issue on its Public Policy Blog in response to ASHRAE (the American Society of Heating, Refrigerating and Air-Conditioning Engineers) adding data centers to their building efficiency standard, 90.1. Google’s concern is that the ASHRAE standard is too prescriptive, stating that the building should use economizers (which bring in ambient cooling air from outside for cooling). The term ‘economizer’ reflects the fact that using natural ventilation is more energy efficient than using mechanical ventilation systems, particularly those that incorporate chillers, which are commonplace in data centers. As Google note, this can in some cases work very well, but to quote a British expression, its horses for courses.

Google argue that an efficiency-based approach should be taken with aggressive targets for non-computing power consumption. To me this makes sense. In terms of liquid cooling, the target should take into account useful waste heat that can be used for heating homes and offices in the locality. Although this is harder to measure, I believe it’s important to take a holistic approach to measuring and reducing the ‘non-useful’ energy consumption of data centers.

The leading thinkers in the industry are on the right track in pursuing Power Usage Effectiveness. Simply dumping the heat generated by tens of thousands (and in a few cases hundreds of thousands) of servers to the ambient air, albeit with an energy-efficient ventilation system, is not the way to go. Hopefully common sense will prevail.

That’s it for now, back to work on my forthcoming Heatsink 201 web seminar.

Dr. J, Hampton Court

Post Author

Posted April 19th, 2010, by

Post Tags

, , , , , , , , , , , ,

Post Comments

No Comments

About John Parry’s Blog

A mixed bag of things that interest me professionally -CFD technology and its use in education, cooling technologies and the place of thermal design in the overall design flow. John Parry’s Blog

Comments

Add Your Comment

Archives

May 2014
  • Ramping Up for THERMINIC! Abstract Deadline 28th May 2014
  • February 2014
  • FREE Exhibition at SEMI-THERM 30 Conference, San Jose March 9-13
  • August 2010
  • Lies, Damned Lies, and “CFD Comparison Charts” – Part IV
  • Lies, Damned Lies, and “CFD Comparison Charts” – Part III
  • Lies, Damned Lies, and “CFD Comparison Charts” – Part II
  • Lies, Damned Lies, and “CFD Comparison Charts” – Part I
  • July 2010
  • Mechanical Analysis Products Now in Mentor’s Higher Education Program
  • Sony Vaio laptop in mass ‘recall’
  • June 2010
  • Nearly Back to Business as Usual
  • April 2010
  • The Debate about Liquid Cooled Data Centers
  • MicReD Technology Wins Highest Technical Honor
  • March 2010
  • Sticking Plaster and Light beats Skin Cancer
  • IBM Work to take Moore’s Law to 2025
  • Concurrent CFD Explained (Part IV)
  • Roundup of SEMI-THERM, FloTHERM IC launch and JEDEC
  • February 2010
  • NEW ElectronicsCooling Magazine Website
  • Liquid Cooling – Are We There Yet?
  • Foresight and X-Ray Vision or Hindsight and Regret?
  • FREE Exhibition at SEMI-THERM, Santa Clara February 23-24
  • Force Prediction with Concurrent CFD
  • January 2010
  • Champcar Exhaust Analysis
  • Concurrent CFD Explained (Part III)
  • Stop Press: New Electronics Cooling Community
  • Interested in Indy Car?
  • Concurrent CFD Explained (Part II)
  • Concurrent CFD Explained (Part I)
  • December 2009
  • Cool Youtube Video
  • The Secret’s Out!
  • Wanna Know a Secret?
  • Thermal Design: Who’s Job Is It Anyway?
  • November 2009
  • More on Concurrent CFD in Product Design
  • Concurrent Design and Thoughts on ‘Flows’
  • Mind Your Head(room) Again
  • Solutions Expos – Going MAD in the UK
  • Mind Your Head(room)
  • October 2009
  • Solutions Expos – Just Back
  • Web slashes and missing polar ice
  • Going MAD at European Solutions Expos
  • What’s black and stuck on a PCB?
  • September 2009
  • Try the latest thing in CFD – Free!
  • How to survive a recession
  • ‘Simulating and Optimizing’ – A Series of Free Web Seminars
  • August 2009
  • Fluid Dynamics = Fun (Just back from holiday!)
  • Engineers Spend 60-80% of Work Time Changing Existing Designs
  • Hayfever: Stopped by a Red Light
  • Free Thermal Management Design Guide
  • July 2009
  • Where did CFD come from?
  • Formula 1 and KERS
  • A True Market Leader
  • Mind Your Thermal Management To Improve Reliability
  • Tennis – it’s a rough sport
  • Fluid Dynamics and BBQs
  • June 2009
  • Air – Is it Running Out of Gas?
  • The Deal with Electronics Cooling CFD – Meshing
  • The Deal with Electronics Cooling CFD: Geometry (Lots!)
  • May 2009
  • What’s the Deal with Electronics Cooling CFD?
  • The Start of A New Chapter