IT Peer Network

3 Posts authored by: DonAtwood
DonAtwood

Retro-fitting data centers

Posted by DonAtwood Apr 19, 2011

Is it worth the capital investment to Retro-fit data centers for sustainability?  the answer is YES..  Consider this, for every watt of power your IT equipment consumes within the DC, the real total consumption per watt is > 2w with power losses to the utility and cooling.  Let’s face it, typically if the investment does not provide a financial return it’s often a hard sell to management.  It’s my experience working at a mega global company that the story and financial justification is possible, but what you pick and how you deliver the message is important.  In our 90+ DC’s worldwide, we have every conceivable design, age, and efficiency level but every one of our DC’s has low hanging fruit. The easy answer to the question is find your low hanging fruit and pick it; keep it simple and go after the big wins with little investment or risk to your company.  Here are my top 5 “low hanging fruit” opportunities for energy conservations via retro-fit in the DC:

 

1) control the air – stop 99% of the air mixing with blanking panels, row/rack realignment, walls, air barriers or whatever it takes (typically delivers >15% cooling efficiency)

2) measure and tune – stop over cooling the room and make sure you are running the right amount of cooling for your needs (many DC’s overcool routinely)

3) Free cooling – outside air is great in the right regions and wet side economizers for pre-cooling in other locations can save you a ton of cooling (no pun intended)

4) increase electrical efficiency - replace transformers / breakers for 415v power to the DC (saves about 7% in efficiency loss),

5) buy and run high efficiency IT equipment (this matters).

Don Atwood – Intel DC Architect

What’s wrong with high-efficiency in the data center today?  When we talk about high efficiency, going green, and sustainability, the real intent is to reduce carbon footprint and consume less energy overall but it seems “we” as an industry often get sucked into chasing a number for good public relations and /or bragging rights instead of doing what might be the right thing to do despite the net “PUE” result.  I’m working on a fantastic project right now that will technically deliver the lowest PUE in the world if I wanted to chase the number but because I define “high efficiency” as (IT + Mechanical + Electrical = highest efficiency opportunity) , my PUE number looks worse although my total power consumption is much better (1.02 vs. 1.11).  It’s time for the Data Center industry to step up and step away from our current industry best measurement because it could cause wrong actions in the chase for a good numbers.  Just my two cents.

 

Don Atwood – Intel DC Architect

 

Hi I’m Don Atwood, author of the newly released white paper and video that discusses our proof of concept (PoC) that tested cooling our Data Center with outside air. The topic of humidity control and if this would work in an ultra high humid climate keeps coming up. Most OEM spec’s allow for a wide range of humidity and it’s our belief that this cooling methodology could be used almost everywhere globally. Our only uncertainty comes around trying this near the ocean with high levels of salty corrosive wet air. We know it would negatively affect the servers at some point but the question is how quickly and is it within our refresh timetable. During a trip to ASIA last week I discussed trying a small scale “near the ocean” PoC to test this theory.. Does anyone thing this would add value to your company?

Filter Blog

By author:
By date:
By tag: