[AusNOG] Data Suburb

[Mark Newton]

I'm not sure that 1.24 counts as "poor." Especially when it's inside the ballpark of the contrary example you've cited :)

   - mark



On 04/01/2012, at 11:22 PM, "Tony de Francesco" <tonyd at pue.com.au> wrote:

> Poor PUE at part load is an excuse for poor design.
>  
> There is no theoretical reason why PUE should be much, if any, worse at part load compared to full load. It largely comes down to the choice of technologies and how they are controlled.
>  
> A good case in point is a 300kW (peak capacity) data centre we are monitoring in Melbourne.  It is less than 15% full and is still operating at a PUE of around 1.15 in winter and around 1.30 in summer. As the load increases we are expecting the PUE to stay about the same or maybe increase slightly.
>  
>  
> Kind Regards
>  
> Tony de Francesco
> Technical Director
> 
> email: tonyd at pue.com.au
> mob: +61 (0) 457 701 179
> .....................................................
> <image001.jpg> 
> From: ausnog-bounces at lists.ausnog.net [mailto:ausnog-bounces at lists.ausnog.net] On Behalf Of Mark Newton
> Sent: Wednesday, 4 January 2012 11:07 PM
> To: Phillip Grasso
> Cc: ausnog at ausnog.net
> Subject: Re: [AusNOG] Data Suburb
>  
> 
> On 04/01/2012, at 9:20 PM, Phillip Grasso <phillip.grasso at gmail.com> wrote:
> 
>> "The world's highest density large scale data centers are also the most efficient!"
>> 
>> Quoted from their site; also said they are 1.24 PUE, which compared to ancient datacenters might be pretty efficient but I won't say they are the "most efficient". 
>>  
>  
> They aren't full yet. Efficiency always takes a hit when capacity is underutilized during the buildout phase, but improves rapidly when installed infrastructure starts to reach its designed "sweet spot."
>  
> Give 'em another year then look again.
>  
>    - mark
>  
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.ausnog.net/pipermail/ausnog/attachments/20120105/b6afca91/attachment.html>