Eclipse Digital - Fotolia
Pressure is growing on the datacentre community to incorporate the amount of water their facilities consume when calculating their power usage effectiveness (PUE) scores.
Emerson Network Power has become the latest member of the datacentre industry to speak out about the issue because of the massive role water plays in helping keep facilities cool.
As such, the company has published a blog post setting out how a revised PUE formula, which takes into account the contribution water makes to datacentre operations, would look and work.
Typically, PUE is calculated by dividing the total power consumption of a datacentre by the amount of energy used by the IT equipment inside it on an annualised basis.
The revised formula, dubbed power usage effectiveness refined, would include additional figures calculated when the amount of water a facility consumes is multiplied by the water equivalent energy factor to help establish the liquid’s evaporative energy.
Using this formula, Emerson calculated the power usage effectiveness refined score of a 1MW datacentre with a touted PUE rating of 1.1 would be 1.42.
“Our ‘new’ PUE of 1.42 is still a respectable number in the grand scheme of things, but a long way from the ‘claimed’ PUE of 1.1,” the blog post stated.
The results highlight a trend that industry watchers have repeatedly flagged, whereby datacentre operators move over to evaporative cooling systems – which rely on large amounts of clean water – to achieve a lower PUE score.
Read more about datacentre efficiency
- With datacentre operators under increased competitive pressure to cut their PUE scores, are their ratings really all they seem?
- Advania Data Centres selects Iceland as a location to build an environmentally-friendly and cost-effective IT facility, both for the country’s ambient cool temperature and its geothermal energy.
“These inaccurate performance claims have created a perceived disparity between evaporative cooled datacentres and those deploying other technologies, such as eco-mode pumped refrigerant or closed-loop chilled-water with air-cooled chillers.
“Now with power usage effectiveness refined, we have a proper formula to account for all energy sources used in a datacentre and are able to make a meaningful analysis of all our available cooling options,” it added.
The supplier also said adopting the formula would provide operators with a more accurate and comprehensive means of gauging the efficiency of their facilities.
“We believe this has provided the basic framework for such change to take place. The datacentre industry may have a truly meaningful and comprehensive metric to use in evaluating all sources of energy use in the datacentre,” the post concluded.
Piling on the PUE pressure
As reported by Computer Weekly in April 2015, the accuracy of the PUE scores publicised by datacentre operators are often called into question because there is no requirement for them to be verified by a third party.
This is the reason why the Green Grid Association – which oversaw the introduction of PUE in 2007 – is in the throes of getting the metric recognised as an ISO by the International Organisation for Standardisation, which would help bring a degree of regulation to proceedings.