Story image

Why water use is a key consideration when cooling your data center

22 May 2018

For years in data center circles, we’ve been talking about Power Usage Effectiveness, or PUE.

Largely lost in the discussion, however, is another factor that has taken on increased importance as data centers rely on economizer modes of cooling: Water Usage Effectiveness or WUE.

Both are measures of data center sustainability developed by the Green Grid.

The availability and cost of water should play a role in your decision when choosing between cooling architectures, especially when considering economizer solutions.

Let’s Start at the Beginning

But for starters what is WUE?

Most people are familiar with PUE, the total power consumed by the data center divided by the power consumed by the IT gear within the data center.

WUE is a similar metric that divides total site annual water consumption by the IT power.

Water usage by a data center (or any commercial building) is a complex subject. Not only is water used on-premise, but the electric power generation usually involves significant water consumption by the utility as well.

Thus, increasing water consumption at the data center could reduce total water consumption by driving down the electricity needed. Think about a multi-megawatt data center which can easily use tens of thousands of gallons every day.

Reduction of water usage is certainly a desirable goal for data centers deploying evaporative (or adiabatic) cooling for both sustainability and local regulatory reasons.

Consider Water Source and Pressure for Adiabatic Economizers

Adiabatic economizers typically spray water onto heat exchanger surfaces or in some cases directly into the air stream. The water serves to cool the air as it enters the data center.

In the process, however, some of the water evaporates and is lost.

This means you need a reliable, continuous source of water for these systems to be effective. If your water source is cut off for any reason, you will lose the economizer benefit.

If water availability is a significant risk then you may have to design larger economizer systems than you would otherwise to compensate, or include separate backup cooling systems, both could substantially increase upfront capital costs.

Another element to consider is water pressure. High pressure systems generate a fine mist, which is subject to a high degree of evaporation and water loss, driving up WUE. Low pressure systems act more like a shower and a greater amount of water can be collected and recirculated through the system. If a system provides no recirculation capability than the water loss is 100%.

Cost and Water Quality as Decision Factors

Regardless of which system you use, you need to factor in the cost and availability of water to determine which one is the best fit.

Bear in mind it’s possible that the cooling system with a lower power consumption but higher water consumption has the best results for your total cost of ownership.

Lower WUE by itself is a good goal, but is not the only consideration.

An additional consideration is water quality. Because high pressure adiabatic systems force water to pass through small orifices to create a fog they are more sensitive to water quality problems.

Low pressure evaporative systems are more forgiving, given the orifices are far larger and less prone to clogging. This reduces maintenance costs and reduces risk to system reliability.

Decide Which Economizer System is Best For You

It’s time to start factoring WUE into your cooling system designs and not just PUE. You may find there’s money to be saved striking a balance between the two.

You can start exploring which economizer system is best for your data center.

Article by Maurizio Frizziero, Schneider Electric blog network. 

Opinion: How SD-WAN changes the game for 5G networks
5G/SD-WAN mobile edge computing and network slicing will enable and drive innovative NFV services, according to Kelly Ahuja, CEO, Versa Networks
TYAN unveils new inference-optimised GPU platforms with NVIDIA T4 accelerators
“TYAN servers with NVIDIA T4 GPUs are designed to excel at all accelerated workloads, including machine learning, deep learning, and virtual desktops.”
AMD delivers data center grunt for Google's new game streaming platform
'By combining our gaming DNA and data center technology leadership with a long-standing commitment to open platforms, AMD provides unique technologies and expertise to enable world-class cloud gaming experiences."
Inspur announces AI edge computing server with NVIDIA GPUs
“The dynamic nature and rapid expansion of AI workloads require an adaptive and optimised set of hardware, software and services for developers to utilise as they build their own solutions."
Norwegian aluminium manufacturer hit hard by LockerGoga ransomware attack
“IT systems in most business areas are impacted and Hydro is switching to manual operations as far as possible.”
HPE launches 'right mix' hybrid cloud assessment tool
HPE has launched an ‘industry-first assessment software’ to help businesses work out the right mix of hybrid cloud for their needs.
ADLINK and Charles announce multi-access pole-mounted edge AI solution
The new solution is a compact low profile pole or wall mountable unit based on an integration of ADLINK’s latest AI Edge Server MECS-7210 and Charles’ SC102 Micro Edge Enclosure. 
How Dell EMC and NVIDIA aim to simplify the AI data centre
Businesses are realising they need AI at scale, and so enterprise IT teams are increasingly inserting themselves into their company’s AI agenda.