Heatwaves and data centres – what are the risks?

Posted on in

The UK has experienced soaring temperatures so far this month.

With a high of 32oC recorded in London last weekend, an official heatwave has now been declared and temperatures are set to remain above 25oC for the next week at least, with peaks of 28oC in Manchester and London.

So what does this mean for data centres – which need to be kept cool at all times?

Cooling is a critical part of a data centre’s infrastructure. If the environment gets too warm, then the equipment can overheat and fail, causing outages. This means that data centres are well prepared for the temperature spikes that summer can bring. However, as climate change increases the frequency of heatwaves across the globe, some DCs are getting caught out.

In July last year, for example, both Google and Oracle experienced outages after their London-based data centres were forced offline when Britain experienced record-high temperatures of over 40oC and the data centres’ cooling systems became overwhelmed. In September last year, Twitter also experienced downtime after its Sacramento data centre experienced a “total shutdown of physical equipment” due to a heatwave.

What’s the optimal data centre temperature?

Official guidelines set by ASHRAE state that 21oC is optimal. Some studies show that running a data centre at a higher temperature is perfectly acceptable, but this can only be truly considered if you have a full understanding, control and monitoring over almost every piece of hosted equipment in the data centre.

In a multi-tenanted, multi-vendor collocated environment the cooling requirements of hosted equipment will vary hugely and so making sweeping temperature decisions could have hard-hitting consequences for some customers.

Really, the run temperature for a data centre can be anywhere between 18-27°C. Turning the air-con down a degree or two can significantly reduce energy consumption without any detrimental effects on the equipment.

Cooling resilience

As proven by Google and Twitter’s experiences, an air conditioning system can fail, just like any other component. So it’s important that a data centre provider has significant cooling redundancy measures in place.

At our Manchester data centre, for example, our air con works in N+1 configuration. There are also failover components within the actual units themselves to ensure that the risk of downtime to any individual unit is avoided as far as possible. If a unit is lost, then the N+1 resilience level ensures cooling capacity is maintained as required. We also split all units alternately between our dual power feeds, which can operate independently from each other, through different switchgear and on diverse paths.

It’s therefore important to ask your provider questions about how they maintain their air conditioning units, what their capacity is, how it’s all monitored, and what degree of redundancy they offer to protect against failure or unit isolation for routine maintenance.

SLAs should also be in place to guarantee cooling temperatures. Extensive monitoring systems should be evident to ensure that alerts are generated where thresholds are crossed.

Energy-efficient cooling technology

At our London-edge facility we use energy efficient adiabatic cooling solutions which are designed to maximise energy efficiency using cost effective, state-of-the-art technology. This free cooling design uses a flooded airflow approach to deliver energy efficient and cost effective cooling, significantly reducing running costs and our carbon footprint.

If you have concerns about the resilience of your data centre facility during heatwaves, get in touch with your provider and ask about cooling redundancy measures. As the increase in global heat waves shows no signs of slowing down, technology companies must work hard to monitor and mitigate extreme heat, otherwise, the risk of outages increases too.