The ultimate stress test was placed on UK IT infrastructures as a temperature of 40.3°C was reached in July 2022. Data centre operators fought to ensure that cooling functionalities could deal with the challenge to prevent any connectivity outages and service disruptions.
By tradition, many legacy data centres were not designed to manage temperatures, and therefore, struggled to deal with the heat. Keeping close control over the ambient temperature inside the halls of a data centre is a challenge, with even incremental temperatures outside of the building threatening success.
It’s a problem that’s likely to persist in the coming years. In fact, the Royal Meteorological Society states that 40°C temperatures in the summer months will soon become commonplace. It places urgency on operators to prepare their sites as extreme temperatures become the norm. Therefore, what lessons can they learn from the situation last year and what are the actions they can take to deal with the heat in future?
Futureproofing older buildings
Preparing for extreme weather events equates to having the correct processes, procedures and the right infrastructure underpinning them to ensure resilience. Modern data centres are designed to withstand temperatures of around 44°C, but for older ones which were designed for temperatures up to 35-38°C, it’s certainly a challenge to retrospectively fit and prepare them for extreme heat.
It’s not just high temperatures that need to be considered either; events like Sudden Stratospheric Warmings (SSWs), which can cause cold conditions in winter, are also being affected by climate change. The industry needs to be prepared for these colder temperatures in winter too, all the while meeting ESG and sustainability targets.
Making use of hot and cold aisle containment, high temperature liquid cooling systems, low power servers and reusing waste heat are all tools that can help prepare vulnerable buildings in the coming years. Many of these systems also have a dual purpose in making the building more energy efficient. For example, liquid used for immersion cooling is a more efficient conductor of heat than air.
Maintenance and servicing all year round
With the correct infrastructure as the foundation, processes and procedures are the next step. Here it’s about planning the holistic year-round servicing, maintenance and testing cycle with the changing seasons in mind.
In advance of the summer and the subsequent winter season, data centres need to be prepared for the strain ahead. For example, it’s essential that cooling units are in peak condition ahead of summer, whereas some of the cooling equipment can be turned down in winter to ensure energy efficiency.
As the seasons change, regular services and planned preventative maintenance will need to be factored in. This will not only ensure equipment is prepared for the stresses it faces, but also that major works aren’t required to take place during extreme weather events. It’s often during these events that supply issues can occur, so again, preparedness is key.
All hands on deck
With the correct equipment and a holistic maintenance schedule as the foundation, the third component for peak preparedness is proactivity, especially in the case of emergencies. When extreme temperatures strike, a well-rehearsed plan should be implemented to minimise downtime risk and ensure any issues that do occur can be swiftly resolved.
Where non-essential maintenance is postponed in the event of an emergency, engineers should be positioned in strategic locations around the building to react accordingly. It should not be ‘business as usual unless something breaks’. Instead, these teams can jump on issues as soon as they occur, with each minute saved critical. For example, a reactionary team of engineers should be ready on the roof to fix the cooling systems if needed.
Data centres that offer colocation also provide a number of resources, such as people and skills, to ensure continuity of services. For some pieces of equipment, there may only be a handful of engineers deployed by a manufacturer in a certain geographic location. Larger data centre providers have the size, scale and relationships to ensure priority assistance from these providers in an emergency.
Preparing for the new norm
More extreme temperatures are a certainty as climate change escalates. To deal with these changes and protect the UK’s IT infrastructure, data centres need to be suitably equipped and have the right people in place to respond to any issue.
Little separates success and failure for data centres, where one seemingly small hitch can have huge ramifications on operations. The 2022 heatwave made it clear that preparedness and proactivity are critical to ensuring that success remains a reality and sites can continue to be operational as temperatures rise.