• • • DATA CENTRE MANAGEMENT • • •
Maximising data centre uptime while minimising CO2 emissions
he data centre sector is experiencing unprecedented pressure from a number of directions. Customers are demanding the highest levels of performance and sustainability, alongside financial, environmental and political pressure to improve energy efficiency. At the same time, recent growth in the demand for data centres is set to accelerate further with increasing investment in AI infrastructure, and growing concern about a lack of capacity in AI-ready data centres.
T
In the following article, Anu Kätkä an expert in environmental monitoring and control from Vaisala, explains how data centre companies can respond to external pressures by utilising the latest measurement technologies to optimise both energy efficiency and operational uptime.
Reducing CO2 emissions
through sensor selection Data centres account for at least 1 per cent of global electricity consumption, so not withstanding escalating energy costs, and in the context of climate change, it is essential that data centres are
able to optimise their energy efficiency and reduce CO2 emissions.
Up to 40 per cent of energy consumption in data centres is used for cooling and air conditioning. So, reduction in energy use for these purposes will help to improve energy efficiency. However, the performance of computers and servers in data centres can be adversely affected if there is insufficient cooling, overheating can cause IT equipment to fail, resulting in significant and costly downtime. A fine balance therefore exists between minimising the energy consumption of cooling operations and maximising the uptime of IT equipment. This is why accurate, reliable sensors play such an important role. The control of HVAC systems can only be as accurate and precise as the sensors upon which they depend. If the measurements are inaccurate, the output of the building management system (BMS) controller will also be inaccurate. If a poor- quality sensor gives an incorrectly high temperature reading, the controller will react by over cooling and thereby increasing energy costs and emissions. If the same sensor gives an incorrectly low reading, cooling will be insufficient,
which can lead to IT equipment working inefficiently or even breaking down.
Measurement stability is key
to long-term performance It is important to remember that measurement precision is not just about accuracy at the time of installation. All sensors drift over time, to a greater or lesser degree, so measurement stability is vitally important. Some sensor suppliers claim very high accuracy, but they may not have high stability, which means that measurements from these sensors will damage energy efficiency, even after a short period. Good-quality sensors provide accurate measurements that remain accurate in the long term. By ensuring the controller has accurate inputs it is possible to precisely control indoor conditions and optimise energy efficiency. Highlighting the importance of sensor accuracy,
Vaisala participated in a simulation based on three real data centres in Europe, and found that a setpoint temperature difference of just 1°C (resulting from imprecise sensors) could increase annual energy usage by as much as 8.5 per cent.
16 ELECTRICAL ENGINEERING • APRIL 2025
electricalengineeringmagazine.co.uk
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50
