9 things to consider before raising IT inlet temperatures to improve data center efficiency
Schneider Electric/APC notes that while it is true that raising the temperature for IT inlets does result in more economizer hours, this does not always have a positive impact on the data center overall.
A new technical white paper from Schneider Electric/APC notes that raising IT inlet temperatures is a common recommendation given to data center operators as a strategy to improve data center efficiency. However, while it is true that raising the temperature does result in more economizer hours, the paper's analysis contends that this does not always have a positive impact on the data center overall.
The paper provides a capex and energy cost analysis of a data center to demonstrate the importance of evaluating the data center holistically, inclusive of the IT equipment energy. The impact of raising temperatures on server failures is also discussed. The analysis demonstrates that there are many variables that influence cost savings (or penalty), and that raising temperatures is not always a good thing.
The authors conclude that, before making temperature changes to a data center, it is important to have a solid understanding of the plant's design conditions, system attributes, load, etc. Schneider Electric/APC therefore recommends the following 9 factors be taken into account before raising data center temperatures:
1. Air management practices such as containment and blanking panels must be in place before attempting to increase IT inlet temperatures. This will avoid creating hot spots.
2. Make sure you understand how your IT equipment will behave (power consumption and CFM requirement) as you raise temperatures. Ask your IT vendors for this information.
3. Consider whether you can adjust the BIOS settings of your IT equipment to optimizetheir performance at higher temperatures. This requires a higher level of collaboration between facilities and IT departments.
4. X-factor predicts a relative increase of failure rates but work with your IT vendor(s) to determine if the actual rate is significant enough to be a concern.
5. Since data centers are not solely made up of servers, make sure you also understand the reliability impact on other equipment like storage and networking.
6. Ensure your cooling architecture can operate at elevated temperatures (i.e. some chillers cannot run at higher chilled water temperatures).
7. Make sure your growth plan comprehends the potential negative energy impact of increasing IT inlet temperatures. In other words, a savings at 50% load might actually be a cost penalty at 80% load.
8. Model out how much total energy you may save by raising temperatures vs. other optimization strategies. Companies such as Romonet have software to help analyze the system dynamics of your specific data center. This is critical because every data center will behave differently.
9. When evaluating changes, be sure to look at total energy consumption as a metric, as PUE alone can be misleading.
View/Download the white paper.