Air Management in Small Data Centers (report for PG&E, 2016)
Lawrence Berkeley National Laboratory · Magnus Herrlin, Randall C. Cole
An LBNL report funded by PG&E on air management in small data centres shows large fan savings and smaller chiller savings.
On this page
Overview
The report is a 2016 study prepared by Lawrence Berkeley National Laboratory for PG&E, written by Magnus Herrlin and Randall C. Cole. It addresses air management in small data centres, reviews barriers and gives recommendations.
A small data centre is defined in the report as under 5,000 ft2, and elsewhere as a facility with 50-750 kW of IT load. As method, air-management packages are simulated with the Airflow Management Calculator developed by BPA and the DOE Air Management Tool.
The main result is that air management can deliver very large supply fan energy savings (70%-80%) and lower chiller savings (15%-25%). The report also stresses that installing blanking panels, or any single measure alone, is not sufficient for good air management. Limits: the results rest on simulation and the report is aimed at small facilities; the full text was not read for this record. The message for designers is that air management should be treated as a package, not a single measure.
Key points
- Small data centres are defined as under 5,000 ft2; elsewhere as facilities with 50-750 kW of IT.
- Supply fan energy savings from air management can be very large (70%-80%); chiller savings are lower (15%-25%).
- Installing blanking panels or any single measure alone is not sufficient for good air management.
- Uses the Airflow Management Calculator (developed by BPA) and the DOE Air Management Tool.
- Prepared for PG&E; authors Magnus Herrlin and Randall C. Cole.
Using it in design
- In small-room projects, present air management in the airflow module as a package: containment, blanking and fan speed control.
- Show fan and chiller savings separately.
- Do not assume good air management after installing blanking panels alone.
- Check facility scale (under 5,000 ft2 or 50-750 kW IT) as an applicability criterion.
Monthly newsletter · free
Keep your reading list current
Once a month: new library sources, changes to Turkish regulations and upcoming data centre events.
SoSo CAD
Check cooling capacity alongside your design
Review zone heat loads, available capacity and the capacity balance after the largest unit is lost in SoSo CAD.
Request a demo
Who should read it
Engineers and facility managers designing or upgrading small data centres and server rooms.
Publication details
- Authors
- Magnus Herrlin; Randall C. Cole
- Publisher
- Lawrence Berkeley National Laboratory
- Year
- 2016
- Document language
- English
- Source type
- Government / public
- Access
- Free to read
- Licence
- Copyright retained; citation only — the publisher’s terms apply to the original document
Original licence note
Report prepared for PG&E with reuse restrictions stated in its notice; cited only.
Citation
Magnus Herrlin; Randall C. Cole (2016). Air Management in Small Data Centers (report for PG&E, 2016). Lawrence Berkeley National Laboratory. https://eta-publications.lbl.gov/sites/default/files/pgande_final_report_2016_herrlin2001204.pdf
Events on this subject
Browse the events calendarAll content and rights belong to the respective authors and publishers. SoSo CAD provides only the citation, its own summary and a link to the source, and is not responsible for the sources' content.
Related sources
All sources on this topicLawrence Berkeley National Laboratory / ANCIS Incorporated 2023
DOE Data Center Air-Management (AM) Tool: Engineering Reference, Version 3
Calculate required sensible airflow from heat load with a stated temperature rise, air density and specific heat.
- The AHU sheet accepts up to 40 operating units.
Lawrence Berkeley National Laboratory (Center of Expertise for Energy Efficiency in Data Centers) / U.S. DOE FEMP 2020
Data Center Master List of Energy Efficiency Measures, Version 2.0 (September 2020)
Compare the planned UPS module count and redundancy scheme against the load curve: check the per-unit load at day-one and at full build, and consider modular units or switching off surplus modules.
- Variable-speed chillers usually peak at 60-80% of full load; constant-speed chillers peak at full load.
Lawrence Berkeley National Laboratory 2017
Humidity Control in Data Centers (March 8, 2017)
Write the humidity strategy around room dew point: set a wide dead band (about 16 °F to 59 °F dew point unless the IT owner agrees a higher lower limit) rather than a narrow RH band.
- Class A1 equipment is known to function up to 90 °F and A4 up to 113 °F, although all classes share the same recommended range.
Applied System Innovation (MDPI AG) 2026
Proactive Cooling Control Algorithm for Data Centers Based on LSTM-Driven Predictive Thermal Analysis
For predictive cooling control, plan at least one inlet and one outlet temperature sensor per rack; below that, prediction error rose by about 22%.
- The LSTM uses a 60 min input window and a 30 min prediction horizon, with a reported RMSE of 0.25 and R² of 0.985.
Sustainability (MDPI AG) 2026
Retrofit Optimization of Raised-Floor Plenum Thermal Performance for Energy-Efficient and Sustainable Operation of Non-Standard Campus Data Centers
For plenum imbalance, consider a 50%-perforated transverse baffle about 0.3 m from the unit outlet; 50% open gave a smaller resistance increase than 30% (8.5% against 18.7%).
- For S4, SHI fell from 0.42 to 0.35, maximum rack inlet temperature fell from 27.2 °C to 26.7 °C, and all racks met the 27 °C ASHRAE recommended limit.
European Commission JRC 2025
2025 Best Practice Guidelines for the EU Code of Conduct on Data Centre Energy Efficiency (JRC141521, EUR 40267)
Design the facility to operate within the ASHRAE Class A2 allowable range and require A2 operation within warranty in IT procurement; plan separate environmental zones (practice 5.3.4) for legacy equipment.
- IT equipment AC/DC power converters should be rated at 90% efficiency or better across expected load ranges.