As data centers proliferate, their energy intensity deserves close attention. Always-on operations and growing usage for cloud and other backend processes make servers the fundamental driver of data center energy use. Yet servers’ power draw under real-world conditions is poorly understood. This paper explores characteristics of volume servers that affect energy use, quantifying differences in power draw between higher-performing Standard Performance Evaluation Corporation (SPEC) and ENERGY STAR servers and that of a typical server. First, we establish general characteristics of the US installed base, before reporting hardware configurations from a major online retail website. We then compare idle power across three datasets (one unique to this paper) and explain their differences via the hardware characteristics to which power draw is most sensitive. We find idle server power demand to be significantly higher than benchmarks from ENERGY STAR and the industry-released SPEC database, and SPEC server configurations—and likely their power scaling—to be atypical of volume servers. Next, we examine power draw trends among high-performing servers across their load range to consider whether these trends are representative of volume servers, before inputting average idle power load values into a recent national server energy use model. Lastly, results from two surveys of IT professionals illustrate the incidence of more efficient equipment and operational practices in server rooms/closets. Future work should include server power field measurements in data centers of different sizes, accounting for variations in configurations and setting changes post-purchase, as well as investigating the linkage between time and server energy efficiency.
This is a preview of subscription content, log in to check access.
Buy single article
Instant access to the full article PDF.
Price includes VAT for USA
Subscribe to journal
Immediate online access to all issues from 2019. Subscription will auto renew annually.
This is the net price. Taxes to be calculated in checkout.
For example, all federal agencies must procure ENERGY STAR or Federal Energy Management Program (FEMP) designated products when possible, according to the Energy Policy Act of 2005.
To test the power supplies, NCI followed the generalized internal PSU efficient test protocol document used by the 80 PLUS program (Mansoor et al. 2014). This standard specifies how to set a constant load on the 12 V/5 V/3.3 V rails for a given loading condition (i.e., 10%). NCI tested a single sample of each type of 80 PLUS PSU.
No particular date of publication or revision is given on this site, other than a copyright running from 2007 to 2018. We include the access date for each discrete data collection event.
In an effort to assign a “typical” value based on number of sockets and number of processors, we used median values because they are less influenced by extreme values in the distribution, and also represent an actual value from the distribution.
The most recent year of market share data we had available was 2014.
Assuming a 95% confidence level; the Bureau of Labor Statistics reports 348,500 computer and information systems manager jobs nationwide in 2014 at https://www.bls.gov/ooh/management/computer-and-information-systems-managers.htm.
Bard, A., Huang, R., & Friedmann, R. (2014). From our closet to yours: fashioning energy efficiency programs for small data centers. ACEEE Summer Study on Energy Efficiency in Buildings. http://aceee.org/files/proceedings/2014/data/papers/6-232.pdf. Accessed October 2, 2017.
Barroso, L. A., Clidaras, J., & Holzle, U. (2013). The datacenter as a computer: an introduction to the design of warehouse-scale machines. In M. D. Hill (Ed.), Synthesis lectures on computer architecture (2nd ed.). San Rafael: Morgan & Claypool Publishers http://www.morganclaypool.com/doi/pdf/10.2200/S00516ED2V01Y201306CAC024. Accessed September 21, 2017.
Brown, R., Masanet, E., Nordman, B., Tschudi, W., Shehabi, A., Stanley, J., Koomey, J., Sartor, D., Chan, P., Loper, J., Capana, S., Hedman, B., Duff, R., Haines, E., Sass, D., & Fanara, A. (2007). Report to congress on server and data center energy efficiency: public law 109–431. Berkeley: Lawrence Berkeley National Laboratory LBNL-363E. https://escholarship.org/uc/item/74g2r0vg. Accessed September 15, 2017.
ENERGY STAR. (2013). ENERGY STAR Program Requirements: Product Specification for Computer Servers—Eligibility Criteria, Version 2.1. U.S. Environmental Protection Agency and U.S. Department of Energy. https://www.energystar.gov/sites/default/files/asset/document/Version%202.1%20Computer%20Servers%20Program%20Requirements.pdf. Accessed September 5, 2017.
ENERGY STAR. (2016). ENERGY STAR Unit Shipment and Market Penetration Report–Calendar Year 2015 Summary. U.S. Environmental Protection Agency and U.S. Department of Energy. https://www.energystar.gov/ia/partners/downloads/unit_shipment_data/2015_USD_Summary_Report.pdf. Accessed September 28, 2017.
ENERGY STAR. (2017). ENERGY STAR unit shipment and market penetration report – calendar year 2016 summary. http://www.energystar.gov/ia/partners/downloads/unit_shipment_data/2016_USD_Summary_Report.pdf?12be-ead3. Accessed September 28, 2017.
IDC (International Data Corporation). (2014). Worldwide quarterly server tracker. Installed Base, 2006-2018. Framingham: IDC December.
Koomey, J. (2008). Worldwide electricity used in data centers. Environmental Research Letters, 3, 034008.
Koomey, J. (2012). The economics of green DRAM in servers. Berkeley: Analytics Press http://ww.mediafire.com/view/uj8j4ibos8cd9j3/Full_report_for_econ_of_green_RAM-v7.pdf. Accessed August 30, 2017.
Koomey, J. & Taylor, J. (2017). Zombie/comatose servers redux. http://anthesisgroup.com/wp-content/uploads/2017/03/Comatsoe-Servers-Redux-2017.pdf. Accessed October 2, 2017.
Mansoor, A., Fortenbery, B. Vairamohan, B., Geist, T., May-Ostendorp, P., Calwell C., Rasmussen, R., McIlvoy, D., & Boehlke, J. (2014). Generalized test protocol for calculating the energy efficiency of internal Ac-Dc and Dc-Dc power supplies – revision 6.7. http://ww.plugloadsolutions.com/docs/collatrl/print/Generalized_Internal_Power_Supply_Efficiency_Test_Protocol_R6.7.pdf. Accessed November 9, 2018.
Masanet, E., Brown, R., Shehabi, A., Koomey, J., & Nordman, B. (2011). Estimating the energy use and efficiency potential of U.S. data centers. Proceedings of the IEEE, 99(8), 1440–1453.
Masanet, E., Shehabi, A., & Koomey, J. (2013). Characteristics of low-carbon data centres. Nature Climate Change, 3(7), 627–630.
Natural Resources Defense Council. (2014). Data center efficiency assessment – scaling up energy efficiency across the data center industry. Issue Paper 14-08-A. http://ww.nrdc.org/sites/default/files/data-center-efficiency-assessment-IP.pdf. Accessed September 29, 2017.
Shehabi, A., Smith, S. J., Horner, N., Azevedo, I., Brown, R., Koomey, J., Masanet, E., Sartor, D., Herrlin, M., & Lintner, W. (2016). U.S. data center energy usage report. Lawrence Berkeley National Laboratory Report #1005775. http://eta.lbl.gov/sites/all/files/lbnl-1005775.pdf. Accessed September 20, 2017.
Van Heddeghem, W., Lambert, S., Lannoo, B., Colle, D., Pickavet, M., & Demeester, P. (2014). Trends in worldwide ICT electricity consumption from 2007 to 2012. Computer Communications, 50, 64–76.
This work was supported by the Office of Energy Efficiency and Renewable Energy, Building Technologies Program, of the US Department of Energy under Lawrence Berkeley National Laboratory Contract No. DE-AC02-05CH11231.
Conflict of interest
The authors declare that they have no conflict of interest.
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
About this article
Cite this article
Fuchs, H., Shehabi, A., Ganeshalingam, M. et al. Comparing datasets of volume servers to illuminate their energy use in data centers. Energy Efficiency 13, 379–392 (2020). https://doi.org/10.1007/s12053-019-09809-8
- Volume servers
- Energy use
- Server hardware
- Data centers
- Operational practices