skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Data Center Economizer Contamination and Humidity Study

Abstract

Data centers require continuous air conditioning to address high internal heat loads (heat release from equipment) and maintain indoor temperatures within recommended operating levels for computers. Air economizer cycles, which bring in large amounts of outside air to cool internal loads when weather conditions are favorable, could save cooling energy. There is reluctance from many data center owners to use this common cooling technique, however, due to fear of introducing pollutants and potential loss of humidity control. Concerns about equipment failure from airborne pollutants lead to specifying as little outside air as permissible for human occupants. To investigate contamination levels, particle monitoring was conducted at 8 data centers in Northern California. Particle counters were placed at 3 to 4 different locations within and outside of each data center evaluated in this study. Humidity was also monitored at many of the sites to determine how economizers affect humidity control. Results from this study indicate that economizers do increase the outdoor concentration in data centers, but this concentration, when averaged annually, is still below current particle concentration limits. Study results are summarized below: (1) The average particle concentrations measured at each location, both outside and at the servers, are shown in Tablemore » 1. Measurements show low particle concentrations at all data centers without economizers, regardless of outdoor particle concentrations. Particle concentrations were typically an order of magnitude below both outside particle concentrations and recently published ASHRAE standards. (2) Economizer use caused sharp increases in particle concentrations when the economizer vents were open. The particle concentration in the data centers, however, quickly dropped back to pre-economizer levels when the vents closed. Since economizers only allow outside air part of the time, the annual average concentrations still met the ASHRAE standards. However, concentration were still above the levels measured in data centers that do not use economizers (3) Current filtration in data centers is minimal (ASHRAE 40%) since most air is typically recycled. When using economizers, modest improvements in filtration (ASHRAE 85%) can reduce particle concentrations to nearly match the level found in data centers that do not use economizers. The extra cost associated with improve filters was not determined in this study. (4) Humidity was consistent and within the ASHRAE recommended levels for all data centers without economizers. Results show that, while slightly less steady, humidity in data centers with economizers can also be controlled within the ASHRAE recommended levels. However, this control of humidity reduces energy savings by limiting the hours the economizer vents are open. (5) The potential energy savings from economizer use has been measured in one data center. When economizers were active, mechanical cooling power dropped by approximately 30%. Annual savings at this center is estimated within the range of 60-80 MWh/year, representing approximately a 5% savings off the mechanical energy load of the data center. Incoming temperatures and humidity at this data center were conservative relative to the ASHRAE acceptable temperature and humidity ranges. Greater savings may be available if higher temperature humidity levels in the data center area were permitted. The average particle concentrations measured at each of the eight data center locations are shown in Table 1. The data centers ranged in size from approximately 5,000 ft{sup 2} to 20,000 ft{sup 2}. The indoor concentrations and humidity in Table 1 represents measurements taken at the server rack. Temperature measurements at the server rack consistently fell between 65-70 F. The Findings section contains a discussion of the individual findings from each center. Data centers currently operate under very low contamination levels. Economizers can be expected to increase the particle concentration in data centers, but the increase appears to still be below the most conservative particle standards. The particle concentration increase caused by economizer use can also be negated with modest improvements in air filtration. Humidity was consistent and within the ASHRAE recommended levels for all the data centers without economizers. Results from Center 8 show that, while slightly less uniform, data centers with economizers can also control humidity within the ASHRAE recommended levels. The potential energy savings from economizer use is considerable. Annual savings at Center 8 at estimated within the range of 60-80 MWh/year. Greater savings may be available if higher humidity levels in the data center area were permitted. The results from this study indicate that economizers do increase the outdoor concentration in data centers, but this concentration, when averaged annually, is still below current particle concentration limits.« less

Authors:
; ;
Publication Date:
Research Org.:
Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
Sponsoring Org.:
Environmental Energy Technologies Division
OSTI Identifier:
971864
Report Number(s):
LBNL-2424E
TRN: US201006%%868
DOE Contract Number:
DE-AC02-05CH11231
Resource Type:
Technical Report
Country of Publication:
United States
Language:
English
Subject:
32; AIR CONDITIONING; CALIFORNIA; COMPUTERS; CONTAMINATION; ECONOMIZERS; FILTRATION; HUMIDITY; HUMIDITY CONTROL; INDOORS; MONITORING; OCCUPANTS; OUTDOORS; POLLUTANTS; POTENTIAL ENERGY; TEMPERATURE MEASUREMENT

Citation Formats

Shehabi, Arman, Tschudi, William, and Gadgil, Ashok. Data Center Economizer Contamination and Humidity Study. United States: N. p., 2007. Web. doi:10.2172/971864.
Shehabi, Arman, Tschudi, William, & Gadgil, Ashok. Data Center Economizer Contamination and Humidity Study. United States. doi:10.2172/971864.
Shehabi, Arman, Tschudi, William, and Gadgil, Ashok. Tue . "Data Center Economizer Contamination and Humidity Study". United States. doi:10.2172/971864. https://www.osti.gov/servlets/purl/971864.
@article{osti_971864,
title = {Data Center Economizer Contamination and Humidity Study},
author = {Shehabi, Arman and Tschudi, William and Gadgil, Ashok},
abstractNote = {Data centers require continuous air conditioning to address high internal heat loads (heat release from equipment) and maintain indoor temperatures within recommended operating levels for computers. Air economizer cycles, which bring in large amounts of outside air to cool internal loads when weather conditions are favorable, could save cooling energy. There is reluctance from many data center owners to use this common cooling technique, however, due to fear of introducing pollutants and potential loss of humidity control. Concerns about equipment failure from airborne pollutants lead to specifying as little outside air as permissible for human occupants. To investigate contamination levels, particle monitoring was conducted at 8 data centers in Northern California. Particle counters were placed at 3 to 4 different locations within and outside of each data center evaluated in this study. Humidity was also monitored at many of the sites to determine how economizers affect humidity control. Results from this study indicate that economizers do increase the outdoor concentration in data centers, but this concentration, when averaged annually, is still below current particle concentration limits. Study results are summarized below: (1) The average particle concentrations measured at each location, both outside and at the servers, are shown in Table 1. Measurements show low particle concentrations at all data centers without economizers, regardless of outdoor particle concentrations. Particle concentrations were typically an order of magnitude below both outside particle concentrations and recently published ASHRAE standards. (2) Economizer use caused sharp increases in particle concentrations when the economizer vents were open. The particle concentration in the data centers, however, quickly dropped back to pre-economizer levels when the vents closed. Since economizers only allow outside air part of the time, the annual average concentrations still met the ASHRAE standards. However, concentration were still above the levels measured in data centers that do not use economizers (3) Current filtration in data centers is minimal (ASHRAE 40%) since most air is typically recycled. When using economizers, modest improvements in filtration (ASHRAE 85%) can reduce particle concentrations to nearly match the level found in data centers that do not use economizers. The extra cost associated with improve filters was not determined in this study. (4) Humidity was consistent and within the ASHRAE recommended levels for all data centers without economizers. Results show that, while slightly less steady, humidity in data centers with economizers can also be controlled within the ASHRAE recommended levels. However, this control of humidity reduces energy savings by limiting the hours the economizer vents are open. (5) The potential energy savings from economizer use has been measured in one data center. When economizers were active, mechanical cooling power dropped by approximately 30%. Annual savings at this center is estimated within the range of 60-80 MWh/year, representing approximately a 5% savings off the mechanical energy load of the data center. Incoming temperatures and humidity at this data center were conservative relative to the ASHRAE acceptable temperature and humidity ranges. Greater savings may be available if higher temperature humidity levels in the data center area were permitted. The average particle concentrations measured at each of the eight data center locations are shown in Table 1. The data centers ranged in size from approximately 5,000 ft{sup 2} to 20,000 ft{sup 2}. The indoor concentrations and humidity in Table 1 represents measurements taken at the server rack. Temperature measurements at the server rack consistently fell between 65-70 F. The Findings section contains a discussion of the individual findings from each center. Data centers currently operate under very low contamination levels. Economizers can be expected to increase the particle concentration in data centers, but the increase appears to still be below the most conservative particle standards. The particle concentration increase caused by economizer use can also be negated with modest improvements in air filtration. Humidity was consistent and within the ASHRAE recommended levels for all the data centers without economizers. Results from Center 8 show that, while slightly less uniform, data centers with economizers can also control humidity within the ASHRAE recommended levels. The potential energy savings from economizer use is considerable. Annual savings at Center 8 at estimated within the range of 60-80 MWh/year. Greater savings may be available if higher humidity levels in the data center area were permitted. The results from this study indicate that economizers do increase the outdoor concentration in data centers, but this concentration, when averaged annually, is still below current particle concentration limits.},
doi = {10.2172/971864},
journal = {},
number = ,
volume = ,
place = {United States},
year = {Tue Mar 06 00:00:00 EST 2007},
month = {Tue Mar 06 00:00:00 EST 2007}
}

Technical Report:

Save / Share:
  • A new chiller-less data center liquid cooling system utilizing the outside air environment has been shown to achieve up to 90% reduction in cooling energy compared to traditional chiller based data center cooling systems. The system removes heat from Volume servers inside a Sealed Rack and transports the heat using a liquid loop to an Outdoor Heat Exchanger which rejects the heat to the outdoor ambient environment. The servers in the rack are cooled using a hybrid cooling system by removing the majority of the heat generated by the processors and memory by direct thermal conduction using coldplates and themore » heat generated by the remaining components using forced air convection to an air- to- liquid heat exchanger inside the Sealed Rack. The anticipated benefits of such energy-centric configurations are significant energy savings at the data center level. When compared to a traditional 10 MW data center, which typically uses 25% of its total data center energy consumption for cooling this technology could potentially enable a cost savings of up to $800,000-$2,200,000/year (assuming electricity costs of 4 to 11 cents per kilowatt-hour) through the reduction in electrical energy usage.« less
  • The data center in this study had a total floor area of 8,580 square feet (ft{sup 2}) with one-foot raised-floors. It was a rack lab with 440 racks, and was located in a 208,240 ft{sup 2} multi-story office building in San Jose, California. Since the data center was used only for testing equipment, it was not configured as a critical facility in terms of electrical and cooling supply. It did not have a dedicated chiller system but served by the main building chiller plant and make-up air system. Additionally, it was served by a single electrical supply with no provisionmore » for backup power. The data center operated on a 24 hour per day, year-round cycle, and users had all hour full access to the data center facility. The study found that data center computer load accounted for 23% of the overall building electrical load, while the total power consumption attributable to the data center including allocated cooling load and lighting was 30% of the total facility load. The density of installed computer loads (rack load) in the data center was 63 W/ft{sup 2}. Power consumption density for all data center allocated load (including cooling and lighting) was 84 W/ft{sup 2}, approximately 12 times the average overall power density in rest of the building (non-data center portion). For the data center, 75% of the overall electric power was the rack critical loads, 11% of the power was consumed by chillers, 9% by CRAH units, 1% by lighting system, and about 4% of the power was consumed by pumps. The ratio of HVAC to IT power demand in the data center in this study was approximately 0.32. General recommendations for improving overall data center energy efficiency include improving the lighting control, airflow optimization, and control of mechanical systems serving the data center in actual operation. This includes chilled water system, airflow management and control in data centers. Additional specific recommendations or considerations to improve energy efficiency are provided in this report.« less
  • The data center in this study had a total floor area of 3,024 square feet (ft{sup 2}) with one-foot raised-floors. It was a rack lab with 147 racks, and was located in a 96,000 ft{sup 2} multi-story office building in San Jose, California. Since the data center was used only for testing equipment, it was not configured as a critical facility in terms of electrical and cooling supply. It did not have a dedicated chiller system but was served by the main building chiller plant and make-up air system. Additionally it was served by only a single electrical supply withmore » no provision for backup power in the event of a power outage. The Data Center operated on a 24 hour per day, year-round cycle, and users had full-hour access to the data center facility. The study found that data center computer load accounted for 15% of the overall building electrical load, while the total power consumption attributable to the data center including allocated cooling load and lighting was 22% of the total facility load. The density of installed computer loads (rack load) in the data center was 61 W/ft{sup 2}. Power consumption density for all data center allocated load (including cooling and lighting) was 88 W/ft{sup 2}, approximately eight times the average overall power density in rest of the building (non-data center portion). The building and its data center cooling system was provided with various energy optimizing systems that included the following: (1) Varying chilled water flow rate through variable speed drives on the primary pumps. (2) No energy losses due to nonexistence of UPS or standby generators. (3) Minimized under-floor obstruction that affects the delivery efficiency of supply air. (4) Elimination of dehumidification/humidification within the CRAH units. For the data center, 70% of the overall electric power was the rack critical loads, 14% of the power was consumed by chillers, 12% by CRAH units, 2% by lighting system, and about 2% of the power was consumed by chilled water pumps. General recommendations for improving overall data center energy efficiency include improving the lighting control, airflow optimization, control of mechanical systems serving the data center in actual operation.. This includes chilled water system, airflow management and control in the data center. Additional specific recommendations or considerations to improve energy efficiency are provided in this report.« less
  • This document presents the details of a study of the atmospheric impacts of an Hanford Nuclear Energy Center (HNEC) that might result from the use of evaporative cooling alternatives. Specific cooling systems considered include once-through river cooling, cooling ponds, cooling towers, helper cooling ponds and towers and hybrid wet/dry cooling towers. The specific impacts evaluated are increases in fog and relative humidity.