In case you missed the first seven parts of this seven part series, I will take just a moment to clarify that this will not be a discussion on the criticality of plugging holes with filler panels and floor grommets, separating hot aisles from cold aisles, minimizing or eliminating bypass and recirculation, deploying variable air volume fans, intelligently locating perforated floor tiles and measuring temperature at server inlets. I do not consider any of those practices to be “considerations”; rather, those practices are what I call the minimum price of admission. None of these practices fall into state of the art or leading edge categories of data center design, but are firmly established as best practices. By all established industry standards and guidelines, these airflow management tactics are the minimum starting point before you can start benefiting from being able to control airflow volume and temperature – the activity of airflow management, and the key to exploiting both efficiency and effectiveness opportunities in the data center.

Airflow management considerations will inform the degree to which we can take advantage of our excellent airflow management practices to drive down the operating cost of our data center. In previous installments of this seven part series, I demonstrated that data centers could be run warmer than conventional wisdom would suggest before increased server fan energy reversed mechanical plant savings before server performance was adversely affected and before server price premiums consumed mechanical plant savings. I then suggested chiller-free data centers are much more realistic than conventional wisdom might purport and provided evidence that IT equipment OEM’s tend to generally allow for wider humidity ranges than mainstream standards and industry guidelines. The first five parts of this series provided evidence from manufacturers’ product information, independent lab research results and math models that together make a rather compelling argument for the efficacy of designing, building and operating data centers without chiller plants or refrigerant cooling. In the sixth piece, I demonstrated how the ASHARE “X” factor can be used to predict the effect on server life and reliability operating in different temperature environments. Up to that point, our focus had been on the health and well-being of our computer equipment and controlling the expense of managing the environment for that equipment. In part seven, I shifted my focus from the health of servers and checkbooks to the health of people working in the data center, specifically what to look for in acoustic hazards. And now, in part 7a of this seven part series, I will continue the focus on human health and a high-temperature work environment.

We have all heard the standard response to the executive’s complaint about being uncomfortably warm when he/she visits the data center: “Well, they call it a hot aisle for a reason.” However, with what I have discussed in the previous seven installments of this series, we can see occasions when the cold aisle is going to be hotter than the hot aisle and then the issue becomes less about comfort and more about safety. After all, when we allow the “cold” aisle to creep up to 100˚F, we should expect to see a hot aisle in the 120-130˚F range. I have not yet seen real life examples of the 140-160˚F that ASHRAE warns us about¹, but we can reasonably expect to see more extreme temperatures as vendors provide us continued assurances about taking advantage of the energy savings opportunities I have elaborated in this series of blogs. Furthermore, there has been some nonsense attached to this issue of high temperature working environments as well, such as OSHA requirements for workers to be tethered in a hot aisle. The fact is that there is no regulatory standard from OSHA or anyone else dictating specific responses to specific temperatures²; nevertheless employers, including data center owners/operators, are held accountable to the General Duty Clause, Section 5(a)(1) of the Occupational Safety and Health Act (OSHA) of 1970, which requires employers to provide a work space that “is free from recognizable hazards that are causing or likely to cause death or serious harm to employees.” The courts have taken action indicating this General Duty Clause specifies that employers must provide a work environment safe from conditions or activities that the industry recognizes as hazardous, including heat-related hazards.³

The data center industry itself, while recognizing there is a high-temperature work environment potential, has not quantified that hazard in any meaningful way, so we need to look elsewhere for some guidance. First, however, we need to understand how to measure temperature. In the data center world we are familiar with dry bulb temperatures and wet bulb temperatures, but for the effect on workers we introduce wet bulb global temperature (WBGT), which is arrived at by:

WBGT = 0.7T_W+0.2T_G+0.1T_D
Where

T_W = Wet Bulb Temperature
T_G = Globe Temperature (radiant heat)
T_D = Dry Bulb Temperature

The radiant heat factor is part of this calculation because most heat stress guidelines are written around outdoor work. While we might suspect there is some radiant heat in the data center produced by conductive heat transfer through the skins of our server cabinets and containment structures, the key variable in Fourier’s Law for calculating this heat transfer is the difference between the inside skin temperature and the outside skin temperature and that difference would be inconsequential in a hot aisle. Although there should be some measurable radiant heat in a cold aisle, for example, purposes here and simplicity’s sake, I’ll assume a hot aisle and therefore essentially equilibrium between the dry bulb temperature and the global temperature. For example, 75˚F @ 20% RH would give us:

(.7 x 54) + (.2 x 75) + (.1 x 75) = WBGT of 60.3

For illustration purposes by the same basis of calculation then,

75˚F @ 60% RH = 71.25˚F WBGT
90˚F @ 20% RH = 71.1˚F WBGT
90˚F @ 60% RH = 83˚F WBGT
100˚F @ 20% RH = 78.3˚F WBGT
100˚F @ 60% RH = 91.6˚F WBGT

These reference examples are actually meaningful to counter-balance the ASHRAE warning that all the temperature thresholds in the National Institute of Occupational Safety and Health (NIOSH) recommendations for exposure limits were less than any of the maximum allowable temperature limits for the various ASHRAE server classes.⁴ For example, when that NIOSH chart recommends 15 minutes of work and 45 minutes of rest for moderate work at 88˚F WBGT, the actual cold aisle dry bulb temperature at 40% RH would be 110˚F and at 30% RH it would be 118˚F, far higher than the dire warnings suggested by ASHRAE based on the NIOSH recommended exposure limits in Table 1 below.

These recommendations from 1992 have been subsequently updated by NIOSH since the publication of the ASHRAE guideline to remove any confusion regarding WBGT. Table 2 below shows the update recommended exposure limits based on adjusted temperature. The baseline temperature in this table is based on being indoors or in the shade at 30% relative humidity. There are degrees of temperature adder for the amount of direct sun exposure, which is not relevant to us and then there are adders and subtractors for humidity, specifically -8˚ at 10% RH, -4˚ at 20%, +3˚ at 40%, +6˚ at 50% and +9˚ at 60%.

One of the obvious implications here ties together what I have previously written about the efficacy of robust grounding and bonding allowing data centers to operate at the low end of vendors’ humidity specifications, which are typically lower than most general industry guidelines, and the associated worker safety and comfort at higher temperatures with lower humidity.
The final ingredient to applying these guidelines to the overall management plan for a highly efficient space is some clarification on what NIOSH might mean by light, moderate and heavy work. I have found no clear definitions specifically targeting our data center work environments, so again we’ll need to extrapolate from other reference points. Table 3 provides some military examples.

Industrial and factory examples are compiled in Table 4 from a twenty-five-year-old text book.

I will leave it to my readers to apply these examples to the activity levels of workers in their data centers to determine how best to plan managing exposure limits, but I feel safe in asserting that after initial construction or perhaps excluding some containment structure installation and assembly, most of our work is not likely going to fall under the heavy column. Also, as mentioned earlier, the exposure levels can be dramatically different between cold aisles and hot aisles, even as you have all enthusiastically embraced my previous endorsements for raising cold aisle temperatures. Therefore, further considerations might be to implement containment with chimney cabinets to minimize the heat exposure or deploy open computer servers or other standard commercial servers that are serviced from the front in conjunction with hot aisle containment to control heat exposure. Another possible consideration might be to schedule third shift standard maintenance activity when all temperatures will typically be more moderate and schedule major upgrades or expansions during cooler times of the year.

In this series of blogs over the past four months, I have endeavored to demonstrate how to maintain budgetary and hardware health in higher data center operating temperatures and I have made the case for seriously considering designing and operating spaces without any sort of mechanical/refrigerant cooling. In the last two pieces, I turned my focus toward the folks working in those spaces and considerations for assuring their well-being. I hope my readers have found this useful and instructive, and as always, we look forward to continuing to learn more through your feedback.

1 Thermal Guidelines for Data Processing Environments, 4th edition, ASHRAE TC 9.9, 2015, page 85.
2 NIOSH Criteria for a Recommended Standard: Occupational Exposure to Heat and Hot Environments. By Jacklitsch B, Williams WJ, Musolin K, Coca A, Kim J-H, Turner N. Cincinnati, OH: U.S. Department of Health and Human Services, Centers for Disease Control and Prevention, National Institute for Occupational Safety and Health, 2016, page vii 3 IBID.
4Thermal Guidelines for Data Processing Environments, Fourth edition, (Appendix E: OSHA and Personnel Working in High Temperatures) Page 102
5 IBID., page 101
6 NIOSH Criteria for a Recommended Standard: Occupational Exposure to Heat and Hot Environments, page 76
6 “Wet Bulb Temperature Monitoring,” (Data derived from “Work/Rest and Water Consumption Table,” Korey Stringer Institute, University of Connecticut
7 The Work Environment: Occupational Health Fundamentals, Volume 1, Doan J. Hansen, CRC Press, 1991, page 156