There is no doubt that the emergence of high density equipment such as blade servers has dominated the thoughts of those charged with building, operating and the management of data centre environments. Vast increases in density demands have left many scratching their heads in a bid to work out "where next'. But whilst no one can predict the pace of future technological development, planning for the future is key to the long-term success of a data centre.

Sometimes analogies are a good way to learn about complex issues, especially if that issue is as complex as specifying the power and cooling provision to support high density IT loads. In this case, one of the best analogies relates the specification of a car's fuel efficiency to that of a data centre's power density.

Let's imagine that you are in the market for a new car, but given the exorbitant cost of petrol you decide to make your choice according to fuel economy. It is highly unlikely that you would use a measurement such as miles per tank of petrol. Describing fuel efficiency using miles per tank is not sufficient to determine the fuel economy of a vehicle simply because tank capacity varies from model to model. Instead, you are likely to specify miles per gallon (MPG) because this is a comparable measurement which can be made across all car marques and models.

Similarly, why would you specify data centre power density using Watts per square metre (W / m2) when you can't be sure of what is included in area and what is included in power? The problem with this description may be less obvious than "miles per tank', but it is nonetheless ambiguous, misleading and insufficient to determine power or cooling compatibility with high density computing loads like blade servers.

The sidebar "Density Specification Methods' clearly shows that density specifications for What do high density computing loads and the price of petrol have in common? There is no doubt that the emergence of high density equipment such as blade servers has dominated the thoughts of those charged with building, operating and the management of data centre environments. Vast increases in density demands have left many scratching their heads in a bid to work out "where next'. But whilst no one can predict the pace of future technological development, planning for the future is key to the long-term success of a data centre. the same facility can vary by a factor of almost 8 depending on the density definition used. Yet, this is exactly how the power density for most, if not all, data centres is specified today. Unsurprisingly this has led to tremendous confusion in the industry, and common miscommunication between IT personnel and facilities designers and planners.

The historical method of specifying data centre density in Watts / m2 provides little guidance for answering critical questions that are faced by data centre operators today. In particular, the historical power density specification does not answer the key question: "What happens when a rack is deployed that exceeds the density specification of the overall data centre?' This is a very practical question because the typical data centre today has a density rating of 1.5 kW per rack while IT equipment has a power density of 3-20 kW per rack.

Real data centres do not exhibit a uniform power density. For example, some racks draw more electrical power and consequently generate more heat than others. Patch panel racks may draw zero power while blade server racks may draw 20 kW or more. Compounding this problem is the fact that IT equipment is constantly being refreshed and therefore the power consumption within the racks is subject to change over time. Conventional density specifications do not fully take in to account these power variations and as time goes on they become less effective.

At APC we believe that Watts / rack provide a basis for an improved data centre density specification method. This specification method assures compatibility with anticipated high density loads, provides unambiguous instruction for design and installation of power and cooling equipment, prevents oversizing, and maximises electrical efficiency. Specifically, this method meets the following requirements:

• Predictability: Permits the ability to determine the power and cooling capacity at any rack location for any proposed or actual installation of IT equipment.
• Accept partially specified future requirements: Current practice requires that the exact power be known in advance for each rack location, whereas in fact, IT equipment lasts for only a fraction of the life of a data centre and is routinely changed out for new and different equipment.
• Support power and cooling borrowing: Available power and cooling that is not used at a specific rack should be available for use by other racks.
• Minimise waste: Electrical inefficiency should be minimised. Available power, cooling, and space should be utilised. Capital and operating costs should be minimised.
• Support staged deployment: Supports a staged deployment, including the case where different stages may be at different densities, and where the data for future deployment stages is not known at the time of earlier deployments.

With these requirements in mind, a model can be created for density specification which provides many key benefits such as providing a more complete and accurate description of data centre density than other commonly used specification methods. The Watts/ rack calculation offers a stronger mechanism to gauge performance where data centres built to specification will have more predictable performance levels.

Crucially, the model is specific enough that costs, including capital and operating costs, can be rapidly estimated, thus speeding the design cycle and permitting alternate scenario analysis. It also supports a system of modular, scalable, data centre deployment which can dramatically reduce TCO and improve electrical efficiency.

Such a system offers many practical applications such as allowing users to compare TCO associated with alternate data centre sites or room locations; even offering help in estimating costs associated with increasing density in a planned or existing data centre. What's more, this form of density calculation specification clearly establishes density expectations in a form comprehensible to IT users, so that IT users, data centre operators, and data centre systems suppliers establish the same levels of expectation.

The clearest statement of density is "per rack' power consumption. Unlike the traditional Watts per square metre method, it provides unambiguous guidance regarding the power and cooling requirements of a rack (for IT equipment, the rack's electrical power consumption in Watts also equals the cooling requirement in Watts). Per-rack power consumption has another major advantage in the specification of data centre density - namely, that it is the most effective way to specify variations of density within a data centre.

About the Author

Victor Avelar is an Availability Engineer for APC. He is responsible for providing availability consulting and analysis for clients' electrical architectures and data center design. Victor received a Bachelor's degree in Mechanical Engineering from Rensselaer Polytechnic Institute in 1995 and is a member of ASHRAE and the American Society for Quality.