10 Considerations in Building a Global Data Center Strategy
February 20th, 2013 By: Julius Neudorfer
It would be imprudent to oversimplify all the tangible and intangible elements that need to be fully understood and evaluated when creating a global data center initiative. Yet here are ten considerations to evaluate when building your global data center strategy. This is the forth article in a series on Creating Data Center Strategies with Global Scale.
1) Site Selection and Risk Factors – Knowing Where to Build
Once you have selected a general geographic area, it takes a very experienced team to fully evaluate the suit-ability of a foreign location to build a new data center. Identifying risk factors, both the obvious ones, such as known seismic or flood zones, or the less obvious ones, such as adjacencies to “invisible” but potential hazards, such as airports and their related flight paths, must be an essential part of the final decision.
2) Geopolitical Ownership Considerations
Beyond the basic factors related to physical and logistical resources, the political stability of the country and region should be considered. In some cases the nationality or type of organization of the owner or tenant may make it a target for local political factions.
Insurance costs and even the ability to get coverage may be impacted by building a data center in potential lucrative and growing markets, but which may have a higher risk profile, than a nearby country that has viable communications bandwidth into the target market.
However, be aware that in some volatile or politically restrictive countries, internet traffic is filtered, blocked and or monitored.
3) Global Risk Issues
Given the recent and more frequent catastrophic weather related events affecting even highly developed areas, we all need to review and perhaps re-evaluate our basic assumptions. While there is still some contention about how much Global Warming impacts the world, it is no longer a matter of “if”. Planning based on 100 Year Flood Zones may no longer be considered ultra conservative. The evaluation of any potential data center or other critical infrastructure site is not a cut and dried exercise. Geographic diversity for replicated or back-up sites is no longer an option, it is a necessity.
4) Extended Operation and Autonomy During a Crisis
Regarding availability and continuous operation, how much fuel should be stored locally (i.e. 24 hours, 3 days a week)? During a small localized utility failure 24 hours of fuel may be previously considered adequate, but given more recent events 3-7 days offers a better safety margin. During an extended widespread crisis, the relied upon expectations of daily refueling may prove to be difficult, if not impossible to achieve (case in point, Hurricane Katrina, and “Super Storm” Sandy). In some cases, so much of the general infrastructure was dam¬aged that even fuel availability and delivery to back-up generators became a severe problem (both for data centers, and their employees, limiting their ability to get to work). In the end, you will typically pay more for the co-lo with the greatest levels of redundancy, resources and better SLAs, but would be imprudent to assume that nothing will ever happen to impact the operation of your own data center because you are in a “safe” area. Storing more fuel may be a small overall price to pay for the extended autonomy and could be the difference between being operational or shut down during a major crisis.
Also understand that these same problems would potentially impact your communications providers, so investigate their capabilities for extended operations during a crisis. It is useless if your data center is operational, but your have no viable communications network during a major event.
5) Availability and Cost of Power and Water
Of course picking a site location that is physically secure and has reliable access to power, water and communications is an important first step. Since energy is the most significant operating cost of a data center, focus your attention on the cost of power and its long term impact. Energy costs are highly location dependent and are based on local or purchased power generation costs (related to fuel types or sustainable sources such as, hydro, wind or solar), as well as any state and local taxes (or tax incentives). In the United States rates vary but are generally low compared to some foreign markets. Internationally energy costs are higher and can vary widely. It is important to check local rates and look for utility and energy incentives. Some countries are offering tax and other incentives to build data centers. Another factor is location and long term overall market demand for constrained resources such as power and water, which can ultimately limit the data center capacity.
If the site is relatively remote and needs to be newly developed, be sure to factor in the cost of bring¬ing in new high voltage utility services, which can be expensive and require long lead times to have planned, approved and constructed.
Site selection can also directly impact the facility’s energy efficiency. The relative energy efficiency of the data center facility infrastructure is measured as “Power Usage Effectiveness” “PUE”), as well as the IT equipment use of power vs its computing performance. One of the largest uses of energy is cooling and is location dependent, since it is related to the ambient temperature and humidity conditions. With the rising acceptance of the use of outside air for “free cooling”, picking a location with a moderate climate can offer the opportunity to save a significant amount of energy cost over the long term, as well a lower initial capital investment by the reduced need for mechanical based cooling systems. For more details see part 3 of this series.