If you’re facing a data center relocation, one of the most important decisions you’ll be making is site selection. This is true whether you’re considering collocation space or building your own facility. Either way, site selection will have the biggest impact on your implementation schedule, your data center’s reliability and its lifecycle costs. Perhaps your eye was caught by Google’s floating data center concept, a design recognized by Time as one of the best inventions of 2008. Google imagined (and patented) a data center on a raft, with electricity generated by wind turbines and wave power, and the ocean waters cooling the servers. And, of course, there’s no landlord on the high seas. Sounds nice. But before we can fully endorse the Google floating data center notion, let’s take a closer look at some of the issues this data-center-on-a-boat raises for site selection.For a data center with Tier-III class redundancy (the Uptime Institute’s designation for centers that are “concurrently maintainable while in service”), here are some of the factors we need to take into account: SUBSCRIBE TO OUR NEWSLETTER From our editors straight to your inbox Get started by entering your email address below. Please enter a valid email address Subscribe Power Density – What type of systems do you expect to house in the new facility? If you’re expecting to support high density systems (like blade servers requiring 10kW per rack or more), how much room will you need? And if you’re planning to move into an area that only supports 150 W/SF, you will need to space out your racks accordingly (for proper airflow), increasing the amount of raised floor space you thought you needed by a factor of 4. Power Availability – Is there sufficient power available in the grid to supply the site? If not, be prepared to foot the bill for power company infrastructure upgrades which may take 18-24 months to complete. Power Redundancy – Is the space serviced by a redundant substation with independent power feeds to your location (or maybe even multiple substations)? You want that unless you’re prepared to deal with downtime. Power Backup – If you’re looking at an existing facility, you have to ask if it has backup power to cover the center’s full load. It’s also wise to find out if there’s a clear plan in place to increase capacity as you grow. If you’re looking at a new facility, you have to find out if there’s sufficient space for backup power generators and their fuel storage tanks. And are there any zoning issues which may cause delays or add to your costs when you try to install these backup systems? Cooling – Is there sufficient cooling capacity to maintain a proper operating temperature in the facility even when it’s operating on backup power? Is there sufficient floor to ceiling clearance to allow for adequate cool air supply and the removal of hot air exhaust? Quick test: If you’re moving into a facility with 200 W / SQ ft. capacity, are there at least 36-inches of raised floor space to assure adequate airflow for system cooling? If you’re planning on 400 W/SQ FT? Look for a floor raised 4 feet or more. Lack of sufficient height is one of several reasons why conventional office space is suboptimal for anything more than 100W / SQ ft. Network Access – Ideally there should be multiple WAN providers capable of serving your facility, each with redundant fiber / network connections. This will assure long term competition on price and an alternative if one provider’s price or service levels become an issue. Geographic Considerations – Are you planning on putting your data center someplace where earthquakes, hurricanes, tsunamis or floods occur from time to time? I wouldn’t. Will planes fly over it making their approach to a nearby airport? I’d think about that. Will it be easy to deliver replacement parts and get professionals there for needed repairs or maintenance? Is the location safe from terrorism or desperate profiteers like Somali pirates? Perhaps the most costly and avoidable mistake I see companies make is deciding to use a space “because we have it.” Unless you get extremely lucky, it’s highly unlikely that the spare space you have will be suitable for your data center. More likely is that you’ll be paying for it over and over again through costly retrofits, increased infrastructure costs and much higher operating expenses than would otherwise be necessary. Fact is, even “free” real estate quickly can become a very costly proposition for a new data center. Anyway, as real estate represents a very small portion of data center costs,it should not be a primary driver in your decision. Google’s Floating Data Center So how well does Google’s floating data center match up to these requirements? It certainly offers an abundance of energy – provided you’re comfortable with harnessing and depending upon the waves, the tides, the sun and winds. Ocean water indeed can be used to cool the servers through the use of seawater / fresh water heat exchangers, which in turn will cool the air. Of course, the environment better be airtight unless you think salty air is good for servers. (It’s not, by the way.) While the floating data center does offer the promise of cheap real estate, it does so at the expense of increased complexity and risk. Security is on the ocean is—shall we say—problematic. Exposure to disaster is high. Access to multi-WAN providers . . . Who knows? I’m not suggesting Google was entirely serious with its water-based data center patent, but it certainly won’t help organizations that face data center deficiencies today. Perhaps this is part of Google’s secret strategy to scale up its App Engine / Cloud Computing service. If so, good luck, guys! Nonetheless, Google’s floating data center model has raised awareness about the very real and growing problem of increasing data center power and cooling demands. It also provides an excellent way to focus one’s thoughts on what data center site selection really requires and, more importantly, what potential problems could rise from the depths to bite you where you don’t want to get bitten. As always, thank you for sending comments, tips and topic suggestions to me at CIOblog@TransitionalData.com._________________________________Michael Bullock is the founder and CEO of Transitional Data Services (TDS), a consulting firm helping clients implement energy saving green data center solutions, data center relocations, web based enterprise applications and 24/7 technical operations. Related content feature The dark arts of digital transformation — and how to master them Sometimes IT leaders need a little magic to push digital initiatives forward. Here are five ways to make transformation obstacles disappear. By Dan Tynan Oct 02, 2023 11 mins Business IT Alignment Business IT Alignment Business IT Alignment feature What is a project management office (PMO)? The key to standardizing project success The ever-increasing pace of change has upped the pressure on companies to deliver new products, services, and capabilities. And they’re relying on PMOs to ensure that work gets done consistently, efficiently, and in line with business objective By Mary K. Pratt Oct 02, 2023 8 mins Digital Transformation Project Management Tools IT Leadership opinion The changing face of cybersecurity threats in 2023 Cybersecurity has always been a cat-and-mouse game, but the mice keep getting bigger and are becoming increasingly harder to hunt. By Dipti Parmar Sep 29, 2023 8 mins Cybercrime Security brandpost Should finance organizations bank on Generative AI? Finance and banking organizations are looking at generative AI to support employees and customers across a range of text and numerically-based use cases. By Jay Limbasiya, Global AI, Analytics, & Data Management Business Development, Unstructured Data Solutions, Dell Technologies Sep 29, 2023 5 mins Artificial Intelligence Podcasts Videos Resources Events SUBSCRIBE TO OUR NEWSLETTER From our editors straight to your inbox Get started by entering your email address below. Please enter a valid email address Subscribe