Data Centers: Operations & Maintenance, Upgrades, and Expansions

 

If you have been following along with Red Vector’s data center video series, or if you are familiar with the industry, you have an idea of the cost, time, and effort that goes into delivering a data center. From the time that a need is identified, through site search and location, design development, construction, commissioning, and turnover, a company might easily wait 3-5 years or more, and have spent well into the 9 figures. For that level of cost, effort, and duration, you might, not unreasonably, expect the data center to run itself, and maybe even do the dishes, or at least prepare cocktails for the ribbon-cutting ceremony. There is, in fact, an industry term that even implies a self-sufficient facility – a “lights-out” data center. Sadly, at least given current technology, such a scenario is not yet plausible. Without a constant, vigilant, well-planned and well-executed Operations & Maintenance, or “O&M” program, even the most robustly designed and well constructed and commissioned facility is doomed to failure, sooner or later.

 

In addition to a robust O&M program, while not necessarily inevitable, it’s quite typical that over the life of a facility that might well cost over $100M to construct, and house equipment worth multiple times that initial construction cost, a data center will experience an expansion, a system upgrade, or both. For a number of reasons, many of which we will outline later in this lesson, expansions, either planned or unplanned, are a common occurrence in the life of a data center. Upgrades are also quite common given that the life of a data center – typically planned for no less than 25 years – exceeds the expected life of even the most well-maintained electrical and mechanical systems. Thus, over the life of a data center, as untold trillions of bits of information constantly course in, out, and through the facility, the facility manager will all but certainly be faced not only with maintenance of that 99.999% uptime environment, but the assurance of that uptime in the face of upgrades and expansions. Let’s take a look at how best practices can minimize risk and maximize chances for success in the face of such a demanding arena.