How Much Service Does Your Data Center Need?

Like everything else these days, you have a myriad of choices when it comes to deciding how much service is right for your data center’s critical infrastructure, which supports your digital infrastructure. On one hand, for those who don’t want to leave anything to chance, there are comprehensive maintenance programs with regularly scheduled Preventive Maintenance (PM) visits, 24/7 emergency service, a whole host of add-ons for power equipment (IR scans, switchgear maintenance, and primary and secondary circuit breaker testing), plus cooling optimization services for your precision cooling units. On the other end of the spectrum, there are basic packages that offer only emergency service when a problem comes up. And, of course, there is everything in between.

While you probably won’t lose any sleep debating the merits of the basic vs. premium packages, when it comes to something like your cable bundle, deciding on the right level of protection for the equipment responsible for keeping your business online is a much bigger deal. Nobody wants to pay for service they don’t need, but too little service could cost you much, much more in terms of unplanned downtime, poor system performance, or energy inefficiency.

The service decision clearly has major implications for your business, but it doesn’t have to be a difficult or even stressful choice. Ultimately, it comes down to three things: understanding the value of service, calculating your risk factor, and weighing the consequences you will face if and when an equipment failure does occur.

Here, we take a closer look at each of these issues to help you more confidently select the right service coverage for your data center.

1. What value does the service deliver? Studies, including those commissioned by Vertiv, clearly illustrate that preventive maintenance (PM) service programs, when properly implemented by trained technicians, ensure maximum reliability of data center equipment including UPS units, UPS batteries, power distribution equipment, and precision cooling units. Regular PM does this by providing systematic inspections, detection, and correction of incipient failures, either before they occur or before they develop into major defects that result in costly downtime. According to Vertiv’s analysis, Mean Time Between Failures (MTBF) for Uninterruptable Power Supply (UPS) units that receive two PM service events a year is 23 times higher than a machine with no PM service events per year. Obviously, a little service goes a long way when it comes to equipment reliability.

Beyond ensuring that vital applications stay up and running, regular service also improves equipment uptime, boosts energy efficiency, and ensures peak system performance. All of these benefits help justify the cost of service and often times deliver lasting value that far surpasses the cost of a service contract.

2. What’s your risk factor? Regular service always has value, but how critical is such service in your specific situation? In other words, how likely is it that your equipment is going to fail? While most power and precision cooling equipment is manufactured to be extremely reliable, all equipment contains life-limited components that need to be replaced according to the manufacturer’s specifications. Most service visits include inspections, tests, measurements, and adjustments of these components as well as parts replacement as needed and other housekeeping practices to keep the equipment in good working order.

Deciding how often these PM visits need to happen is the big question. The age and condition of your equipment has a major impact on the answer, along with the manufacturers’ recommendations. Application, installation design, and real-world operating conditions also factor in. Obviously, older equipment operating in more challenging environments, such as where power quality is consistently poor, are at greater risk of failure and may need more attention, sometimes even beyond what the manufacturer suggests.

3. What level of risk can you tolerate? After deciding if your risk of failure is high, low, or somewhere in between, the next step is to weigh the consequences of a digital infrastructure system failure. Think about what would happen if your system went down. Would such an event be labeled an inconvenience (i.e. your employees can’t access their files, and maybe you lose a day or two of productivity)? Or would it be considered a full-fledge catastrophe, costing your business hundreds of thousands of dollars in revenue, alienating your customers, and damaging your brand? The greater the consequences of a failure, the more important preventing one becomes, and the more you should consider investing in service.

It’s important to note that redundancy should be part of this analysis. If your data center has multiple pieces of equipment performing the same function, or if you have dual data centers, for example, then the consequences of one piece of equipment failing or one entire data center going down is less because you already have a backup solution in place. That’s not to say service doesn’t matter. But if you have a high level or redundancy, that could buy you more time between service visits.

There Are No Right or Wrong Answers—Your Comfort Level Is What Matters Most

Regular service for data center critical infrastructure, including power and precision cooling equipment, can be invaluable for a business in many ways. At a minimum, we recommend working with trained technicians to help keep tabs on manufacturers’ recommendations and to ensure components are professionally tested and replaced as specified. Beyond that, a higher level of service can be the key to helping you achieve the levels of availability, performance, and efficiency that are important to your organization’s mission, your customers’ satisfaction, and your ongoing business success.

Click here to explore Vertiv’s Services.