There are many factors that go into a datacenter’s total cost of ownership (TCO) besides site selection. As part of the datacenter Knowledge Executive Guide Series on Total Cost of Ownership, this post outlines other factors that impact a datacenter “build or buy” TCO analysis. Comparative Maintenance Costs Unlike a typical commercial building, which normally does not operate on a continuous basis and has downtime maintenance windows (i.e. nights and weekends), datacenters do not have that option. While virtually all systems require maintenance, there is additional redundant power and cooling equipment installed to provide what is known as “concurrent maintainability.” Maintaining the electrical and mechanical systems in a 7×24 datacenter requires more complicated equipment, as well as a more sophisticated meticulous approach, since downtime is not an option. This requires a staff trained and experienced with bypassing critical systems, without affecting the computing systems. Staffing And Labor Costs Site staff requires multiple skill sets that must be available 7×24 — both common skill sets such as administrative and physical security (guards) as well as technically qualified electrical and mechanical personnel. In a smaller organization, it may be more difficult and expensive to find, train, motivate and retain experienced personnel with the specialized skill sets required for a datacenter, especially with complex redundant power systems. The TCO for staffing in a smaller site (or organization) will generally be higher per unit (SF and/or KW). In particular, the resources (skill levels) requirements to operate and maintain a 10,000 SF site or a 50,000 SF datacenter, are essentially the same. One of the inherent advantages a larger datacenter facility provider has is the efficiency of scale. Their support staff can oversee a campus site with multiple datacenters covering hundreds of thousands of SF on a 7×24 basis, with almost the same personnel cost as an individual organization would need to properly support their own 10,000 SF site. Expected and Unexpected Costs In addition to regular maintenance of all the power and cooling equipment, some items such as UPS batteries, require replacement anywhere between 5–10 years, but typically around 7 years. This is a significant cost and should not be overlooked. In addition, there can be unanticipated expenses from unexpected equipment failures, which can be significant. These costs may or may not come into play depending on whether you built your own site or if you leased the site from a facility operator and it may be covered under the terms of the lease. Occupancy Rate – Design vs. Actual The capital costs are based on the design maximum and the TCO really is based on the effective use (i.e. occupancy rate over time of the actual fill-up of the computing systems.) Essentially, you need to calculate the TCO based on your initial usage in the first few years as well as when the site is more fully populated in 7, 10 or more years. Alternately, if your organization computing requirements are such that you intend to fill the space and fully utilize power capacity almost immediately, your TCO numbers will be based on a fairly straight line number. Reserved Capacity Realistically, a datacenter is not operated at 100 percent of design capacity for a number of reasons, primarily for ensuring equipment reliability and maintaining uptime. Depending on the organization culture, typically systems are operated at no more than 80-85 percetn of design ratings (some may push to 90 percent) before it is considered “full.” Oversize or Undersize Design Capacity Impacts TCO When deciding on the design capacity of the datacenter there are many competing factors that influence the decisions. The fear of making it too small and running out of space or power in only a few years, is a very realistic scenario and fear. In recent years, the growth in computing power demands and power density has made many datacenters that were built less than 10 years ago functionally obsolete, a real risk of then looking for additional space or power that is not readily resolvable with a dedicated single site. Conversely, over-sizing will mitigate that risk, but will increase both the Capex and Opex and of course, the TCO. Modular Design One method to mitigate the potential of over or undersized datacenters is modular design. Capacity planning and modular capacity designs can help mitigate the risk of capacity or functional obsolescence. In some designs, the total space and utility capacity is designed and built upfront, but only individual sections are fully outfitted with the UPS, generators and cooling equipment. This saves both upfront capital cost and recurring maintenance expenses. Moreover, it also improves energy costs, since the smaller sections are more fully occupied and operate at a higher efficiency. This modular design still allows for growth, but in a pre-planned, stepped fashion.