Provisioning for power failure is an important element of data center design. It is important to assess both tangible and intangible costs of unplanned data center downtime. These costs must be compared with the capital cost of providing various levels of backup power infrastructure to compute and cooling equipment. Various levels of backup power infrastructure each lead to a most probable transient scenario after utility power failure. Because of differences between facilities, the level of risk that unacceptable compute equipment inlet temperature associated with each level of backup power infrastructure is not standardized; in particular, facilities with differing compute equipment power densities may require different levels of backup power infrastructure to maintain safe operation. Choosing one level of backup power infrastructure above another is not necessarily obvious for every facility, as there may be large gaps in costs and unknown levels of risk for lower levels of provisioning. A first order model is also used to compare inclusion of various thermal capacitance values with experimental results. Room level experiments also illustrate the relative level of risk associated with various levels of provisioning for the same control volume and compute equipment. Although provisioning to back up as much equipment as possible remains the "safest" solution, cost will continue to play a factor in facility design decisions. This work offers a step toward appropriate modeling of data center power failure events and suggests further steps to continue the process.