UPS and cooling for data centers: which type your facility needs based on density

Ilustración: UPS y cooling para data center: qué tipo necesita tu instalación según densidad

The choice between UPS and cooling technologies stopped being a generic decision several years ago: IT load density (kilowatts per rack) is the variable that has the greatest impact on the sizing, operational cost, and useful life of both subsystems. A room with 5 kW per rack servers cools comfortably with air; a room with AI clusters at 40 kW per rack needs liquid. Between those two extremes there is a gray zone where the decision depends more on growth projection than on current density.

This article describes the density ranges that define the choice of UPS and cooling, how they relate to each other (because the UPS defines how much energy it delivers and the cooling how much energy it dissipates), which technologies dominate each segment, and the criteria for sizing correctly without over-investing or falling short. The goal is for the reader to finish with a concrete decision map for their target density.

The density map: from 5 kW to 80 kW per rack

Four density ranges define the universe of UPS and cooling you need.

The first, from 5 to 10 kW per rack, is the historical enterprise operation range: typical 1U servers, switches, storage. The dominant UPS is online double-conversion of 20 to 100 kVA per unit; cooling is perimeter CRAC (Computer Room Air Conditioning) with chilled water or direct expansion.

The second range, from 10 to 20 kW per rack, appears with consolidation and virtualization: cabinets with higher compute density. Here the modular online double-conversion UPS begins to replace the traditional one, and cooling migrates to in-row systems or rear-door heat exchangers.

The third range, from 20 to 40 kW per rack, is where the convergence between compute and cooling changes paradigm. AI clusters with GPU (Graphics Processing Unit, a chip originally for graphics but today used massively for AI model training) enter this segment, along with dense all-flash storage. The high-capacity modular UPS (300 kVA to 1.2 MVA per unit) dominates, and cooling migrates to active rear-door heat exchangers or direct cold plate on CPU/GPU.

The fourth range, from 40 to 80 kW per rack, is hyperscale and large model training territory: here the UPS remains high-capacity online double-conversion, but cooling migrates to immersion or direct liquid cooling to the chip (DLC).

How the UPS choice conditions the cooling choice

There is an inverse relationship that many projects ignore: the higher the density, the greater the cooling efficiency, but the more heat to dissipate per square meter. An online double-conversion UPS has an efficiency of 93% to 96% (it loses 4% to 7% as heat). A modular online double-conversion UPS with eco mode (operating mode that prioritizes efficiency over isolation) reaches 98% to 99% at medium load, but loses that advantage at full load. Multiplied by 1 MW of IT load, that 2 to 3 percentage point difference is between 20 and 30 kW of additional heat that the cooling system must dissipate.

The second relationship is the footprint: a 500 kVA modular online double-conversion UPS occupies 1.5 to 2 square meters of floor space and weighs between 800 and 1,500 kg. A rotary UPS (UPS based on a rotating motor-generator, used for loads that do not tolerate even micro-outages) for the same power occupies 8 to 12 square meters and weighs between 4,000 and 7,000 kg, which requires reinforced floor and limits placement in the room. In data centers where footprint is expensive, the rotary UPS is discarded even though it offers greater electrical robustness.

UPS technologies by target density

Three families dominate the UPS market for data centers in 2026:

  • Line interactive: range 1 to 10 kVA, efficiency 96% to 98%, transfer 2 to 6 ms. Suitable for offices, auxiliary racks, non-critical loads. Not suitable for IT racks with loads above 3 kW per rack.
  • Online double conversion: range 10 kVA to 1.2 MVA, efficiency 93% to 96% at full load (up to 98% at half load with eco mode), transfer 0 ms. The industry standard for critical loads. Available in modular versions that allow scaling by 20 to 50 kVA modules without replacing the entire UPS.
  • Rotary (dynamic): range 500 kVA to 3 MVA, efficiency 95% to 97%, UPS + generator combination in a single machine. Suitable for operations that need maximum robustness and can tolerate greater footprint.
  • Cooling technologies by target density

    Five families dominate the data center cooling market in 2026:

  • Perimeter CRAC: operational range up to 10 kW per rack, acceptable efficiency up to 8 kW. Low initial cost, easy maintenance. Limited by distance to the rack: hot air must travel less than 12 meters to maintain uniform temperature.
  • In-row cooling: operational range 10 to 25 kW per rack, installed between rows of racks on the solid floor (does not require raised floor, which is one of its advantages over perimeter CRAC). Eliminates the distance problem of CRAC by bringing the cooling unit directly next to the load, and allows higher density without modifying the site slab. Suitable for retrofit where installing raised floor is not viable or cost-effective.
  • Rear-door heat exchanger: operational range 15 to 35 kW per rack, installed on the rear door of the rack. Captures heat at the point of generation. Compatible with standard 600 mm racks without modifying the layout.
  • Direct cold plate (DLC): operational range 25 to 80 kW per rack, cold liquid plates on CPU and GPU. Requires modification of the servers to include the cold plates and connection to a distribution manifold.
  • Immersion: operational range 30 to 200 kW per rack, servers submerged in dielectric liquid. Eliminates air as a transfer medium. Requires a complete site overhaul: floor, cabinets, liquid handling system.
  • Decision table by density range

    Common mistakes when sizing UPS and cooling together

    Four mistakes concentrate most of the decisions that get reviewed at two years.

  • Sizing cooling for the current density without considering the growth curve: a data center that starts at 8 kW per rack and reaches 20 kW per rack in three years pays double for cooling if it had to replace CRAC with in-row instead of planning the transition from the start.
  • Sizing the UPS for the current load plus a 30% margin without projecting the load to 5 years: the UPS ends up undersized and the scaling option (modular) costs 40% more than buying the modular one from the start.
  • Ignoring the thermal interaction between UPS and cooling: the UPS generates heat that the cooling must dissipate, and if both subsystems are sized independently, between 5% and 10% of operational efficiency is lost.
  • Oversizing the UPS to be “safe”: a UPS operating at 30% load loses between 5 and 8 efficiency points compared to one operating at 60%, which raises the electrical OPEX for the entire useful life.
  • How to start if you are evaluating your project

    Three questions filter 90% of the cases.

  • What is the target density at 3 years, not the current density? If you are going to grow beyond 15 kW per rack, size from the start for in-row cooling or rear-door.
  • Is your current UPS modular or fixed? If it is fixed and you anticipate growth, migrate to modular before the load exceeds 70% of nominal.
  • Is your electricity tariff indexed to consumption or to maximum demand? If it is to maximum demand, the oversized UPS punishes you twice (equipment cost + cost of contracted demand not used).
  • Answering these three questions before quoting avoids 80% of the decisions that get reviewed at 24 months.


    Sources

    [1] ASHRAE — Technical Resources (thermal management guidance) — https://www.ashrae.org/technical-resources

    [2] TIA-942-C — Telecommunications Infrastructure for Data Centers — https://tiaonline.org/product/tia-942-c/

    [3] IEEE — Institute of Electrical and Electronics Engineers — https://www.ieee.org/

    Also in UPS and Backup Power

    ← Back to categories