Capacity, space allocation and building resilience are among important factors to consider.
Data centers are in high demand by many industries, including agriculture, banking, e-commerce, logistics, defense, mining and health care. As operations become more data-driven, these industries and others rely on secure and efficient infrastructure to store, process and analyze large volumes of information.
According to a recent report by Newmark, data center demand will double by 2030. Given the excess office stock in the United States, adapting an office building (or another underutilized building) can be a win-win solution. However, the conversion process can be challenging due to data centers’ complex infrastructure requirements.
Understanding Leasing for Data Centers
Unlike most asset classes in which tenants lease square footage, data center leases are structured according to power usage along with space rented and related services such as security. Because disruption of service can be catastrophic for data centers and the end users relying on them, redundancy in power and cooling pathways is critically important. The more sensitive the data, the more redundancy is required. Higher redundancy is directly tied to price.
Data centers are classified in tiers according to a standard established by Uptime Institute. Briefly, the tiers are:
Tier 1: Basic capacity with a single path for power and cooling. Uptime: 99.671% (28.8 hours of downtime annually). Suitable for small businesses with noncritical applications.
Tier 2: Redundant capacity components with multiple power and cooling paths (one active). Uptime: 99.741% (22 hours of downtime annually). Suitable for small- to medium-sized businesses.
Tier 3: Concurrently maintainable with multiple active power and cooling paths. Uptime: 99.982% (1.6 hours of downtime annually). Ideal for larger businesses with high availability needs.
Tier 4: Fault-tolerant with fully redundant power and cooling paths. Uptime: 99.995% (26.3 minutes of downtime annually). Suitable for mission-critical operations.
Lease terms include a service-level agreement (SLA) that specifies the uptime, security and maintenance standards the data center must meet. The SLA also specifies who is responsible for various costs related to maintaining the standards and who is liable for losses related to disruption.
Conversion Considerations
Location is a critical factor in determining the feasibility of a site’s conversion. Data centers are generally best suited to commercial and industrial zoning districts and may, in some cases, be conditionally permitted in rural or agricultural areas. It is crucial to evaluate these factors before a project begins because zoning ordinances can vary significantly between municipalities and they continue to evolve.
Access to reliable water sources is also essential for cooling systems and fire suppression infrastructure. Local water regulations, seasonal variability and infrastructure capacity must be assessed to ensure consistent supply under all operating systems. Engaging with local municipal authorities early in the planning process is crucial to confirm site feasibility and identify any additional entitlements or approvals required for conversion.
A building will be suitable for data center use if it has the capacity to deliver required power and cooling, along with the structure and resilience necessary to ensure adequate space and the protection of equipment. These characteristics can be assessed through a well-scoped property condition assessment (PCA) and feasibility study.
Because electrical supply and cooling systems are critical for data centers, a mechanical, electrical and plumbing (MEP) assessment is also fundamental. An MEP specialist can confirm electrical capacity for the proposed project, create an inventory of current equipment, assess the condition of each asset, and provide a capital budget for deferred maintenance as well as a replacement schedule for these assets. Sometimes power requirements will indicate the need for relocating or adding a substation to support the project.
Electrical systems in data centers must include an uninterruptible power supply (UPS) to provide continuous power nearly instantaneously in case of power failure. The MEP specialist will assess the UPS and include a replacement cost and schedule according to its condition and useful life. The MEP specialist can also evaluate existing cooling systems, not only for functionality and adequacy but for efficiency. Sometimes half of a data center’s total energy consumption is used by cooling systems.
The MEP specialist can recommend additions or replacements that can boost efficiency and improve net operating income. For example, replacing older air-cooled chillers with high-efficiency water-cooled units and adding hot-aisle/cold-aisle containment can cut cooling energy use by 20% to 40% and reduce operating costs. Alternatively, implementing liquid cooling solutions such as direct-to-chip or immersion cooling can improve heat removal efficiency, decrease energy consumption by 30% to 50%, and support higher rack densities.
The condition of the roof and building envelope is of great importance. As with any building, water intrusion can undermine the integrity of its envelope and structure. In data centers, however, water intrusion can also damage sensitive equipment, cause short circuits and even start fires, all of which are serious threats to operational continuity. A building envelope specialist should be engaged to evaluate these systems.
In terms of the building structure and space allocation, consider the following questions:
- Where will the computer room be located?
- Where will the battery room(s) be located?
- Is the floor-to-floor height sufficient?
- Is the structural load capacity of the floors and roof sufficient?
- What level of redundancy is required, and where will backup equipment and supporting infrastructure be located?
Finally, consider climate and seismic resilience. A property resilience assessment, performed in conjunction with the PCA, can provide insights about the building’s vulnerabilities to severe weather events and natural disasters by incorporating regional climate data with an evaluation of site-specific characteristics. It will also include recommendations such as structural reinforcements, elevated equipment, and redundant power and cooling systems. A seismic risk assessment can further identify structural weaknesses and recommend retrofits to reduce damage potential during earthquakes. These measures help minimize downtime and increase resiliency.
Moving Forward With a Conversion
If owners believe their buildings are candidates for conversion to data center use, they should enlist the help of a qualified engineering consultant with expertise in MEP, fire and life safety, building envelope and building resiliency, along with specific experience with data centers. These professionals can assess the existing state of the building and identify necessary improvements. Well-scoped, high-quality assessments can provide the data needed to make an informed decision about the owner’s asset and business objectives.
Leo Bertolino is a national client manager with Partner Engineering and Science, Inc. He is also a certified data center infrastructure specialist accredited by the International Data Center Authority.
