Chris Sharp, CTO at Digital Realty, explores why modularity will be critical for data centres and the AI economy.
The emergence of large-scale commercial AI, especially new generative AI applications, has pushed a new set of technical requirements onto the data centre facilities where these applications reside. The infrastructure that supports them will draw more power, chew through more data, and use more bandwidth than ever before, all within facilities that may have been built 20 years ago. These facilities now need to adapt to support what may be in some cases an order of magnitude increase in power draw per rack. The only way to achieve this is with a modular design.
Data centres may seem like highly static entities. They’re typically enormous brick-and-mortar buildings with row after row of generators and other equipment outside. However, the modern data centre is anything but static; many facilities are designed from the beginning to be highly modular, and a given data centre floor may be adapted for changes in network topology, airflow considerations and physical redundancy several times a year if required.
The widespread emergence of AI deployments in the data centre shows how quickly customer requirements can change. Where only last year, a data centre operator may have been able to plan on an average of 10 kW power draw per rack of customer equipment, the need for increasingly large blocks of 25, 50 or even 100 kW racks at different places across that same data centre facility is here and will only continue to grow. With a traditional static design, this can create many problems in terms of performance, maintenance, and redundancy.
Firstly, such dense racks often require more network bandwidth to operate at their highest level of efficiency. This is often overlooked, and a customer will be very unhappy if they deploy such a dense rack (or 10, or a 100 of them) and then can’t get the bandwidth that they require.
Secondly, an uneven increase in power draw across the floor of a data centre can often stress a cooling system that was not designed to accommodate these types of hot spots. A dense rack on one end of a row in the data centre could easily lead to increased temperatures at the other end.
Finally, resiliency and redundancy measures are based on where specific electrical loads are across the facility and how they are distributed. If a very dense cluster of equipment is added in one area, static designs may not be able to ensure that it is covered by enough reliable generator capacity.
A modular approach
For the AI customer, each of these concerns is a significant issue – but by using a highly adaptable modular design framework, these can be addressed in data centres of any age.
For one, spaces can be repurposed or designed-in from the beginning of the facility to be used as additional network rooms to allow for the installation of more network circuits, switches, and routers to boost network bandwidth to the customer over time. Additionally, a modular method of designing and deploying overhead cable trays allows the data centre operator to physically bring that connectivity to the customer, which is often overlooked in static, non-flexible designs.
Understanding the true state of cooling across a facility through the use of CFD (Computational Fluid Dynamics) provides the data centre operator with the means to identify trapped airflow, unintended patterns of airflow that may result in sub-optimal cooling, and where additional air capacity exists that can be used to cool dense, hot AI deployments. Many data centre facilities can also be modular enough to be upgraded from an air-only cooling configuration to a hybrid setup where air and liquid cooling (both AALC and DLC) are available on an as-needed basis, allowing AI deployments to take place as part of an existing data centre floor or larger suite.
With a modular power configuration – where the data centre is conceptualised as a series of blocks each with its own supporting power, backup and cooling infrastructure – core components can be sized and deployed appropriately based on the customer deployment in relatively small increments. This ensures that as deployments are added to a space, even if they differ wildly in power consumption, they can be supported at the expected level of resiliency.
Modular designs will be the difference between being able to support current and future generations of AI deployments in existing sites and needing to build.