CFD
severely limited in scope. Worse still, they are likely to lead to
other decisions that can even degrade overall performance.
Using heat loads
One way to improve models is to introduce heat loads
into the data hall to simulate the type of workload that's
expected. This data can be captured and then applied to
the model to identify where it begins to diverge from the
captured data. To stay with the racing analogy, this is the
equivalent of using a wind tunnel to test aerodynamic
components before putting them on a racing car.
The use of heat loads is nothing new. An increasing
number of companies already use them to test the initial
design of the data hall. The problem is that they are
not universally used nor are they regularly used during
refurbishment. This is where data centre designers are
missing the point. It’s not just about the heat loads
validating their designs and models, but providing a better
baseline and library of designs that can speed up the design
of data centres in the future.
All about workload
No matter how efficient the design model appears, and how
well it has performed under test conditions, it’s only when
real workloads are applied that it can be truly validated.
This creates a significant challenge for designers. Hardware,
software and workloads change over the life of a data
hall. This means that a model can be outdated before any
hardware has been installed. When hardware changes it’s
possible to import the technical data from the vendor to
update a model, and this will help to improve the model and
the way the data centre is configured. The bigger problem is
software and the underlying workloads.
An example of the problem is the introduction of
virtualisation. Workloads changed from being contained on
servers to running anywhere in the data centre. This created
the opportunity to move high heat loads to areas where
there was adequate cooling. By automating the process it
meant that workloads were prioritised for resources rather
than heat load balancing.
Returning to the motor racing analogy, this is the
equivalent of testing the aerodynamic components on the
car during a test session. It delivers accurate data as to how
the components work under real conditions, which enables
designers to further improve their models.
Moving to real-time data
There are several sources of data that can be used to
help drive models in a live data centre. The key is to take
advantage of the tsunami of sensors that have appeared
over the last 20 years. These are located inside servers,
storage devices, switches, power units, racks and aisles. So
what data can be used and how?
Using the data from sensors in the racks and aisles will
provide information on airflow and air temperature, both
hot and cold. This can be used to feed into the model to see
where it's predicting heat and help make it more effective
with real-time data. If linked to orchestration software,
the d