All too many data centre operators are unable to answer simple questions about their data centres, such as where best to deploy a new server from a power and cooling perspective, and when they will reach the limits of their power and cooling infrastructure.
This is according to Michelle Souza, programme manager at Schneider Electric’s Energy University, a free, online, educational resource, offering more than 200 vendor-neutral courses on energy efficiency and data centre topics to help individuals identify, implement, and monitor efficiency improvements within organisations.
She says that the Energy University has seen an increase in the data centre courses it offers to the public. In fact, “a comparison of AC and DC power distribution in the data centre”, “advantages of row- and rack-cooling architecture”, and “an overview of data centre physical infrastructure” are now its top three courses.
A number of forces – such as the use of ultra high density IT equipment, pressure to control total cost of ownership (TCO) and more fully utilise data centre capacity, the rapid pace of change due to virtualisation and refresh cycle of IT equipment – put more stress on data centres in today’s business environment.
“So the day of reckoning is likely not far away when you’ll have to be able to provide answers to basic questions about capacity. To do so requires a systematic approach to capacity management, which is the topic of a free course at Schneider Electric’s Energy University, ‘Power and cooling capacity management for data centres’,” says Souza.
As the course makes clear, the foundation of capacity management is the ability to quantify the supply and the demand for both power and cooling. While such information at the room or facility level helps, it’s not sufficiently detailed to answer questions about specific IT equipment deployments.
On the other hand, providing power and cooling supply and demand information at the IT device level is difficult to achieve and unnecessarily detailed. An effective and practical level at which to measure and budget power and cooling capacity is at the rack level.
The model described in the course quantifies power and cooling supply and demand at the rack level in four ways:
* As-configured maximum potential demand;
* Current actual demand;
* As-configured potential supply; and
* Current actual supply.
“You’ll learn more about each of these four measurements during the course as well as why the supply of power and cooling capacity must always be greater than or equal to demand to prevent the data centre from experiencing a failure. This must be true at each rack, and for each supply device supplying groups of racks,” adds Souza.
In practice, that means there should always be excess capacity, meaning overall supply is greater than or equal to overall demand. That excess capacity comes in four different forms for purposes of capacity management, which are spare capacity, idle capacity, safety margin capacity and stranded capacity.
While it’s possible to keep track of all these measurements with paper and pencil, or by constantly updating a spreadsheet, neither is practical. With the dynamic changes made possible by server virtualisation and constant changes in the demand for power and cooling capacity by IT equipment, a more automated solution is required.
Souza explains that the course will explain how power and cooling capacity management software works to address issues including presentation of capacity data, setting the capacity plan, alerting on violations of the capacity plan and modelling proposed changes.
“If it’s not here already, the day will soon come when your spare data centre capacity runs out and you will need to be able to answer some basic questions about how best to utilise your data centre capacity,” says Souza.
“Energy University is also proud to present a further five brand new and exciting data centre courses now open for registration. These are: Comparing efficiency of AC and DC distribution for data centres; Avoiding common pitfalls of evaluating and implementing DCIM solutions; Consolidating the data centre; Fundamentals of cooling architecture II; and Fundamentals of cooling architecture III.”
