The Tier Classification System is a tool created by the Uptime Institute with the fundamental objective of consistently assessing various data centre facilities in terms of potential site infrastructure performance, or uptime. Accordingly, an understanding of Tiers is beneficial (if not essential) to data centre operators. This should include an insight into UPS’ contribution to Tiers, as UPS availability contributes significantly to data centre uptime.
The Tier Classification System has, over the past couple of decades, evolved from a shared industry terminology into a global standard for third-party validation of data centre critical infrastructure. While this evolution has ensured that Tiers has maintained its importance and relevance, it has also meant that misunderstandings have arisen about Tiers concepts. This makes it all the more important to understand these concepts as they apply today.
THE FOUR-TIER SYSTEM
The system comprises four tiers, with each tier incorporating the requirements of those below, as listed:
- Tier I: basic capacity
- Tier II: redundant capacity components
- Tier III: concurrently maintainable
- Tier IV: fault tolerant.
While the security of the highest possible tier level is tempting, data centre infrastructure complexity and costs increase with tier level. Accordingly, the best practical approach is to choose the tier that most closely fits the data centre’s requirements. This is set by the organisation’s risk tolerance, which in turn is dictated by its business model. This helps operators to avoid the risk of either unjustified over-investment, or unacceptable exposure to power outages.
The Uptime Institute has summarised its tier system as follows:
Tier I: basic capacity
A Tier I data centre provides dedicated site infrastructure to support information technology beyond an office setting. Tier I infrastructure includes a dedicated space for IT systems; an uninterruptible power supply (UPS) to filter power spikes, sags, and momentary outages; dedicated cooling equipment that isn’t shut down at the end of normal office hours; and an engine generator to protect IT functions from extended power outages.
Tier II: redundant capacity components
Tier II facilities include redundant critical power and cooling components to provide select maintenance opportunities and an increased margin of safety against IT process disruptions that would result from site infrastructure equipment failures. The redundant components include power and cooling equipment such as UPS modules, chillers or pumps, and engine generators.
Tier III: concurrently maintainable
A Tier III data centre requires no shutdowns for equipment replacement and maintenance. A redundant delivery path for power and cooling is added to the redundant critical components of Tier II so that each and every component needed to support the IT processing environment can be shut down and maintained without impact on the IT operation.
Tier IV: fault tolerance
Tier IV site infrastructure builds on Tier III, adding the concept of fault tolerance to the site infrastructure topology. Fault tolerance means that when individual equipment failures or distribution path interruptions occur, the effects of the events are stopped short of the IT operations.
Earlier revisions of the tier classification referred to relative values of ‘expected downtime per year’. However, this was removed in 2009; the current standard does not assign availability predictions to tier levels. Industry experience had shown clearly that operations behaviour can impact site availability more than the physical infrastructure. Additionally, Tiers is not prescriptive. It doesn’t define specific technology or design criteria beyond the tier definitions already given. The institute recognises that many data centre designs are individual and custom, with multiple technologies. It is up to the data centre operator to meet the tier criteria using methods that fit their own infrastructure goals.
CHOOSING THE RIGHT UPS
Choosing the right UPS topologies helps operators to build power infrastructures that comply with tier requirements. The most basic level – Tier I – calls for a UPS that filters power spikes, sags and momentary outages. The solution is to use an online rather than offline UPS, as this arrangement ensures the load receives processed power by default. During normal operation, the mains input is fed through the UPS rectifier and inverter, which block mains-borne noise and voltage transients, while providing a well-regulated output voltage.
Note also that Tiers regards an engine-generator as the only reliable source of data centre power, as utility power is subject to unscheduled interruption. Accordingly, ensuring that UPS are capable of synchronisation with generators, and set up to do so, is essential to Tiers compliance.
Using a modular UPS topology allows power system designs to more easily meet redundancy requirements specified by Tiers II to IV. Modular UPS racks can be populated with one to five modules, each having anything from 10 to 100 kVA capacity, depending on the UPS model. This granularity allows easy setup of N+1 redundant systems that are closely matched to the data centre’s power requirements. Better yet, if these modules have ‘hot swap’ capability, compliance with Tier III’s demand for concurrent maintainability becomes easier to manage.
Modular systems’ cost- and space-efficient matching to load size also eases compliance with the Tier III-IV demand for redundant power delivery paths. The need to install a separate UPS system on each power path becomes less onerous if each unit has minimal wasted capacity.
Overall, the Uptime Institute provides third-party, unbiased guidance to operators seeking to design, manage and operate a facility that meets business expectations reliably. This support extends through the life of the facility, starting with Tier Certification in Design Documents (TCDD); these ensure that a planned facility design aligns with the organisation’s ultimate business objectives.
As a data centre moves from a theoretical plan to a real construction, a Tier Certification of Constructed Facility (TCCF) ensures that a facility has been constructed as designed, and verifies that it can meet the defined availability requirements. Finally, because operational stability is the culmination of the tier certification process, the Uptime Institute issues a management and operations (M&O) stamp of approval to ensure operational effectiveness and reduce risk.