Explaining the Uptime Institute's Tier Classification System (April 2021 update)
Uptime Institute Journal · Matt Stansberry
Matt Stansberry's Uptime Journal explainer that corrects common misreadings of the Tier system. Its most important clarification: Tier levels carry no expected downtime or availability percentage.
On this page
Overview
The article first restates the four Tier outcomes. Tier I includes UPS, dedicated cooling and an engine generator; Tier II adds redundant UPS modules, chillers and pumps, and generators. The author stresses that the standard states desired results rather than a prescriptive checklist, so different engineering solutions can reach the same Tier. A separate paragraph handles the most misunderstood point: Uptime removed 'expected downtime per year' and availability percentages from the Tier Standard in 2009, and the current standard assigns no availability predictions to Tiers.
The 99.671 / 99.741 / 99.982 / 99.995 figures still circulating in the market should therefore not be presented as Tier properties. The certification sequence is described as TCDD, TCCF and TCOS. In TCDD Uptime reviews 100% of the design documents. For TCCF, the article reports Uptime's observation that more than 85% of data centre designs are incorrectly executed in construction; the stage ends with a complete 'pull the plug' test. The TCOS paragraph spotlights human error: in the 2021 outage survey (about 1,000 operators) it accounted for more than 70% of downtime, and over 75% of operators said their latest outage was preventable.
This is Uptime describing its own system; the numbers rest on its survey and certification observations and carry no independent verification. Even so, the product conclusion is clear: present a Tier as a verified level of topology and operations, not as an availability promise. The article ties the existence of TCCF after TCDD to an observation: even though design review covers 100% of documents, more than 85% of designs are incorrectly executed in construction, so approval on paper does not guarantee the result on site.
Key points
- Uptime removed expected annual downtime / availability percentages from the Tier Standard in 2009; the current standard assigns Tiers no availability predictions
- In TCDD Uptime reviews 100% of design documents
- Uptime observes more than 85% of data centre designs are incorrectly executed in construction
- Human error accounted for more than 70% of downtime; over 75% of operators said their latest outage was preventable (2021 survey, about 1,000 operators)
- TCCF ends with a complete 'pull the plug' test
- Tier I: UPS, dedicated cooling, engine generator; Tier II adds redundant UPS modules, chillers/pumps and generators
Using it in design
- Do not display legacy availability percentages such as 99.671/99.741/99.982/99.995 as Tier properties
- If the app shows availability, compute it from component reliability (RBD/Markov) and label it a model estimate
- Add an as-built versus design diff nudge in the commissioning module
- Weight operational readiness heavily in risk scoring
Monthly newsletter · free
Keep your reading list current
Once a month: new library sources, changes to Turkish regulations and upcoming data centre events.
SoSo CAD
Assess redundancy through scenarios
Compare normal operation and equipment failures in SoSo CAD, with supplied loads and capacity shortfalls in one view.
Request a demo
Who should read it
Consultants who explain Tier terms to clients, product teams, and owners new to certification.
Related standards
- Uptime Tier Standard: Topology
- Uptime Tier Standard: Operational Sustainability
Publication details
- Authors
- Matt Stansberry
- Publisher
- Uptime Institute Journal
- Year
- 2021
- Document language
- English
- Source type
- Industry body
- Access
- Free to read
- Licence
- Copyright retained; citation only — the publisher’s terms apply to the original document
Citation
Matt Stansberry (2021). Explaining the Uptime Institute's Tier Classification System (April 2021 update). Uptime Institute Journal. https://journal.uptimeinstitute.com/explaining-uptime-institutes-tier-classification-system/
Events on this subject
Browse the events calendarAll content and rights belong to the respective authors and publishers. SoSo CAD provides only the citation, its own summary and a link to the source, and is not responsible for the sources' content.
Related sources
All sources on this topicUptime Institute 2026
Uptime Institute Tier Certification (TCDD, TCCF, TCOS)
Add a three-gate certification pathway to the project plan, starting with a TCDD-like design review before construction drawings freeze
- TCDD awards issued after 1 Jan 2014 expire two years after the award date
Open Compute Project Foundation 2022
Leak Detection and Intervention, Revision 1.0 (OCP Advanced Cooling Solutions white paper)
Run a probability-and-impact leak risk analysis at project start, specify BSPP/O-ring joints for serviceable connections and check the O-ring compound against the coolant chemistry using the full wetted-materials list.
- A UQD2 dry-break quick disconnect is specified to drip less than 0.063 cc when disconnected at 200 psi.
U.S. Army Corps of Engineers 2006
TM 5-698-2, Reliability-Centered Maintenance (RCM) for Command, Control, Communications, Computer, Intelligence, Surveillance, and Reconnaissance (C4ISR) Facilities (6 October 2006)
At design stage carry out an FMEA for each critical system and record failure modes, effects and detection methods as input to the RCM decision logic; the text stresses that RCM starts in design and continues for the life of the facility.
- For an exponential failure distribution with constant failure rate, an item with a 1000-hour MTBF has only a 37 percent probability of surviving 1000 hours of continuous operation.
U.S. Army Corps of Engineers (Headquarters, Department of the Army) 2006
TM 5-698-4 Failure Modes, Effects and Criticality Analyses (FMECA) for Command, Control, Communications, Computer, Intelligence, Surveillance, and Reconnaissance (C4ISR) Facilities (29 September 2006)
At design stage run a functional FMEA of each critical system (power, generators, cooling); do not start without schematics, bill of materials, block diagram and the mission requirement.
- The Risk Priority Number is Severity (1-10) x Occurrence (1-10), optionally multiplied by Detection: RPN = S x O x D.
U.S. Army Corps of Engineers (Headquarters, Department of the Army) 2002
TM 5-693 Uninterruptible Power Supply System Selection, Installation, and Maintenance for Command, Control, Communications, Computer, Intelligence, Surveillance, and Reconnaissance (C4ISR) Facilities (31 May 2002)
Calculate availability from MTBF and MTTR before choosing a UPS configuration; apply the same method to single-unit, N+1 and dual-redundant layouts to compare the gain from redundancy with the cost of the added components.
- C4ISR facilities require a reliability level of 99.9999 percent (the six-nine rule), which may call for greater redundancy.
Schneider Electric 2025
Direct Liquid Cooling System Challenges in Data Centers
Use the eight challenges as a DLC readiness checklist in the commissioning and design-review module.
- Heat capture ratio defines the air share: 80% liquid capture leaves 20% for air cooling.