Measuring Sustainability: The Certification Process, Part 2Measuring Sustainability: The Certification Process, Part 2

To make sure your data center attains Tier compliance, plan for the certification process before you begin construction.

Data center configurations ranging from non-redundant to fully redundant are possible with the proper design and implementation. The fully redundant is the most expensive configuration to implement and operate. If a low cost design is implemented, then it could also be the less reliable. But cost is only part of the reliability equation; the effect of human error is a major factor as well.

This blog is a continuation of a previous post, "Measuring Sustainability: Certification Value, Part 1" in which Clinton Gage, the Global Marketing Director of the Uptime Institute was interviewed.

Clinton, How does an IT organization go about applying for certification?
It is best to start by connecting with one of our regional leaders and discussing your Tier objectives. There are no special prerequisites to launch the process. Data center owners and operators may engage directly or through an intermediary.

What does the Uptime Institute do in the certification process?
There are different certifications for the various phases of a project, including:

• Tier Certification of Design Documents
• Tier Certification of Constructed Facility
• Tier Certification of Operational Sustainability

How do you evaluate the design documents that describe the solution's compliance?
We verify the site infrastructure solutions, as represented in the design documents, are consistent with the Tier objective of the project. This desktop review will provide consulting support to guide a final design compliant with the Institute's Tier Classification System.

The owner will receive recommendations to enhance Operational Sustainability. Tier Certification of Design Documents is a prerequisite for Tier Certification of Constructed Facility. All Tier Certification of Design Documents awards issued after 1 January 2014 will expire two years after the award date.

The elements of this evaluation include:

• Review of detailed design document package
• Identify Tier deficiencies and Operational Sustainability enhancements
• Teleconference with project team, including project owner and Engineer-of-Record, to ensure comprehension of report findings
• Review of revised design drawing package

How do you verify the data center construction meets the availability expectations?
We determine the facility has been constructed as designed and has the demonstrated capability to meet the target Tier objective. Selected construction phase practices, such as value engineering proposals, represent an opportunity for a Tier-compliant design to be compromised. A team of consultants completes an on-site visit to confirm that the design has been adhered to throughout construction including:

• On-site assessment of installed site infrastructure
• Identify discrepancies between design and installed infrastructure
• Confirmation of commissioning documents
• Observe select demonstrations

Tier Certification of a Constructed Facility is a prerequisite for Tier Certification of Operational Sustainability.

Data center operations also play a part in the sustainability equation. How do you evaluate operations?
We determine that the Operational Sustainability behaviors and risks are consistent with the business Tier objectives. A team of consultants completes an on-site visit to evaluate the effectiveness of each component behavior of the Management & Operations and Building Characteristics elements. Site risk factors and enhancements are evaluated to determine if the appropriate mitigation is in place, weighed in accordance with the Tier Standard: Operational Sustainability in terms of potential impact:

• On-site assessment to validate specific effectiveness of Operational Sustainability behaviors or risks
• Assess site risk
• Identify deficiencies and provide recommendations

Have many IT sites failed Certification? If so, what failed?
In the Tier Certifications underway in over 50 countries, there has not been an impediment to meeting the Tier criteria. Tier Classifications are not a one size fits all, but allow for many ways to meet the criteria.

The most significant deviations from the Tier Standard found in most sites can be summarized as inconsistent solutions. Frequently, a site will have a robust Fault Tolerant electrical system patterned after a Tier IV solution, but will utilize a Tier II mechanical system that cannot be maintained without interrupting computer room operations. This results in an overall Tier II site rating.

Most often, the mechanical system fails Concurrently Maintainable criteria because of inadequate coordination between the number and location of isolation valves in the chilled water distribution path. Another common oversight is branch circuiting of mechanical components, which results in having to shut down the entire mechanical system to perform electrical maintenance. If more than the redundant number of chillers, towers, or pumps is de-energized for electrical maintenance, computer-room cooling is impacted.

Electrical systems often fail to achieve Tier III or Tier IV criteria due to design choices made in the UPS and the critical power distribution path. UPS configurations that utilize common input and output switchgear are almost always unmaintainable without critical environment outages and will fail the Tier III requirements even after spending many hundreds of thousands of dollars. Topologies that include static transfer switches in the critical power path for single-corded IT devices will likely fail both the Fault Tolerance criteria and the Concurrent Maintenance criteria.

Consistent application of standards is necessary to have an integrated solution for a specific data center. It is clear that the IT organization invests heavily in the features offered by newer critical environment technology.

Often, as the electrical and mechanical infrastructures are defined and the facility operations are established, there is a growing degree of inconsistency in the solutions incorporated in a site. An investment in one segment must be met with a similar investment in each of the other segments if any of the elements in the combined solution are to have the desired effect on IT availability. A well-executed data center master plan or strategy should consistently resolve the entire spectrum of IT and facility requirements.

Certification fails typically occur when Certification is sought well after the project has begun. If the design is completed, and construction is nearly complete, the opportunities to address Tier issues are limited.

Do the certifications define any measurable metrics like 99.99% availability?
No. Tier Certification verifies the performance capability of the design, construction, and operation of the site. Uptime Institute cautions against using 99.XXX%, as it can lead to inferences of outages per year in seconds or minutes, when full restoration of service may take hours. Also, this statistical approach may undervalue the exposure to human error, the leading cause of data center downtime.

How does an enterprise know what service reliability to expect?
Service reliability is first determined by Redundancy, Concurrent Maintainability, and Fault Tolerance. Each of these concepts translates to a performance capability that, in turn, supports a defined business need.

Concurrent Maintainability represents a true 24x7 solution, as it eliminates planned downtime for equipment work and replacement. For organizations that can tolerate planned down time, a Tier I or II would be responsive. However, if an organization cannot remove the data center from service without an untenable disruption of the business, then a Tier III (or rarely IV) solution is appropriate.

Layered upon the design and implementation is how the operational site is managed and operated. These Operational Sustainability criteria address the largest exposure to operational data centers: human error. Operational Sustainability provides a methodology to manage the data center to its performance potential over the long term. A Tier IV data center can be defeated by poor management and operations.