How do you know if you are running an efficient cooling operation? If you’re not sure, paying for a cooling audit could be the answer. Cooling audits are popular with some suppliers – some even promise to give you the audit for free if they can’t find any recommendations that will improve your setup and deliver savings that will exceed the cost of the audit.

But once you opt for a cooling audit, what is the process? What can you expect in return?

First, a supplier will pay a visit to your facility to collect the necessary information. This is not a straightforward process and it might take as long as two weeks – although it could take as little as two days.

The audit might take place on consecutive days, or be staggered over several days. The first thing to ensure is that the days where the auditor is present are convenient for you. Having strangers wandering around the data center at your busiest time of the month will not make you popular.

You can expect the supplier to need at least two weeks’ advance notice of when the visit should take place, and possibly more.

So, what will they examine and what can you expect from them when they arrive on site? The old adage that ‘you can’t change what you can’t measure’ applies here. A company will first want to check existing conditions in the data center.

This will help the supplier assess exactly how far from efficiency your facility is and naturally allow it to start pricing any remedial action. Many factors will immediately come into play – from your location, to the shape of your data center. The assessment will involve checking temperatures and humidity levels (some suppliers call this the temperature and humidity baseline). “The T&RH (temperature and relative humidity) profiles are used for the evaluation of existing conditions, and as a baseline for trending and optimisation,” says an assessor. “The profiles are evaluated against relevant industry preferred practice recommendations, hardware specifications and customer-defined data center goals.” From this assessment, the supplier will build a profile of your data center based on factors such as type and age of IT equipment, and airconditioning placement and effectiveness.

“The T&RH profiles are used for the evaluation of existing conditions” Other factors that will impact the profile are hot spots and high-density hardware equipment layout. Taking measurements at the hardware intakes is vital, and these measurements should be multipoint and take into account intake and exhaust conditions.

The supplier is looking for areas with problems such as air bypass, bad recirculation, and design inefficiencies and implementation.

After the initial assessment, the supplier should be able to correctly identify placement and location of all equipment in your data center. Be available to make sure that what they believe to be strategic is also what you know to be vital. The measurements at the computer hardware intakes are used to identify areas in need of improvement, so make sure the correct measurements are being taken.

The data that is recorded will be used to analyse the functioning of air-conditioners, the influence of outside sources, such as exterior air temperatures, and other factors that will affect cooling.

ENVIRONMENTAL SUPPORT
The setup and efficiency of the environmental support equipment that provides cooling may be evaluated in relation to site-specific conditions and hardware requirements.

Make sure that all air-conditioners serving the data center are examined, and that information regarding set points, sensitivities or dead bands, control modes, function modes, calibration, alarms and other factors are examined and documented.

The physical conditions and maintenance logs should be examined as part of the assessment.

The supplier should also wish to speak with data center management who define policies, and personnel with responsibility for maintenance of the air-conditioners. Airconditioner and humidifier sensors should be calibrated, where possible, against a control standard, although this may be limited by the age of the equipment, or by site restrictions.

WHAT ARE YOUR RESPONSIBILITES?

Any assessment will require co-operation between the data center operator and the supplier. Reasonable requests should be adhered to, but beware of terms and conditions. Remember, an audit will require granting the supplier access to documentation, personnel and procedures that may be commercially confidential. On a practical level, the supplier will ask for access to telephones, copiers, faxes, conference rooms and printing facilities. You will need to consider this when looking at the costs. The supplier will want to see service level agreements with relevant suppliers. Access to personnel, including business, IT and operational staff, will be required. It will be up to you to ensure disruption is kept to a minimum. You might consider appointing a full-time escort. The supplier will ask for timely delivery of information. You must dictate what is reasonable and the supplier will want to ensure that its ability to deliver the service is not adversely affected. Disclosure of details of standards to which the data center operation adheres will be required. If the audit runs into timing problems, or information is not forthcoming, the supplier will have an escalation procedure to ensure the audit is completed within the agreed timeframes. Some suppliers will want to see your organisational, configuration and process documents. It goes without saying that the supplier will need access to the facilities and IT infrastructure. This means not just the data center, but also mechanical and electrical rooms, and any power-generation facilities that are onsite. The supplier will require a briefing on all aspects of the mechanical and electrical plant being used. There needs to be customer personnel who are knowledgeable about the mechanical systems and electrical infrastructure, including air from outside the controlled environment (fresh air, building air, shared primary air, and so on), as well as the electrical infrastructure from the utility supply to the facility to the data center (generators, UPS, PDUs and so on). The supplier will want to take photographs. Ensure that no proprietary information is exposed or distributed. You will need to choose a time when no major changes are taking place to any server, storage or networking hardware or software, as this will affect the final report. Choose a quiet month.

COOLING ADVICE FROM APC

Plan for a power density that is increasing and unpredictable Industry projections of power-density requirements show great uncertainty, but new data centers must meet requirements for 10 years. They must also take into account IT refreshes that occur every 18 months to two-and-a-half years. System design, so that it can be adapted easily, even retrofit, must cool high-density racks which might be isolated cases or widespread in future. Adapt to ever-changing requirements Loads are frequently changed. It is difficult to know if the cooling system must be changed, and difficult to determine if the existing system can provide sufficient cooling. Install a cooling system where it is possible to assure that a new load can be cooled, and where cooling can be easily and quickly directed to isolated high-power loads, without complicated construction and planning.   Allow for cooling capacity to be added to an existing operating space Many existing spaces were not designed for the power density currently being installed or planned. Adding cooling capacity to an existing operating data center or network room can be difficult and costly. Retrofit options, which provide additional cooling capacity, possibly targeted at specific racks or equipment, which can easily be installed without complex planning or engineering, and without replacing or shutting down the existing systems.

COOLING USING CFD

A White Paper from Future Facilities describes one path to cooling efficiency   Modern IT equipment with high-power dissipation and powerful internal cooling fans are a primary cause of cooling and e ciency problems in today’s mission-critical facility. These problems appear when high-velocity, high-temperature exhaust air from IT equipment - ows unintentionally into the inlets of surrounding equipment, despite measures taken to prevent such occurrences. The conventional approaches to data center cooling design, such as the hot aisle/cold aisle layout, kW per cabinet limits and the use of traditional computational - uid dynamics (CFD) software tools, are blind to equipment-related cooling and e ciency problems. Future Facilities, describes Cooling Path Management (CPM), a CFD-based methodology for data center cooling design and optimisation. CPM can address all possible air- owrelated cooling breakdowns, and sources of ine ciency for any con guration of room, cooling system and IT equipment. CPM can be used for initial cooling system design and for ongoing management of cooling system performance that is a challenge due to IT equipment-related cooling problems and the time-varying nature of IT deployments. CPM is based on a specialised implementation of CFD analysis that solves the governing equations for - uid motion and heat transfer over the full range of physical scale that occurs in the data center – from small gaps within cabinets to the open room. This implementation of CFD provides a 3D graphical view of the entire cooling path over which the breakdowns occur. The cooling path is the route taken by the cooling air from the air handlers to the intakes of each unit of IT equipment and from each exhaust vent back to the air handlers. Cooling paths are formed by the thermal and physical characteristics of the IT equipment, cabinets and room, and the way they are con gured within the data center. The cooling path can be split into three primary segments to simplify the CPM design process, as shown in Figure 2. Each segment of the cooling path has a specific design goal and associated set of design options. This makes CPM intuitive, easy to use and applicable to all possible combinations of IT equipment, cabinets and rooms.  Understanding the interactions between thermal footprint and the environment is the basis for addressing the most common data center cooling and efficiency problems. Given the impact of thermal footprints on the data center environment, it is no surprise that cooling path segments can change dramatically with each configuration of IT equipment, cabinets and room. As a result, resilience and efficiency are dramatically impacted by IT equipment refresh and locations changes.

CHANGING UP
After the assessment is complete, the supplier will work on a plan to modify the air-conditioner and humidifier set points. The plan will need management approval before any action is taken.

An air-distribution efficiency assessment is an airflow assessment from the airconditioners to the final distribution at the hardware, and all airflow between these points.

This assessment will include looking at air distribution tile placement (these are often in the wrong place) and hardware alignment.

Tiles and cable cutouts are evaluated to determine potential recovery for more efficient cooling.

The movement of air distribution tile placement and number will be made to fix any problems, and large cable cutouts can be minimised. Changes should be reassessed.

Measurements of changes are best done overnight, and for longer periods at various IT loads and conditions.

Many assessments also offer ‘what if’ scenarios that will map the likely effects of CRAC (computer room air-conditioner) failures. These can be effective and CFD (computational fluid dynamics) is a fastmaturing discipline.

The final assessment will be presented in an optimisation report that explains the process and data, and provides guidelines for maintenance between site visits.

Make sure your supplier is working to industry-accepted best practices and compliance standards, such as the American Society of Heating, Refrigerating and Air-Conditioning Engineers (ASHRAE); the American Society for Testing and Materials (ASTM); BSI British Standards; International Electrotechnical Commission (IEC); IEE Wiring Regulations; Institute of Electrical and Electronics Engineers (IEEE); International Organization for Standardization (ISO); National Electrical Code (NEC); and the National Fire Protection Association (NFPA). And also make sure they know the manufacturer specifications and are operating to verified field methodologies.

Ask what short-term measures can be implemented and what long-term strategies would the supplier recommend.

The supplier should then provide an assessment report, which should contain the following:

• A description of the actions provided;
• A summary of the findings;
• Recommendations for any additional actions, if required; and
• Representations of improvements achieved.

This article appeared in DatacenterDynamicsFOCUS magazine June/July Edition. Subscribe to the Digital Edition here