This white paper from AdaptivCool offers and in-depth analysis of the issues that occur when computer room air conditioners (CRACs) inject vast quantities of relatively warm air under the raised floor of a data center.  It describes the disconnect between above- and below-floor zones of influence for individual cooling units and the dangers associated with obvious solutions to the problems.  Lastly, it offers strategies for placement of above-floor and under-floor air-movers to dynamically manage airflow.

Learn to reduce mixing both above- and below- floor without significant changes to data center infrastructure. Click here to download this whitepaper from AdaptivCool on the importance of considering below-floor space when creating cooling-cost-reducing strategies for your data center.

This white paper from Movincool examines the benefits of using ceiling-mount air conditioners to keep server rooms and closets cool inside heated buildings.  It discusses the importance of system cooling, citing the ease with which overheating can be missed or ignored.  It then reviews the significance of cooling systems throughout the history of the computer, explaining the differences between mini-splits and precision cooling systems, and the drawbacks associated with precision units such as their large size, high cost of installation and limited placement flexibility.  Next, the functions of a ceiling-mount air conditioning unit and the advantages to utilizing them are explored, such as low cost, easy installation and flexible placement, as well as what to look for when choosing a self-contained, ceiling-mount air conditioner.

Learn the many advantages of ceiling-mount air conditioning systems and the dangers of overheating.  Click here to download this whitepaper on the history of server cooling, the drawbacks of standard mini-split and precision cooling systems and the benefits of self-contained, ceiling-mount air conditioners.

Please visit the Data Center Knowledge White Paper Library for all the latest expert insights on technologies to run your data center.

This white paper from Opengate defines cooling over-supply and the dangers of the mixing of cooling overprovision with hot exhaust air from IT equipment.  Next, it provides examples for quantifying cool air bypass and hot air recirculation, and solutions to eliminate leakage and bypass while providing tools to report the actual cooling being demanded by the equipment. Lastly, it demonstrates these solutions through detailed examples of reclaiming stranded cooling.

One of the key aspects you will like are the peer reviewed case study data from ASHRAE which have been updated with CFD model analysis. These studies reveal more information and provide visual cues about best practice on ceiling grate return and other passive cooling methods.

Learn the ability to more closely match the cooling supply volume to IT consumption.  Click here to download this white paper on the benefits of reclaiming the wasted cooling capacity which results from hot air leakage and cool air bypass.

The new facility will use a custom cooling system from Deerns America, which has been hired for its expertise in green data center design. Deerns America, a mechanical and electrical engineering firm, will implement its Green Cooling for Data Centers (GC-DC) technology. Green House Data says it expects this approach to outside air cooling, and with its efficient design, will allow the new facility to run at an annual average Power Usage Effectiveness (PUE) of 1.16 and a peak PUE of 1.22.

“This progressive step is an exciting advancement for our company adding additional data center space utilizing energy efficient 100% free cooling,” said Shawn Mills, President of Green House Data. “I see the increasing demand for low-energy cooling systems, green technologies and efficiencies as an avenue to reduce utility costs and offer these savings to our clients in this competitive industry.”

Separate Air Streams

In Deerns ‘cooling system, outdoor air is drawn through a plate heat exchanger, where it absorbs heat from the IT room’s hot return air. It is then cooled and re-circulated through the data center. By separating the air streams, the outside air can be cooled evaporatively without influencing the humidity in the data hall and without risk of contamination from dust, smoke, pollen, and other particulates. If outdoor air temperatures rise, evaporative coolers will provide low-energy supplemental cooling without requiring refrigeration-based cooling systems.

The design employs a slab (hard floor) aisle containment. Additionally, the cooling system can seamlessly grow along with Green House Data’s modular data center building design as new units can be added as needed.

“With the cool, dry geographical location selection chosen by Green House Data, implementing our free cooling system will have a great impact on energy efficiency,” said Gary Cudmore, Principal of Data Center Engineering for Deerns America. “Additionally, the GC-DC system we’ve developed for this project will provide a data center environment complying with ASRHAE TC 9.9 guidelines without the need for expensive, energy-intensive chillers.”

Deerns is a privately-owned firm with headquarters in the Netherlands and branches in the United States (Denver and Rockville, Md.), Germany, France, Spain, the United Kingdom, and Dubai. Deerns is focused on critical infrastructure including data centers, airports, hospitals, clean rooms, and biohazard labs. In the last five years Deerns has designed more than 2.3 million square feet of white space with almost 700 megawatts in IT power. The company’s GC-DC cooling id described in a white paper on its web site.

A server tray using Asetek's Rack CDU Liquid Cooling system, which was announced this week. The piping system connects to a cooling distribution unit. (Source: Asetek)

Asetek Inc., a leading supplier of liquid cooling solutions for high-performance gaming PCs and workstations, has announced its entry into the data center market.  The San Jose, Calif. company this week unveiled a suite of products adapting its technology for servers and racks, and is targeting the offering for the high performance computing (HPC) market, as well as financial companies conducting high speed trading.

“We have studied the server market and engaged with our customers,” said André Sloth Eriksen, Founder and CEO of Asetek. ”While much of what is written suggests that the problem of data center cooling is monolithic, we have discovered the need is for a diverse set of solutions to meet specific data center performance, density and efficiency objectives. Using proven Asetek technology to engineer a range of cooling solutions gives Asetek a unique ability to address the wide diversity of cooling challenges that exist in the HPC and data center market today.”

Asetek’s liquid cooling systems use a cold plate and pump to extract heat from CPUs and GPUs, and are deployed today in hundreds of thousands of computers, the company said. The company is providing three levels of server cooling:

• Internal Loop Liquid Cooling enables the use of the fastest processors, including high wattage processors, in high density servers.
• Rack CDU Liquid Cooling removes processor and or GPU heat from rack servers and blades out of the data center without the use of traditional computer room air conditioners or water chillers, enabling extreme densities on server, rack and data center level. The strongest value proposition however, is that the solution uses free outside ambient air cooling allowing around 50% power savings on the data center cooling cost.
• Sealed Server Liquid Cooling removes all server heat from the data center via liquid; literally no air from inside the data center is used for server cooling. This solution enables high density with high performance processors and ambient room temperature server cooling.

Liquid cooling provides a more efficient heat transfer than air, and offers potential savings to companies that can commit to a liquid-cooled design. It has been used primarily in high-performance computing (HPC) and other applications requiring high density deployments that are difficult to manage with air cooling.

Interest in liquid cooling has been on the rise as a growing number of applications and services are requiring high-density configurations. In recent years we’ve featured liquid cooling technology for the data center from companies including Green Revolution, Clustered Systems, Hardcore Computer, Iceotope and Coolcentric (Vette).

Asetek says its pumping systems use low pressure, which reduces failures because it puts less stress on joints and connections. The company says its liquid channels are helium integrity tested and sealed at the factory for its life time, eliminating the need for any liquid handling by the server OEM, or data center operator.

Asetek’s solutions are used by leading OEMs servicing the gaming, workstation and performance PC and data center markets. Founded in 2000, Asetek has offices in San Jose, California, Denmark and Asia.

This white paper from MovinCool examines the benefits of using ceiling-mount air conditioners to keep server rooms and closets cool inside heated buildings. It discusses the scenarios in which overheating can be missed or ignored, explains the differences between mini-splits and precision cooling systems, and the drawbacks associated with precision units. Next, the functions of a ceiling-mount air conditioning unit and the advantages to utilizing them are explored, as well as what to look for when choosing a self-contained, ceiling-mount air conditioner.

Learn the many advantages of ceiling-mount air conditioning systems and the dangers of overheating. Click here to download this white paper on the benefits of self-contained, ceiling-mount air conditioners.

Please visit the Data Center Knowledge White Paper Library for all the latest expert insights on technologies to run your data center.

The tunnels linking data halls in the Green Mountain Data Center in Norway, which will use cool water from a nearby fjord to support its cooling system.

A small but growing number of data centers are slashing their cooling costs by using the environment as their chiller, tapping nearby rivers, underground lakes, wells and even the Baltic Sea. A new project in Norway plans to draw cold water from an adjacent fjord and use it to cool data halls.

The Green Mountain Data Center is located on the shores of the island of Rennesoy, inside concrete buildings within caves carved out of the mountain. Racks of servers will now fill underground halls that once stored ammunition for NATO.

The project is being developed by the investment arm of the Norwegian shipping firm Smedvig, which is working with a leading Nordic IT services firm, ErgoGroup, and electric utility Lyse Energi.

The ability to use the fjord as a low-cost source for chilled water was a major advantage of the Rennesoy location. Green Mountain’s cooling system taps the fjord for a steady supply of water at 8 degrees C (46 degrees F), which is optimal for use in data center cooling systems.

Chilled water is a key component of many data center cooling systems. This water is often supplied by chillers, large refrigeration units that require a hefty amount of electricity to operate. Eliminating the chillers will usually allow a data center to operate with lower energy bills than similar facilities using chillers.

The Green Mountain Data Center is being built out in two phases. The first phase is designed for traditional colocation space, and will include about 7,000 square meters (about 75,000 square feet) of data center space. Another 4,000 square meters (43,000 square feet) will house data center container solutions, which will also use chilled water for cooling.

The developers are in the late stages of negotiations with Norwegian clients, but believe the facility may be attractive to multi-nationals based in the U.S. and Europe. “We are now mainly focusing on corporate customers with worldwide facilities who wish to reduce their carbon footprint across their portfolio of data centres, improve their ‘green credentials’ and reduce spending on power,” said Jonathan Evans of Green Mountain.

The build-out of the colocation halls will begin in January, and the power to the facility is also being upgraded. Green Mountain expects the first clients to be installed in late 2012. Here’s a video providing a conceptual overview of the project.

The Green Mountain Data Center is adjacent to a fjord, which provides a supply of 8 degree C water that will be used in the cooling system.

This graph rich whitepaper compares the two types of economizers – fluid and air. The pros and cons of each one are explained in detail and how they can be utilized in places as diverse as Atlanta and Chicago. Considerations range from capital expenditure costs, best operating hours, duct work, estimating annual energy savings and safely bringing in outside air.

Special consideration must be given to the data center climate control system because sensitive electronics should only be subject to systems that are proven. However, with a potential of 50% energy cost savings this technology cannot be overlooked and deserves a serious review from the IT strategist.

The new blade servers enclosure from Clustered Systems pack 16 blades into a 20 kilowatt chassis. Each blade is cooled with a cold plate, which contains a tubing system filled with liquid coolant.

A new blade server chassis featuring technology from Clustered Systems is promising to cool computing loads of up to 100 kilowatts in a single cabinet. The system, which breaks new ground in the effort to pack massive computing power into smaller spaces, will get its first test drive at  the SLAC National Accelerator Laboratory in Palo Alto, Calif.

Average server racks in most data centers use between 4 kilowatts (kW) and 8 kW of power. Cloud computing and high-performance computing (HPC) centers feature denser infrastructures of 12kW to 20 kW and more. The new blade chassis promises to push the boundaries of high-density computing to 80kW to 100kW per rack.

Perhaps most intriguing: the system requires only a 480V power source, and a water supply, with no chillers and minimal cooling infrastructure.

“Changing the Data Center Dynamic”

“If we are successful, then the whole dynamic of data center deployment could change,” said Phil Hughes, CEO and founder of Clustered Systems. “A user can put a system anywhere there is power. No special facilities are required. All investment can go into compute and not have to be shared with bricks and mortar.”

The new blades build on Clustered Systems’ success in a 2010 “chill-off” in which its technology proved more efficient than existing cooling products from major data center vendors.

They key to the system’s density is a fanless cooling system using a cold plate, which contains a tubing system filled with liquid refrigerant. By removing fans and dedicating more power to processors, the Clustered Systems design can support unusual power densities.

The refrigerant system includes a pumping unit and heat exchanger, in which the refrigerant interacts with a water loop. In testing, the system has continued working with water temperatures as high as 78 degrees, meaning it can operate without a chiller, according to Hughes.

“It is expected that the initial deployment will be cooled with tower water or with return water from upstream legacy cooling systems,” he said.

Consortium of Partners

In 2010 Clustered Systems partnered with Emerson Network Power on the Liebert XDS system, which used cold plates on server trays in a 1U rackmount design. The installation at SLAC adapts the technology for blade servers, which can be challenging to cool due to the way they concentrate processing and power consumption.

Each chassis takes up 8 rack units and includes 16 blades, each with two cold plates for heat removal, and a 20kW power distribution unit. Five of the 8U chassis can fit in a rack.

The blade server chassis was jointly developed by a group of companies including Clustered Systems, Intel, Emerson Network Power, Panduit, OSS (One Stop Systems, Inc.), Smart Modular and Inforce. The system development was funded by $3 million in grants from the U.S. Department of Energy and California Energy Commission.

“The efficiency of the Clustered Systems’ cooling system supports the greatest level of density and performance we’ve seen so far, and it has the legs to support several more product generations,” said Dr. Stephen Wheat, Senior Director of Intel High Performance Computing.

System Overview

The cooling system uses Emerson Network Power’s Liebert XD pumped refrigerant cooling products. Emerson also designed and built the system rack, which features a NetSure DC power system which converts 480V AC power to 380V DC power.

The 380V DC will then pass to a Panduit unit in each enclosure which controls power delivery to each blade. “The concept of a power plane manufactured into the cabinet can be a source of improved efficiency in the data center,” said Jack Tison CTO, Panduit, Inc. The 380V DC is then converted to 12V DC at the chassis level.

The dual CPU modules use PCI express as the system interconnect for its network, which was developed by One Stop Systems. “All blades in a system communicate with each other at 40Gb/s over PCI Express (PCIe), increasing the overall performance of the system,”said Stephen Cooper, CEO of OSS. “By utilizing the inherent functionality of PCIe over cable, we’ve designed switch blades and large 40-port switches that provide complete non-blocking communication at previously unheard of performance rates.”

In the chassis, each blade houses two motherboards, each with two processors from the future Intel Xeon E5 family. The motherboards were designed by Inforce. The DIMM memory modules were designed as a cooperative effort between SMART Modular and Clustered. “These modules are a derivative of standard DIMMs and include an optimized heatsink design that creates an efficient and cost effective method to transfer heat from the DIMMs to the cold plate,” said Mike Rubino SMART Modular’s VP of Engineering.

First Deployment

The first two racks are scheduled to be installed at Stanford Linear Accelerator (SLAC) within the next few months. For the cooling system, SLAC will use cooling water exiting from existing IT equipment or directly from a cooling tower.

“We are very excited to be chosen as the first deployment site,” said Norm Ringold, Head of IT Operations and Infrastructure, SLAC National Accelerator Laboratory. “The estimated 50 Teraflops per rack will add considerably to our compute capacity,”

Clustered Systems has not announced detailed pricing, but says it will be “highly competitive with other POD and container based systems.” The company says a 3.2 megawatt data center using the new blade chassis could cost as little as $9.2 million, or about $3 million per megawatt of critical load. Industry experts new data center construction costs about $10 million to $15 million per megawatt on average, with hyper-scale projects like those at Google and Yahoo slashing that to $5 million per megawatt.

Hughes says the target market will begin on a slightly smaller scale.

“The ideal customer will have need for HPC but no data center space to house it,” he said. “Typical customers could be academic department heads with money for hardware but not for infrastructure, or high frequency traders wanting to maximize crunch power in a very small allocated space.  Longer term, we also expect to address cloud computing, which has much the same requirements as HPC.”

A closer look at a single blade from the Clustered Systems chassis.

The ability to recycle server heat - using air from the hot aisle to warm nearby office space – is a proven concept being used in a growing number of data centers, usually to warm offices in the data center or adjacent buildings. The Times story acknowledges several of the obvious drawbacks – security of the servers and temperature control in the “server room” – but also examines the economics of the arrangement. The Times writes:

“According to the researchers’ calculations, a conventional data center must invest about $400 a year to run each server, or about $16,000 for a cabinet filled with 40 of them. (This includes the costs of building a bricks-and-mortar center and of cooling the machines.) Having homes host the machines could reduce the need for a company to build new data centers. And the company’s cost to operate the same cabinet in a home would be less than $3,600 a year — and leave a smaller carbon footprint, too. The company’s data center could thus cover the homeowner’s electricity costs for the servers and still come out way ahead financially.”

The paper describes three types of Data Furnaces:

• Low-Cost Seasonal Data Furnaces using older recycled servers that are decommissioned from large production data centers. These could run batch jobs and scientific research processing large datasets. In this model, the servers would provide heating at night and in winter months in areas with seasonal temperature fluctuations.
• Low-Bandwidth Neighborhood Data Furnaces would use the home’s existing broadband connection (such as a cable modem) and serve cached data for applications integrating geographic proximity – such as mapping, location-based advertising and content delivery.
• Eco-Friendly Data Furnaces use newer, energy-efficient servers and a dedicated T1 or FiOS network connection. The servers would operate year-round, with exhaust heat being vented outside in summer. “These DFs would give service providers the ability to expand into urban areas more quickly and easily without urban real estate and infrastructure expenses, as long as the application scale to the number of servers.

The paper’s authors include Christian Belady, the GM for Data Center Advanced Development in Microsoft Global Foundation Services.

Is the Data Furnace a crazy idea, or a stroke of genius. Take our poll below and share any additional opinions or insights in our comments section.