By Wayne Rash  |  Posted 2007-03-28 Print this article Print

The Fraport data center was designed for reliability from the ground up. However, this did not mean that the design was years in the making. According to officials with APC, in West Kingston, R.I., the final decision to go with such a highly redundant data center model was made during a visit to the CeBIT trade show in 2005 in Hannover, Germany, when Wieland had a chance to inspect APCs Infrastruxure products firsthand. The project was finished in less than a year after Fraport officials decided to go with the APC technology. Construction on the first of the data center buildings began last spring, and once the buildings were constructed, it took two to three months to get the data center infrastructure running. The speed in getting the data center equipment in place "is dramatic for an installation of this size," said Aaron Davis, chief marketing officer for APC. He said that one reason the installation could be done so quickly is that the Infrastruxure data center solution integrates everything—from power and cooling to security and services—with the equipment racks, so everything can be simply rolled into place and connected.
Equally important, Davis said, was that Fraport could build the data center before it had chosen the type of servers to go into it.
"Usually what you find is that people buy the servers and then start thinking about the power," Davis said. "In this case, they built and powered up the data center before they even chose the servers. The fact that they could wait to choose the servers meant they could get the latest server technology." Davis said that one reason Fraport was able to get its data center up and running so quickly is because officials there started from scratch. "This was a greenfield operation," he said. "It was a brand new build, so they were able to take a clean-sheet-of-paper approach." There also were some internal time pressures, Davis said. "They also had a significant timeline because they had to move very quickly," he said. "The new CIO was coming on board and was expecting to take on an operational data center." He said that many companies would do well—and probably save a significant amount of money in both capital expenses and operational costs—by simply building a new data center rather than to try upgrading their old one. Wieland said one reason for going with a new data center was so he could have support for the high server density he needs. This dictated a move away from the massive traditional water cooling systems in his 1,250-square-meter facility if he was going to have room for the equipment racks he needed. He said he also needed the latest technology in the power management system because it was getting difficult to buy enough "clean" power on the market at prices that are reasonable. As a result, he can use new technology to clean up "dirty" commercial power. "A data center is a living object," Wieland said, explaining why he chose a modular approach with the APC equipment rather than more traditional power, cooling and rack systems. "Theres always something different." Check out eWEEK.coms for the latest news, views and analysis on servers, switches and networking protocols for the enterprise and small businesses.

Wayne Rash Wayne Rash is a Senior Analyst for eWEEK Labs and runs the magazineÔÇÖs Washington Bureau. Prior to joining eWEEK as a Senior Writer on wireless technology, he was a Senior Contributing Editor and previously a Senior Analyst in the InfoWorld Test Center. He was also a reviewer for Federal Computer Week and Information Security Magazine. Previously, he ran the reviews and events departments at CMP's InternetWeek.

He is a retired naval officer, a former principal at American Management Systems and a long-time columnist for Byte Magazine. He is a regular contributor to Plane & Pilot Magazine and The Washington Post.

Submit a Comment

Loading Comments...
Manage your Newsletters: Login   Register My Newsletters

Rocket Fuel