As it turns out, Google actually is using a Bloom Energy box to power an “experimental” data center at its main campus, according to a Reuters story.

Bloom has exploded (or I guess, bloomed) onto the data center industry in the past week, largely due to a segment on “60 Minutes” where Bloom Energy founder unveiled the company’s technology. Bloom produces a new fuel-cell technology that feeds off natural gas and can be used as an alternative to getting power off the electric grid. The machines (in the picture shown above), which Bloom calls “energy servers,” cost up to $800,000 and provide 100 kilowatts of electricity. Some major companies — Google, eBay, Bank of America, WalMart — already have them installed.

The 60 Minutes show said that Google is using a Bloom box to power one of its data centers. Then this week, Rich Miller at Data Center Knowledge reported a different story:

It turns out that’s not quite correct. “These fuel cells aren’t powering any off-site data centers,” said a Google spokesperson. “Instead, Bloom fuel cells are powering a portion of Google’s energy needs at our headquarters right here in Mountain View. This is another on-site renewable energy source that we’re exploring to help power our facilities. We have a 400kW installation on Google’s main campus. Over the first 18 months the project has had 98% availability and delivered 3.8 million kWh of electricity.”

Then today, however, Reuters reported that indeed, Google was using it for a data center:

Google founder Larry Page said he was a big supporter of the technology. The search giant was Bloom’s first customer in July 2008 and uses the fuel cell to power a building on its main campus in Mountain View, California, a facility that includes an experimental data center.

“I would love to see us having a whole data center running on this,” Page said.

Needless to say, Google might not be running a production data center on the Bloom box right now, but I’d be willing to bet that they will be sooner rather than later.

After years of secrecy around how its data centers operate, Google has now drawn the curtain to show how efficient its data center facilities are. But during a panel discussion at The Uptime Institute’s conference in New York today, some questioned whether all data centers should be cut in the same mold.

In particular, the question was whether the data center power usage effectiveness (PUE) of some businesses — financial institutions, for example — should be compared to those of search engines such as Google.

“Should a bank have the same PUE as a search engine?” Ken Brill, Uptime founder and executive director. “The answer is no.”

The reasoning behind it is that bank and financial applications require a higher level of uptime than search queries, and thus need more redundancy, which leads to lower efficiency. But Weihl questioned the logic.

“We actually have some Sarbanes Oxley requirements,” he said. “We’re not just a search engine company. We also run very reliable data centers that I think any data center operator here would be proud to run.”

Weihl later added that the discussion sounded like “people making excuses for why the EPA or DOE should not push hard for a standard because, hey, we’re different.”

“To me,  not to be too combative, but that sounds like an excuse for not doing better.”

Currently the federal government is working on developing an Energy Star rating for data centers. Michael Zatz, the manager of the Energy Star commercial buildings program, sees the potential for different categories of data centers, but would prefer that those categories be defined by what kind of work the data centers perform, and not necessarily by what industry they’re in or how they identify themselves.

Container-based data center

Google confirmed what everyone already knew — that the company has a container-based data center. Robert X. Cringely reported this back in November 2005, so it’s not exactly news. But it’s the first time Google actually confirmed the rumors and showed a sneak peek inside. You can take a look at the video below, taken by Data Center Knowledge:

[kml_flashembed movie="http://www.youtube.com/v/bs3Et540-_s" width="425" height="350" wmode="transparent" /]

Pretty cool stuff. But as James Hamilton, an engineer at Amazon, wrote in a recent blog post, it’s interesting to note that Google built this container-based data center, but then never returned to that design. In fact, Hamilton thinks that the data center design isn’t optimized for shipping containers:

The design chosen essentially built a well executed but otherwise conventional data center shell using standard power distribution systems and standard mechanical systems. No part of the building itself optimized for containers. Even though it was a two level design, rather than just stacking containers, a two floor shell was built. A 220 ton gantry crane further drove up costs but the crane was not fully exploited by packing the containers in tight and stacking them.

For a containerized model to work economically, the attributes of the container need to be exploited rather than merely installing them in a standard data center shell. Rather than building an entire facility with multiple floors, we would need to use a much cheaper shell if any at all. The ideal would be a design where just enough concrete is poured to mount four container mounting bolts so they can be tied down to avoid wind damage. I believe the combination of not building a full shell, the use of free air cooling, and the elimination of the central mechanical system would allow containerized designs to be very cost effective. What we learn from the Google experiment is that a the combination of a conventional data center shell and mechanical systems with containers works well (their efficiency data shows it to be very good) but isn’t notably better than similar design techniques used with non-containerized designs.

Adding to that, there has been talk for years (starting with Cringely) that Google took the containerized data center idea from Internet Archive, the company that runs the Wayback Machine so you can see what web pages looked like a decade ago. The story goes that Brewster Kahle, Internet Archive’s founder, presented the idea of a container-based data center in 2003 and that Larry Page heard the presentation. A couple months later, Google filed a patent application for a modular data center, which the patent office granted them in 2007.

Needless to say, Kahle doesn’t seem like a big Google fan now.When I talked to him last week, he said that “with Google, there’s a giant sucking sound. They tend to take from the commons and don’t tend to give back. The way the world generally works is you give acknowledgement to where things came from. It doesn’t look like they referenced where their ideas came from, but that is like Google.”

When I asked for a response from Google, a spokesperson sent me links to the research pages of Urz Holzle and Luis Andre Barroso, two Google engineers, along with this statement: “Google publishes many papers about our work on data centers and are hoping to have similar sessions to foster openness among the industry.”

Some might call Kahle’s comments sour grapes; others might make a comparison to Thomas Edison patenting the light bulb even though others claimed to have thought up the idea first. Either way, it’s clear that Google doesn’t have a monopoly on the idea, as all the major IT vendors — Sun Microsystems, IBM, HP and others — have their own version of a modular data center, and as far as I can tell, Google hasn’t sued them over it.

Server-based uninterruptible power supply

Let’s be clear. The fact that Google has 12-volt power supplies is nothing new. SearchDataCenter reported on it back in 2007, not long after Holzle and another Google engineer, Bill Weihl, wrote about it in a research report about high-efficiency power supplies for home computers and servers. What is new is that Google is building its own servers to include an uninterruptible power supply (UPS) right on the server, in the form of a 12-volt valve-regulated lead acid (VRLA) battery. Most servers rely on a centralized UPS system that requires a big room filled with big boxes that hold dozens and dozens (or hundreds and hundreds) of batteries. The UPS is there to keep power on to the servers while they transition to a secondary power supply, usually a generator, or primary power from the utility kicks back in.

By building the UPS right on the server board, Google can avoid the centralized UPS system and get much better efficiencies for its backup power supplies (over 99% compared to centralized systems, the best of which are about 96% efficient and the worst of which can dip below 80%). It’s very cool, and very different, and you can expect other leading-edge data centers to start following suit.

River-based data center

Perhaps the most underreported part of the show was Google showing the design for its river-cooled data center in Belgium. Some in the data center industry are saying that the next crisis to hit data centers is water — not necessarily the cost of it, which is still relatively cheap compared to power — but its availability. In Belgium, Google bypassed having to get water from the utility at all, instead sucking up water from a nearby canal, treating it, and using it to cool the data center. Though Hamilton thought the data center could be cost prohibitive because Google had to build its own water treatment plant, it is still a new idea, and one data centers out there can consider.

Overall thoughts

From talking to several people who attended the event, it seemed to be positive overall. One attendee I spoke to did say he was surprised there was any coverage of the event because all attendees had to sign a non-disclosure agreement before entering. Why make everyone sign an NDA and then have the press in to cover it on the record? I don’t know. Sometimes Google works in mysterious ways, I guess.

This same attendee added that he felt Google was most focused on proving that its super-low power usage effectiveness (PUE) numbers were legitimate. Why would they do this? Perhaps they can get some positive press on the matter, which they did. But they can also claim that their super-efficient server-based UPS is a big part of those low PUE numbers. And Google did say during the event that it would be willing to license the idea, which it is also trying to patent. So perhaps Google could profit from the event as well.

Weihl, often referred to as Google’s “green energy czar,” will talk about his company’s various green-energy initiatives at the Uptime Institute’s Symposium, which is scheduled for April 13-16 in New York City.

Last year reporter Bridget Botelho spoke with Weihl about some of Google’s energy efficiency initiatives, including the company’s plan to go carbon neutral by 2008. Well, it isn’t the end of the year yet, but we’ll certainly be able to find out whether that goal was achieved by the time of the keynote. Some of the ways Google has saved energy in the data center include building its own servers with power supplies that are 90% efficient, installing about 9,000 solar panels at its Mountain View, Calif. headquarters, and in a recent patent filing, detailing the possibility of data centers that float in the ocean, powered by crashing waves.

So yes, it will definitely be interesting to see what Weihl has to say in April.

Uptime and power capacity

Miles Kelly from 365 Main, a data center colocation company,  raised an interesting point about uptime and power capacity for a water-based data center.

“I think it’s an innovative idea, though generating 10 to 20 megawatts of power needed for a large modern data center is not a simple undertaking,” he wrote in an email to me. “I’m not a wave-power expert, but I’m certain one will need more than wave power to run servers on the ship (assuming there are more than a handful of servers).”

Uptime is another issue:

“Google may not be planning for essential computing load on the ships, meaning it’s okay if the servers on the ship go offline for one reason or another.  It’s possible they’d view the floating computing capacity as temporary or best effort, but would have other data centers available to pick up the slack if needed.”

Corporate taxes

Much of the stories around the Google patent speculated that building data centers offshore would allow the company to place its jurisdiction outside of the United States, thus ensuring that everyone’s privacy is secured. But there is another side effect to this. If outside of U.S. jurisdiction — and indeed, every country’s jurisdiction — Google may be able to avoid real estate and other corporate taxes that it would otherwise have to pay, even if building alongside the Columbia River in Oregon or in the middle of Iowa.

If they were to avoid corporate taxes in the U.S., that would be pretty amusing. Imagine if Google was able to use the U.S. government’s patent office to protect intellectual property that could then be used to avoid U.S. taxes.

Unsurprisingly, Google doesn’t look at it this way. Its justification for a water-based data center is as follows:

…it can be beneficial to distribute computing power closer to users. As such, data centers may be moved closer to users, with relevant content sent from a central facility out to regional data centers only once, and further transmissions occurring over shorter regional links. As a result, every request from a user need not result in a transmission cross-country and through the internet backbone–network activity may be more evenly balanced and confined to local areas. Also, transient needs for computing power may arise in a particular area. For example, a military presence may be needed in an area, a natural disaster may bring a need for computing or telecommunication presence in an area until the natural infrastructure can be repaired or rebuilt, and certain events may draw thousands of people who may put a load on the local computing infrastructure. Often, such transient events occur near water, such as a river or an ocean. However, it can be expensive to build and locate data centers, and it is not always easy to find access to necessary (and inexpensive) electrical power, high-bandwidth data connections, and cooling water for such data centers.

Kelly added that “any breaks from operating in international waters would be offset by the costs of operating so remotely.  Plus, the incentives offered by aggressive regions in the US
are already quite handsome (north/central Washington for example, another place where Google operates).”

This is a good point, but I wouldn’t overlook the tax benefits to Google for this plan. The company has already shown that it will figure out a way – including by bullying local and state governments – to pay as little taxes as possible, all the while employing far less people than would an aluminum smelter.

Data center pirates

So Google will become the new pirates of the ocean, their data centers spread across the seas, Sergey Brin and Larry Page standing at the helm, complete with their eyepatches, swords, single earrings, and maybe hooks for hands and parrots on their shoulders to top things off.

What’s next, ice-side economizers?

So Google has cultivated the Columbia River for energy. Now it wants to colonize the ocean with data centers. Let’s take a look at this plan.

To the right is a picture of a Pelamis Wave Energy Converter, which is what Google proposes to use to power its water-based data center. Each Pelamis machine is almost 400 feet long — longer than a football field — and as thick as some redwood trees. They produce 750kW of power each. In Google’s patent application, the company presented a scenario of about 40 of these machines spread over a square kilometer and producing 30 megawatts of power. Not exactly non-intrusive.

Perhaps Google will next take its engineering prowess up to Antarctica, where it will figure out a way to harness ice shelves to cool servers. In the next couple years, I wouldn’t be surprised if a new Google patent application popped up for ice-side economizers. But hey, as long as I can continue making super-fast Internet searches, who cares, right?