Live data from Hacker News

Want an energy efficient datacenter? Build it underwater

spectrum.ieee.org

121–130 of 172 posts

Re: Want an energy efficient datacenter? Build it underwater

#121

I really can't see the benefit of submerging these -- the complexity involved with keeping out several hundred PSI of sea water just doesn't seem to make sense to me. For the cooling aspect, they're already using pumped water and heat exchangers. What is the benefit of submersion vs just pumping sea water from a pipe to a land, or barge-based datacenter and using that to cool?

Why does it have to be several hundred PSI? They don't have to put it at the bottom of the ocean. A shallow lake or river would work just as well.

The article mentioned that they would be between 50 and 200 meters below the surface. I assume to access the cooler waters at those depths.

50msw = 74psi

200msw = 293psi

Re: Want an energy efficient datacenter? Build it underwater

#123

I really can't see the benefit of submerging these -- the complexity involved with keeping out several hundred PSI of sea water just doesn't seem to make sense to me. For the cooling aspect, they're already using pumped water and heat exchangers. What is the benefit of submersion vs just pumping sea water from a pipe to a land, or barge-based datacenter and using that to cool?

I don't think it would be that complex, since the pods can be permanently sealed and don't need to exchange matter with the environment. I would assume that a lot of the complexity in waterproofing marine vessels comes from the need for openable doors.

No doubt doors are one of the biggest challenges.

Many of the challenges could be reduced or mitigated if the pods could be at least partially pressurized to reduce the pressure differential between the inside and out -- but that introduces another complexity -- can the server hardware handle it.

There are quite a few engineering challenges, none of them unsolvable but also none of them seem necessary when it seems the same benefits can be obtained for less effort by keeping the pods above water.

Re: Want an energy efficient datacenter? Build it underwater

#124
post #70

Earlier quoted context omitted.

> b) Isn't marine biology highly sensitive to heat pollution? Impact on the marine environment is briefly mentioned in the last couple of paragraphs of the article, although they're a little dismissive and don't provide any evidence supporting their claim of negligible impact.

Nuclear power plants usually dump their tertiary cooling water into the ocean. That's not a great situation for the local sea life (within a few hundred meters, IIRC), but doesn't have much significance beyond that. That is several orders of magnitudes more heat output than could conceivably come off a data centre. So their dismissiveness is likely warranted. A bit more concerning is the notion of relocating these da…

>Nuclear power plants usually dump their tertiary cooling water into the ocean

The heated water from a power plant can actually provide a refuge for manatees and other wildlife that prefer warm water during cold winter. They're actually known as good fishing spots in Florida!

Re: Want an energy efficient datacenter? Build it underwater

#125
post #117
post #115

Doesn't work. DigitalOcean has been working on this for some time and their Atlantis datacenter still isn't open. https://www.digitalocean.com/company/blog/announcing-atlanti...

For those who might miss the date on that blog post, it's an April Fool's joke.

thank you for providing a safe haven free of aprils fools trickery for all of us sensitive people

Re: Want an energy efficient datacenter? Build it underwater

#126
post #70

Earlier quoted context omitted.

> b) Isn't marine biology highly sensitive to heat pollution? Impact on the marine environment is briefly mentioned in the last couple of paragraphs of the article, although they're a little dismissive and don't provide any evidence supporting their claim of negligible impact.

Nuclear power plants usually dump their tertiary cooling water into the ocean. That's not a great situation for the local sea life (within a few hundred meters, IIRC), but doesn't have much significance beyond that. That is several orders of magnitudes more heat output than could conceivably come off a data centre. So their dismissiveness is likely warranted. A bit more concerning is the notion of relocating these da…

Nuclear power plants usually dump their tertiary cooling water into the ocean.

Nuclear plants also use cooling towers to lower the temperature before it dumped back into a lake/river/ocean. You can do a Google search, but those towers are hollow on the inside. Water runs down the inside walls and convection currents move up.

Re: Want an energy efficient datacenter? Build it underwater

#127

Edit: Great points! Space would be a terrible location for data center hosting, not only due to latency and heat radiation issues, but also due to the difficulty in mitigating solar radiation. What about putting the data center in some kind of low Earth orbit? Something within the magnetic field, but far enough out to radiate heat? Would the latency still be a factor if your web server and CDN were hosted "in a cloud…

Someone correct me if I'm wrong, but I believe that radiating heat is actually really hard in space. It seems counter intuitive, because space is so cold, but it's mostly a vacuum. To transfer heat, you need a medium for the heat to transfer through. I believe some heat can be lost due to radiation, and so they have these big metal fins as heat sinks to radiate as much heat as possible, and reflective material on the…

The Atomic Rockets site has some great information on how spacecraft heat radiators actually work.

http://www.projectrho.com/public_html/rocket/basicdesign.php...

Re: Want an energy efficient datacenter? Build it underwater

#129
post #117
post #115

Doesn't work. DigitalOcean has been working on this for some time and their Atlantis datacenter still isn't open. https://www.digitalocean.com/company/blog/announcing-atlanti...

For those who might miss the date on that blog post, it's an April Fool's joke.

You say that, but it sounds like a win/win from where I'm sitting:

>Our investigation was a great success: not only were we able to reduce our electricity costs by 35%, but we discovered our high-density SSD storage was even more dense at 87atm!

Time to replicate / H2O-as-a-service it.

Post reply on HN