Microsoft declares its underwater data center test was a success

Underwater pods can reduce latency by moving cloud services closer to customers.

Read the whole story

 

[Bongle]

This, and all the other exotic data center locations like Iceland or the Arctic feel very sci-fi:
Problem: "We have so many tonnes of computronium packed so densely that both land availability and the computers melting is a problem"
Solution: "Throw them in the Ocean / below a glacier / at L2 in Earth's shadow"

Seems like a pretty reasonable project though. If MS is going to need the compute power anyway and this is actually cheaper in terms of energy/space/reliability, why not?

Plus you could potentially design the outside of the pods to act as an artificial reef for the couple years they're on the bottom.

Another potential upside is if the big tech companies suddenly start coveting vast swaths of oceans, they may inadvertantly become large nature reserves because they won't want their pods snagged by nets/anchors/etc.

 

[Bongle]

- Nuclear Fission (the atoms would have decayed anyway)

This isn't quite right - The enrichment and arrangement of the fuel rods in a reactor massively accelerate the natural decay rate, since each emitted neutron gets used to usefully split another atom, rather than dissipating into nature like it did when the Uranium was in the ground. Moving forward the fissions that would've happened anyway into the present will generate a slight increase in heat in the human era.

An analogy is to think of a nuke exploding: those atoms weren't going to decay anyway when they did, they were encouraged to decay by the structure and mechanisms of the bomb.

- Solar (The light would have heated the ground instead)

Although hitting a vast field of mostly-black solar panels is going to retain more heat (on top of the 20-40% electrical energy we extract and later turn into heat through some other process) than hitting a big high-albedo chunk of desert.

 

[Bongle]

- Nuclear Fission (the atoms would have decayed anyway)

This isn't quite right - The enrichment and arrangement of the fuel rods in a reactor massively accelerate the natural decay rate, since each emitted neutron gets used to usefully split another atom, rather than dissipating into nature like it did when the Uranium was in the ground.

An analogy is to think of a nuke: those atoms weren't going to decay anyway when they did, they were encouraged to decay by the structure and mechanisms of the bomb.

That speeds up the timeframe but eventually it would have decayed away regardless. Still heat is a non issue even for fossil fuels. We have global warming because the ghg are making our greenhouse effect more efficient not because we are adding heat to the environment.

I'm not in any way saying that it's going to contribute to the overheating of the planet, but a nuclear reactor does increase the rate of fissions for a given hunk of U-235 over the natural background. Yes, that hunk of U-235 was going to have 6-7 half-lives in the ground and thus be mostly consumed before the sun consumes the earth, but burning even a couple percent of it instead in a couple-year stint in a reactor is a huge difference in rate, and thus human-relevant heat. Moving forward the fissions what would've happened in the far-distant future into the present makes a small, miniscule, barely calculable difference to our heat levels now. Worrying about it is like the people worrying about these data center boiling the oceans, but it is "new" heat.

And again: human waste heat isn't currently a problem on the scale of CO2-driven climate change. But saying "a nuclear reactor doesn't change how much heat the U-235 is going to emit" is being right on a technicality, because you're operating on a 4-5 billion-year timespan. The U-235 certainly wasn't going to emit the heat the reactor produced in just a few years.

Though my solar panel bit was partially in error: as long as your panel offsets electricity that would've come from a coal plant, it appears even a worst-case albedo impact can be paid back in 3 years: https://blogs.scientificamerican.com/so ... do-effect/. A new solar installation though, making new electricity and covering high-albedo land, could be problematic. Covering the Sahara in panels to power new industry might be a wash.