Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Economics of Orbital vs. Terrestrial Data Centers

andrewmccalip.com

Post reply on HN
Print view View original

141–150 of 282 posts

Re: Economics of Orbital vs. Terrestrial Data Centers

#141

Post by Turskarama »

jmyeet wrote: post #129
jofer wrote: post #39

What really worries me is that I keep hearing "cooling is cheap and easy in space!" in a lot of these conversations, and it couldn't be farther from the truth. Cooling is _really_ hard and can't use efficient (i.e. advection-based air or water cooling) approaches and are limited to dramatically less efficient radiative cooling. It doesn't matter that space is cold because cooling is damned hard in a vacuum. The artic…

I've done some reading on how they cool JWST. It's fascinating and was a massive engineering challenge. Some of thos einstruments need to be cooled to near absolute zero, so much so that it uses liquid helium as a coolant in parts. Now JWST is at near L2 but it is still in sunlight. It's solar-powered. There are a series of radiating layer to keep heat away from sensitive instruments. Then there's the solar panels th…

The computer chips used for AI generate significantly more heat than the chips on the JWST. The JWST in total weighs 6.5 tons and uses a mere 2kw of power, which is the same as 3 H100 GPUs under load, each of which will weight what, 1kg?

So in terms of power density you're looking at about 3 orders of magnitude difference. Heating and cooling is going to be a significant part of the total weight.

Re: Economics of Orbital vs. Terrestrial Data Centers

#142

Post by rockemsockem »

ted_dunning wrote: post #61
modeless wrote: post #58

Earlier quoted context omitted.

OTOH SpaceX has a pretty good history of undercutting the industry on cost. If Starship full reusability works I would be very surprised if it only lowered launch costs by a factor of three. Of course it's not guaranteed to work, but clearly SpaceX's orbital datacenter plans are predicated on Starship working.

SpaceX has never met any milestone that Elon has ever set.

Never on time, but always eventually.

Re: Economics of Orbital vs. Terrestrial Data Centers

#143

Post by nick486 »

brotchie wrote: post #57

Did a similar back-of-the-napkin and got 5x $ / MW of orbital vs. terrestrial. This article's analysis is ~3.4x. I do wonder, at what factor of orbital to terrestrial cost factor it becomes worthwhile. The greater the terrestrial lead time, red tape, permitting, regulations on Earth, the higher the orbital-to-terrestrial factor that's acceptable. A lights-out automated production line pumping out GPU satellites into…

people use aws despite it being 2x-10x the cost of self hosting. cost isnt everything.

Re: Economics of Orbital vs. Terrestrial Data Centers

#144

Post by zkmon »

Economics for who? The builder of the data center and plethora of all contractors and sub-contractors would see great economics though. Even the sponsor/owner of the data center might see economics work out, if you consider the reputational gain (why did we land on Moon? what's the economics?), experience gained and considering the burn of someone else's money. The money of mega companies that go into this kind of "monuments" is not exactly theirs.

Re: Economics of Orbital vs. Terrestrial Data Centers

#145

Post by exmadscientist »

matheusmoreira wrote: post #106
DonHopkins wrote: post #99

Earlier quoted context omitted.

OTOH they have a huge batshit crazy fanbase of boot lickers who are so gullible they'll believe and parrot anything Elon says.

SpaceX created reusable rockets that can fly back to the launch platforms and land gracefully. Hard to blame people for becoming fans. Before them stuff like this only existed in kerbal and sci-fi.

Becoming a fan of someone or something is great!

Accepting everything they then do, forever, even when it's obviously nonsense, is what gets you called a "huge batshit crazy fanbase of boot lickers".

This "idea" is great party conversation. It's probably doing a great job of shoving around the Overton window, too (perhaps the real goal here?). It's, uh, not realistic, and anyone who is seriously "all in" on it (you're allowed to consider it and to dream, that's not the same as being all in) is not worth taking seriously no matter how much of the oxygen in the room they're using up.

Re: Economics of Orbital vs. Terrestrial Data Centers

#146

Post by rsynnott »

zozbot234 wrote: post #19

Will these space-based data centers run on rad-hard silicon (which is dog slow compared to anything on Earth) or just silently accept wrong results, hardware lockups and permanent failure due to the harsh space environment? Will they cool that hardware with special über-expensive high-temperature Peltiers that heat the radiators up to visible incandescence so that the heat can be shed with any efficiency? There's zil…

> or just silently accept wrong results

Silently wrong results are very fashionable these days, you know. Deterministic results are very 2010s.

Re: Economics of Orbital vs. Terrestrial Data Centers

#147

Post by recursivecaveat »

zozbot234 wrote: post #19

Will these space-based data centers run on rad-hard silicon (which is dog slow compared to anything on Earth) or just silently accept wrong results, hardware lockups and permanent failure due to the harsh space environment? Will they cool that hardware with special über-expensive high-temperature Peltiers that heat the radiators up to visible incandescence so that the heat can be shed with any efficiency? There's zil…

Say what you will about the data centers in space idea (I think it's transparently stupid), but ML is generally resistant to random undirected noise. It's almost a requirement by definition that a machine which takes pictures and accurately outputs the probability that they are pelicans has to be pretty robust to nigh-infinite amounts of minor variation. That's part of the reason all the super low precision stuff works. It's only in the control logic or maybe the absolute precise chokepoints of computation where flips are dangerous, so most of them are harmless.

Re: Economics of Orbital vs. Terrestrial Data Centers

#148

Post by simianwords »

zkmon wrote: post #144

Economics for who? The builder of the data center and plethora of all contractors and sub-contractors would see great economics though. Even the sponsor/owner of the data center might see economics work out, if you consider the reputational gain (why did we land on Moon? what's the economics?), experience gained and considering the burn of someone else's money. The money of mega companies that go into this kind of "m…

Who's money is it?

Re: Economics of Orbital vs. Terrestrial Data Centers

#149

Post by viraptor »

rekenaut wrote: post #125
wmf wrote: post #81

Earlier quoted context omitted.

Yeah, you need 50m^2 of solar panels and 50m^2 of radiators. I don't see why one is that much more difficult than the other.

Especially if with the radiators you can just roll out as rolls of aluminum foil, which is very light and very cheap.

Only on a short distance. To effectively radiate a significant amount of heat, you need to actually deliver the heat to the distant parts of the radiator first. That normally requires active pumping which needs extra energy. So now you need to unfold sonar panels + aluminium + pipes (+ maybe extra pumps)

Re: Economics of Orbital vs. Terrestrial Data Centers

#150

Post by noosphr »

jofer wrote: post #39

What really worries me is that I keep hearing "cooling is cheap and easy in space!" in a lot of these conversations, and it couldn't be farther from the truth. Cooling is _really_ hard and can't use efficient (i.e. advection-based air or water cooling) approaches and are limited to dramatically less efficient radiative cooling. It doesn't matter that space is cold because cooling is damned hard in a vacuum. The artic…

Space hardware needs to be fundamentally different from surface hardware. I don't mean it in the usual radiation hardenrining etc, but in using computing substrates that run over 1000c and never shut down. T^4 cooling means that you have a hell of a time keeping things cool, but keeping hot things from melting completely is much easier.
Post reply on HN