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

Data centers in space makes no sense

civai.org

Post reply on HN
Print view View original

981–990 of 1001 posts

Re: Data centers in space makes no sense

#981

Post by marcosdumay »

aunty_helen wrote: post #350
marcosdumay wrote: post #325

Earlier quoted context omitted.

> aka fancy air conditioning pumps Yeah, pumps, tubes, and fluids are some of the worst things to add to a satellite. It's probably cheaper to use more radiators. Maybe it's possible to make something economical with Peltier elements. But it's still not even a budget problem yet, it's not plainly not viable. > getting quite good here with nanotechnology Small features and fractal surfaces are useless here.

My dude, heat pipes were invented for satellites and there’s people walking around with piezo pumps in their phones these days. We’re getting close. Peltiers generate a lot of heat to get the job done so even though electricity is pretty much free, probably not a sure bet.

> We’re getting close.

Oh, yes, I can agree with that. With emphasis on "getting".

Re: Data centers in space makes no sense

#982

Post by rockemsockem »

adastra22 wrote: post #516
rockemsockem wrote: post #488

Earlier quoted context omitted.

Kessler syndrome is only a problem if the satellites are in LEO. They don't have to be.

They do have to be if they want to be approved by the FCC. And btw Kessler syndrome applies to any orbital band. You've got the logic backwards. Kessler syndrome is usually only considered a threat for LEO because that's where most of the satellites are. But if you're throwing million(s) of satellites into orbit, it becomes an issue at whatever orbital height you pick.

Sorry I misspoke, you're totally correct. What I meant to say was it's only a problem if they're orbiting around the Earth. I've heard sun orbits mentioned as a possibility for data centers.

Re: Data centers in space makes no sense

#984

Post by sfink »

PinkiesBrain wrote: post #958
sfink wrote: post #137

Earlier quoted context omitted.

> And finally surface area, once again, getting quite good here with nanotechnology. So your hot thing is radiating directly onto the next hot thing over, the one that also needs to cool down?

The inner side of the radiator would be metallized, an anti black body. Together with a bit of vacuum it would thermally be quite far from the PV&GPU. Thermal insulation is easy in space.

You still can't get more surface area than a sphere without crumpling things up. And given the thermal insulation, you can only lose heat via radiation. Radiating heat from a crumpled boundary means radiating it towards another part of the boundary. If there's an "inner side", then it's a sphere (or some other convex shape, all of which have at most the surface area of a sphere).

I don't think you'd want any vacuum at all between the radiator and the heat sources! Thermal insulation is the problem, not the solution. You want the radiator as thermally close to the heat sources as possible, probably via some highly heat conductive metal.

Though the optimal approach might be to ditch the vacuum and use a more terrestrial configuration with circulating air or water or mercury to conduct the heat away. Space is a horrible place to do this in all ways except for... well, space. You do have plenty of room up there. (Well, and power. Lots of solar energy to play with. Which in turn causes its own problems with heat and radiation.)

Re: Data centers in space makes no sense

#985

Post by sfink »

EGreg wrote: post #874
beloch wrote: post #115

I would not assume cooling has been worked out. Space is a vacuum. i.e. The lack-of-a-thing that makes a thermos great at keeping your drink hot. A satellite is, if nothing else, a fantastic thermos. A data center in space would necessarily rely completely on cooling by radiation, unlike a terrestrial data center that can make use of convection and conduction. You can't just pipe heat out into the atmosphere or build…

The ideal would be to park the data centers at the lagrange point behind the Earth in its umbra, so they don't need to dissipate direct solar heat.

Then they also don't get the only advantage of being in space, namely free solar energy.

You'd need to have solar collectors in a sunny spot, beaming energy to the shady spot, or something. (Beaming because they don't get to be in the lagrange point, so cables aren't going to work.) But then you're just inefficiently moving sunlight around (and shifting/narrowing its frequencies, but still).

Re: Data centers in space makes no sense

#987

Post by EGreg »

sfink wrote: post #985
EGreg wrote: post #874

Earlier quoted context omitted.

The ideal would be to park the data centers at the lagrange point behind the Earth in its umbra, so they don't need to dissipate direct solar heat.

Then they also don't get the only advantage of being in space, namely free solar energy. You'd need to have solar collectors in a sunny spot, beaming energy to the shady spot, or something. (Beaming because they don't get to be in the lagrange point, so cables aren't going to work.) But then you're just inefficiently moving sunlight around (and shifting/narrowing its frequencies, but still).

That’s not true, solar energy still reaches the lagrange point, these tiny machines don’t need that much of it

solar energy reaches the Earth-Sun Lagrange point 2 (\(L_{2}\)), even though it is located behind the Earth, because it sits slightly beyond the reach of Earth's full shadow (umbra). Here is a breakdown of how this works: Location of \(L_{2}\): The \(L_{2}\) point is located approximately 1.5 million kilometers away from Earth on the side opposite the Sun.Earth's Umbra Length: The tip of Earth's main, total shadow (the umbra) ends before it reaches the \(L_{2}\) point, usually around 92% of the distance to \(L_{2}\).Solar Exposure: Because \(L_{2}\) is outside the full umbra, a satellite at this location (like the James Webb Space Telescope) is never in total darkness.Halo Orbits: Spacecraft at \(L_{2}\) usually do not sit exactly at the point but in a "halo" orbit, which keeps them in constant, direct sunlight to power their solar panels.Penumbra: While the Earth may block some sunlight, the region is technically in a partial shadow (penumbra) or outside of it entirely, allowing for consistent solar energy harvesting. In summary, \(L_{2}\) is not in permanent darkness, and solar power is fully functional there.*

Re: Data centers in space makes no sense

#988

Post by Andrex »

estimator7292 wrote: post #937
dfabulich wrote: post #879

Earlier quoted context omitted.

In 2024, Starcloud posted their plans to "solve" the cooling problem. https://starcloudinc.github.io/wp.pdf > As conduction and convection to the environment are not available in space, this means the data center will require radiators capable of radiatively dissipating gigawatts of thermal load. To achieve this, Starcloud is developing a lightweight deployable radiator design with a very large area - by far the larg…

Yes, on the face of it, the plan is workable. Heat radiation scales linearly with area and exponentially (IIRC) with temperature. It really is as simple as just adding kilometers of radiatiors. That is, if you ignore the incredible cost of transporting all that mass to orbit and assembly in space. Because there is quite simply no way to fold up kilometer-scale thermal arrays and launch in a single vehicle. There will…

I kind of want to play it out though... if someone did do this (for whatever reasons), what would the real benefits even be? Something terrestrial operations wouldn't be able to catch up to in 5-10 years?

Re: Data centers in space makes no sense

#989

Post by Andrex »

pclmulqdq wrote: post #439
sam wrote: post #414

Earlier quoted context omitted.

This is mistaken. In space a radiator can radiate to cold (2.7K) deep space. A thermos on earth cannot. The temperature difference between the inner and outer walls of the thermos is much lower and it’s the temperature difference which determines the rate of cooling.

"Radiate" is exactly what you have to do, and that is extremely slow. You need a huge area to dissipate the amount of power you are talking about.

Stupid question: Why not transfer the heat to some kind of material and then jettison that out to space? Maybe something that can burn itself out and leave little material behind?

Re: Data centers in space makes no sense

#990

Post by shagie »

Andrex wrote: post #989
pclmulqdq wrote: post #439

Earlier quoted context omitted.

"Radiate" is exactly what you have to do, and that is extremely slow. You need a huge area to dissipate the amount of power you are talking about.

Stupid question: Why not transfer the heat to some kind of material and then jettison that out to space? Maybe something that can burn itself out and leave little material behind?

How many times can you do that?

Consider your own computer... how often does it get hot under a regular load and the fans kick on? That "fans kick on" is transferring the heat to air and jettisoning it into the room... and you're dealing with 100 watts there. Scale that up to kilowatts that are always running.

There is a lot of energy that is being consumed for computation and being converted into heat.

The other part if that is... its a lot easier to do that transfer heat into some other material and jettison it on earth, without having to ship the rack into space and also deal with the additional mechanics of getting rid of hot things. You've got advantages of things like "cold things sink in gravity" and "you can push heat around and sink it into other things (like phase change of water)" and "you don't need to be sitting on top of a power plant in order to use the power."

Post reply on HN