In a blog post, Musk said the acquisition was warranted because global electricity demand for AI cannot be met with “terrestrial solutions,” and Silicon Valley will soon need to build data centers in space to power its AI ambitions.
This dumb fuck. Unfortunately, his boosters will be all-in on this messaging. Whatever.
A million satellites he says. That’s 100 satellites per starship launch. 5 times per day, every day, for five years. By the time you’re done, the first ones are burned out and you have to do it all again. And that’s assuming one GPU per satellite because solar panels even in space can’t pull enough power to feed multiple of those hungry things.
Energy is the least of their concerns, getting rid of the heat is a much bigger problem.
Radiators in space are a proven tech. In practice that just means more expensive to build and launch.
Yeah it is a proven tech but requires quite a lot of space/weight and usually when satellites get the most energy from solar panels they also “generate” the most heat.
But space is cold
Space feels cold if you have some fluid to evaporate, like blood or something. But servers will very quickly run out of whatever fluids they have if they tried this. (And so would you in their place.)
The only option to sustainably lose heat in space is radiation, which works, but is slow and limited in capacity, so these server satellites would need massive radiators. It’s not impossible to do. ISS also has massive radiators.
So servers in space is possible. How big you can make an orbital server park, I don’t know. I can imagine that with enough radiators, they start catching each other’s heat, so there might be a limit to have many radiators you can put closely together, but I have no idea what that limit might be.
It’s a vacuum. Which means that there aren’t atoms to get hot or cold. Which means there is no medium with which to exchange heat to cool something down, unless you are willing to bring a bunch of your own air to blow over the servers and then vent into space. Which means bringing an awful lot of air with you.
A server sitting in the vacuum of space would quickly over heat for lack of ventilation (if it didn’t get destroyed because it wasn’t structurally engineered to run in a vacuum).
I wasn’t being serious by the way, but thanks for the detailed explanation of why, always appreciated to know the actual ins and outs no matter the topic.
Wait, I just did some research and it turns out I’m partially wrong about this.
While I am correct that you can’t cool in the way we do on earth by bringing cool air to carry away the heat, there is another way to cool things as used by space stations and satellites.
That is you can take the heat and radiate it into space as Infrared radiation. IR radiation is able to travel through space as it is made of photons.
Indeed now that I think about it, that’s why how our FLIR detectors work on earth too. They can measure the infrared radiation that is one of the 2 ways things vent heat even on earth (the second being by exchanging heat with another fluid such as air or water or something more exotic). It turns out that about ~1/3 of radiation from a radiator is actually infrared light while the other ~2/3 is fluid heat exchange, usually with air.
So I am wrong. I’m not sure how effective this would be for the amount of heat generated by servers, but it’s not actually fully disqualified as I thought it would be.
This is how the International Space Station deals with waste heat: https://www.nasa.gov/wp-content/uploads/2021/02/473486main_iss_atcs_overview.pdf
It’s very slow compared with convective cooling, definitely not practical for running any high-powered computer hardware, slow enough that it can be considered disqualified.
Some back of the envelope: An ideal black-body at 100 C will radiate something like a kW pr m2, give or take. So one h100 at 700W(?) would probably need a reflector of around one m2. Very rough but it’s probably within an order of magnitude so it’s not impossible, but just adds to the engineering and logistics challenges.