This is a most excellent place for technology news and articles.
One thing Eric Berger does not go into is bandwidth. There is a hell of a lot more bandwidth available in a single pair of optical fibers on the ground compared to SpaceX' fastest ground to air links.
They claim 1Tb/s for V3 starlink satelites. If that's true, a fiber pair provides at least 20 times that with utterly normal off the shelf DWDM components. And that's a single pair of fibers. Optical cables are often lain with 144 fibers, or 288 fibers.
It's not a good idea at all. The problems it creates are greater in both number and difficulty than the problems it solves.
answer: hard.
Space isn't cold the way cold environments are here on earth. The cold we experience on Earth is because we are surrounded by cold gases. Cold wind and cold air will wick heat away from objects. Because space lacks any atmosphere, all thermal transfer in space is radiative. In comparison to convective thermal transfer via air / atmosphere, radiative thermal transfer is abysmally slow, requiring expansive delicate heat sinks which must be carefully aimed and coated to facilitate thermal egress while impeding solar thermal ingress. If you've ever seen a picture of the space station, much of what you may think are solar panels are in fact heat sinks. You can't just stick a server container in orbit and call the job done.
Launch costs (yeah, Musk promised 100 tons to LEO Real Cheap, Real Soon, you better believe it) and energy requirements for launch kill this. If you could make DCs ISRU in space, well, good luck with that.
Boy, this superbubble is astronomic. Be sure to watch it when it blows.
Musk promised
Hyperloops Mars bases Moon bases Interplanetary travel 1000x cheaper tunnels for trains Travel by ballistic missiles to the other side of the world Rocket powered cars Electric cargo trucks The roadster AI that would be truthful AI powered robots
Just a small list of all the promises from Elmo but let this make clear that if the word comes from Elmo's mouth, then its a lie
The guy literary can only lie
Google and Microsoft already tried underwater data centers to better handle heat dissipation. It wasn't worth it. Hardware can fail and you need somebody to go in and swap boards and faulty cables. Every complex system has multiple points of failure. The wrong board and the whole container stops working. It was so much pain trying to maintain it under water they all gave up after the Proof of Concept stage.
How are they going to deal with it cost effectively up in orbit? Little nanosat modules? Humanoid robots that barely work today?
Be a lot cheaper (and faster) sending a tech in a little cargo van and a toolbox out to the suburbs of Memphis, Phoenix, or Bakersfield.
I see two issues here: get all that stuff into a stable orbit, which would be a way bigger job than building the ISS, which is one of the most expensive projects ever undertaken. Second, it would have to have massive radiators to get rid of the generated heat.
So you need SpaceX to increase its launch capacity to somewhere between 20 to 80 times its current rate, completely reimagine the economics of space-based radiators and solar panels, accept that all that shiny new power and cooling CapEx is just as disposable as the GPUs, and you have to adjust the expected use cases and SLAs to allow for nothing being repairable and latency making them unsuitable for many AI tasks.
Yes. "Possible." I mean, I guess, but we've got some powerful Hyperloop energy here. I cannot imagine it ever being more economical than bullying and bribing rural areas with access to a power grid.
And the already predicted heavy damage to the ozone layer from aluminium oxide from re-entering sattelites would be increased a thousand fold so somewhere on that list is learning to live without oxygen or sunlight.
The thermal problems are the craziest part IMO. Why do you think they use so much water on earth. In low Earth orbit your entire data center would be mostly radiators, which are heavy and complex with enormous fluid flow rates.
Wouldn't it still be cheaper to build megastructures on earth in remote and uninhabited places? Like I get you have to build your own power and run your own fiber if you say build a data center the size of Rhode Island in the Yukon or something, but that has to be more cost effective than orbital.
Taking it to orbit creates far more problems than it solves.
I think that a lot of companies are seeing a regulatory capture opportunity mixed with a very limited ressource (orbits) meaning they can lock out the competition by being the first one to do it.
It is easier to do stuff on the ground. Always. However, not having to deal with neighbors, cities, activists and representatives of thereof who complain about the impact of your data centers on people’s livelihoods is an opportunity. The FCC is in the pocket of SpaceX and other space companies. They don’t really care about impacts on astronomy, ozone layer, the atmosphere and the whole of the biosphere that needs dark nights.
Free sun energy is a good bonus.
But if you can be the first to deploy such a constellation and occupy all those sun synchronous orbits on the day/night terminator in low earth orbit, no one else can, giving you a monopoly on activities in those orbits.
This is the hype. That’s the promise. That’s what they want to sell VCs to get their money. The article highlights with numbers how unreasonable this endeavor is.
Yes, or course that would be cheaper and more practical. It would not, however, be as good at generating moronic hype that captivates foolish investors.
Really fucking hard. Because they demand high power, and any repairs are insanely expensive.
Fucking idiots.
There will be no repairs in space. Everything they launch is set and done and comes crashing back in the atmosphere 5 years later. They fully expect radiation and debris to render the space data center satellites unusable after 5 to 7 years (in the article). We all know that after 5 years those chips will be obsolete anyways.
This is a huge issue, the amount of mass being sent into orbit that is planned to just burn up in the atmosphere 5 years later.
There's a difference between telecom satellites and other space stuff. Hubble launched in 1990 and it's not only still in space, it's still working.
Oh yeah ofc. The Hubble upgrades and repairs are a good example to show how good planning, good technology and will can ensure long standing missions delivering incredible science.
The planning for these mega constellation is different for sure and the goal is money, not science, which is sad. That’s why they will burn in the atmosphere no matter what.
Depends on what you arbitairally define as data center.
Try doing it while disqualifying the GPS constellation.
"we?"
we are not billionaires. wtf are they doing?
We live in the same word as billionaires. They exist, they don’t exist in a vacuum though maybe, briefly, they should.
I always wondered how we planned for dissipating heat in space to be comparable to dissipating heat on earth. Feels like whatever they're using to handle that heat is going to have to be huge and heavy.
Has to be great for avoiding any legal obligations on how you might handle the data though. Can do whatever you want as long as it stays in space.
You know, I just had a great idea how to dissipate that heat in space. we can use tungsten rods and heat them up, and when they’re too hot and don’t cool down anymore, we just drop them down to earth and should they happen to hit something in China or Russia that’s just a bonus
/S obviously
The article goes somewhat in depth about it. Basically, heat dissipation in space is a solved physics problem. It is now in the engineering domain to try to make it more lightweight, efficient, scalable and ultimately cheap. Ars Technica does reference a great video by Scott Manley where he just does the math to figure out how large the heat sink panels need to be. His back of the envelope math leads him to believe that a starlink sized solar panel or something in that order of magnitude will be enough.
This is a false front for laundering VC money. It’s not logistically feasible, and like AI, they will have made off with billions before they ever attempt to launch anything.
Typical “numba go up” scheme.
Though I am confident they are going to try really hard to make it work. They just want to time it so that VC doesn't hold the short end of the stick when the music stops (lol I love mixing analogies like that). I am worried of the impact of launching so many vehicles into space. They will launch a lot of vehicles, there is no denying that, even if it doesn't get to 1M satellite constellation. All the shit they send to LEO will have to fall back down eventually. It will burn up in the atmosphere. That's a lot of extra stuff in the atmosphere. That's also a lot of stuff up there that will interfere with astronomy. A lot of stuff that can lead to Kessler syndrome.
All those rare earth minerals and silicon will just burn up. What a waste. There needs to be legislation that if you put satellite in orbit you are responsible for recovering them at End of Life.
Burning up in the atmosphere is pollution that we don’t even understand how it affects the upper atmosphere.
What are we doing?
We are allowing Psychopaths to get to the top in the perpetual Capitalist economic war - everybody against everybody else, no rules. Rich Psychopaths are now running Western societies as a private Fascist club, and they use their power to manage information/policies, so they are; not in any danger from 'socialism/communism' etc, able to create consent to attack their 'Evil' enemies (that just don't want Epstein psychos to control their nations future or resources), keep alternatives down, and just be able to keep hoarding power/wealth from the backs of ordinary people all around the world..
That is what Psychopaths do, they create chaos and exploit the situation for their own benefit - most often harming everyone else. Capitalism is inherently a psychopath ideology where exploitation and absolute selfishness is both the goal and highest morality. No wonder the ideology is promoted by the most powerful psychopaths that benefit from that belief. We could easily add the 2 'missing' prongs and just call 'Capitalism' a full Dark Triad belief-system (Psychopathy, Machiavellianism, and Narcissism). https://en.wikipedia.org/wiki/Dark_triad
The rich removed - The Dark Triad Epstein Class - won bc they control the narrative and can manufacture consent for what they want.
So to YOU, that still believe in the Capitalist 'free market' dystopia/fantasy: Stop believing in/supporting their Dark Triad Capitalist belief-system and things will calm down by it self..
Its easy: IF the rich removed recommend it, you DON'T !
rich removed recommend
How sad that 'C u n t' automatically gets 'removed' - suicide simplistic censorship - lame..
You can't say cunt on your instance?
Everyone else can.
That's a .ml problem, most instances don't have anything blocking cunt or any other words.
I work in this industry and its hard enough to get a GEO/LEO bird in the air let alone a data center...
Not to mention the payload reqs on this. All the radiation shielding and heat management is gonna need a new Sea Dragon-sized rocket.
Great point, also think about the cost in fuel to keep it in LEO orbit. Then what happens when they lose control of it? Space Lab Part 2
Hard enough that it's not worth it. Unless you're on the board of SpaceX about to make an IPO. Above the cloud: Building data centres in space
Just here to comment that I only pasted the title of the article as the title of the post. I find the content of the article interesting. I'm not actually asking that question, though answer it if you please.
Solar panels and infrared heat disposal into space can both work just fine right here on the ground.
Ooh, I've seen this one. The secret is just to build them out of paperclips.
His AI is already loosing money, and this looks to be massively expensive. Might a tired soul hope that this will put a serious dent in his hoardings?
Don't worry, it'll only put a dent in everyone's index/retirement/etc accounts, everyone other than him and his friends will be holding the bag.
I'd imagine not very hard, but then would it even be worth it? I'm imagining something like in Cyberpunk: an orbital digital prison where one company keeps its enemies' minds on chips that can be swapped to an entirely different person and overwrite their original personality.
