I had a family member talk about space data centers. I tried to explain how the issue in space is more about getting rid of heat, but they couldn’t comprehend it cause space=cold.
I would think dealing with radiaton would be the most difficult thing about massive amounts of electronics in space. That’s why a chip on a satellite is much more expensive than an equivalent chip that stays on Earth.
Don’t forget power it as well. Watched a video where someone did the math and to generate the power required of a typical data center you’d need a solar array something like 40 times the size of the one on the ISS. It would be an absolute behemoth of a satellite and that’s without taking into account the cooling which would likely double the size again. Of course once you get that big then you have to worry about keeping the thing in orbit because moving that much mass isn’t exactly easy. No matter how you slice it it’s a stupid ass idea that doesn’t work.
Power is pretty much the only part of space data centres that does make sense. You can put them in an orbit to get 24hr solar power and its stronger than on the ground as there’s no atmosphere in the way. Large foldable solar panels are available, and unlike radiators you don’t have to pump liquids through them.
Other than hype (which is by far the major driving force behind companies talking about them) access to that power without regulation is the reason you would want to put them in space.
It still doesn’t make sense because of the power density. The size of the solar array you would need is completely impractical. Even a “large foldable solar panel” isn’t going to cut it. Most satellites are relatively low power and even then the size of the solar arrays they have relative to the volume of the satellite is massive. Something as energy hungry as a data center pretty much demands a “small” nuclear generator to power it and the practicality of getting that into orbit nevermind the issues when it eventually de-orbits makes that a nonstarter.
Also, with all that surface area on panels, I feel like there’s a way of having them double as heat radiators - one side captures energy, the other radiates it out…
The solar panels have to be kept cool too though, moving electrons through the panels is generating heat before it even gets to a processor and without air, cooling them will require radiators of their own.
Unrelated, but anyone deep enough in the comments to read this, you might consider checking out the game Stationeers - a brutally complex base/space station/colony building game that will eat years of your life if you let it, stay away. Huge fun.
they were even talking about ocean datacenter a while ago, people dont comprehend how expensive you have to deal with oceanwater, granted it may dissipate heat faster. but dealing with corrosions, logistics would be expensive too.
I had a family member talk about space data centers. I tried to explain how the issue in space is more about getting rid of heat, but they couldn’t comprehend it cause space=cold.
I would think dealing with radiaton would be the most difficult thing about massive amounts of electronics in space. That’s why a chip on a satellite is much more expensive than an equivalent chip that stays on Earth.
Wait, we have to shield it AND get rid of heat?!
Don’t forget power it as well. Watched a video where someone did the math and to generate the power required of a typical data center you’d need a solar array something like 40 times the size of the one on the ISS. It would be an absolute behemoth of a satellite and that’s without taking into account the cooling which would likely double the size again. Of course once you get that big then you have to worry about keeping the thing in orbit because moving that much mass isn’t exactly easy. No matter how you slice it it’s a stupid ass idea that doesn’t work.
Power is pretty much the only part of space data centres that does make sense. You can put them in an orbit to get 24hr solar power and its stronger than on the ground as there’s no atmosphere in the way. Large foldable solar panels are available, and unlike radiators you don’t have to pump liquids through them.
Other than hype (which is by far the major driving force behind companies talking about them) access to that power without regulation is the reason you would want to put them in space.
It still doesn’t make sense because of the power density. The size of the solar array you would need is completely impractical. Even a “large foldable solar panel” isn’t going to cut it. Most satellites are relatively low power and even then the size of the solar arrays they have relative to the volume of the satellite is massive. Something as energy hungry as a data center pretty much demands a “small” nuclear generator to power it and the practicality of getting that into orbit nevermind the issues when it eventually de-orbits makes that a nonstarter.
Starlink sats are of the order of 20-50kW, an AI focused rack in a data centre is on the order of 100kW, powering the things is definitely feasible.
Unlike:
All of which are somewhere between horrible and impossible for data centres in space.
This makes sense to me.
Also, with all that surface area on panels, I feel like there’s a way of having them double as heat radiators - one side captures energy, the other radiates it out…
The solar panels have to be kept cool too though, moving electrons through the panels is generating heat before it even gets to a processor and without air, cooling them will require radiators of their own.
Oh. Good point.
Unrelated, but anyone deep enough in the comments to read this, you might consider checking out the game Stationeers - a brutally complex base/space station/colony building game that will eat years of your life if you let it, stay away. Huge fun.
It’s suggestions like these that make me glad I don’t have a gaming rig.
Those two things aren’t incompatible if you shield it with a massive heatsink.
Still harder than just doing it on earth, though.
they were even talking about ocean datacenter a while ago, people dont comprehend how expensive you have to deal with oceanwater, granted it may dissipate heat faster. but dealing with corrosions, logistics would be expensive too.