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

891–900 of 1001 posts

Re: Data centers in space makes no sense

#891

Post by matt-p »

elil17 wrote: post #855
matt-p wrote: post #362

Earlier quoted context omitted.

(DTC) Datacentres take electricity and turn it into low grade heat e.g 60c water. Put them anywhere where you've either got excess (cheap) energy or where you can use the heat. Either is fine, both is great, but neither is both bad and current standard practice. It's perfectly possible to put small data centres in city centres and pipe the heat around town, they take up very very little space and if you're consuming…

Well a few considerations: - You have to size your cooling towers for your hottest hour. Doing this saves you no capital costs. - You barely have to run the fans on your cooling towers in the winter because the air is so cold. So often this also won’t save you much operating costs. - Already there is an essentially unlimited amount of so called “waste heat” from power plants and factories. Building district heating s…

I don't think I ever said it reduced capital cost. I agree (though you might be willing to take more risk on reducing redundancy e.g instead of 2+1 cooling towers you may be more willing to just buy 2).

You cannot put a power station in the middle of a city centre, you can put a datacentre there. The main reason this isn't done more is that it's expensive to build heat network between the 'far out of town industrial area' where they put the heat sources and the city centre where the heat consumers are.

I don't know why a municipality is involved, but regardless you can simply install a backup heat source and/or add a mix of heat suppliers to the network. Backup gas boiler or similar is not that problematic or expensive to add particularly because you don't need to add redundancy as it's just there for a backup scenario.

Re: Data centers in space makes no sense

#892

Post by zelias »

dwroberts wrote: post #109
xyzsparetimexyz wrote: post #89

You guys clearly didn't read the full blog post where Musk mentions lunar mining. They're going to put an ASML machine on the moon and turns regolith into chips and solar panels automatically. Literally free compute

This is your brain on Factorio

I’m playing Space Exploration right now and all I can think is “damn what is he gonna do without productivity modules”

Re: Data centers in space makes no sense

#893

Post by midtake »

devin wrote: post #887
indoordin0saur wrote: post #884

Earlier quoted context omitted.

I've used Starlink and it's fantastic in rural areas. Why dig thousands of miles of holes for physical wires when the problem is already solved?

Think. You don't even need to dig. We have myriad wireless internet solutions. We did not need to send satellites into space to fix this problem in a far more cost effective way.

Terrestrial wireless internet solutions are stupid. With a satellite you can be anywhere with line of sight to the southern sky and receive signal. With some shitty tower you're still constrained to your location just as you would be with wired, except that instead of a fast, low latency cable you have a noisy, outage prone wireless tower.

Re: Data centers in space makes no sense

#894

Post by slashdev »

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…

As an engineer of the software variety, logically heat dissipation would seem like a difficult problem.

But SpaceX has lots of real engineers who are very smart. I’m certain they ran the math on it. Which is more than you or I have done.

If they say it can be done, I’m inclined to believe them.

Re: Data centers in space makes no sense

#895

Post by _whiteCaps_ »

Terr_ wrote: post #31

I'm convinced that >30% of this comes from ideas leaking out of fiction such as like Neuromancer , and percolating through the minds of wealthy people attracted to some of the concepts. Namely, the dream of being a hyper-wealthy dynasty, above any earthly government, controlling an extraterritorial Las Vegas Fiefdom In Space. (Which in the book, also hosted a powerful AI.) Then they work backwards, trying to figure o…

“And, for an instant, she stared directly into those soft blue eyes and knew, with an instinctive mammalian certainty, that the exceedingly rich were no longer even remotely human.” ― William Gibson, Count Zero

Re: Data centers in space makes no sense

#896

Post by foobiekr »

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…

Musk lies with ease and routinely. This and Optimus are both just more examples of that.

Re: Data centers in space makes no sense

#897

Post by foobiekr »

tgtweak wrote: post #767

The crux of it is that radiative cooling in space is dependent on exposed surface, not total surface area like a radiator or heatsink on earth - this means if you just put an existing finned heatsink in space it would radiate most of it's heat back to itself - the only net cooling you'd have is the amount that can radiate outwards without hitting itself. For a benchmark - the IIS uses about 4500sqft (420 sqm) of radi…

The lifetime of a GPU in practice is around 3 years. There is no way this plan is going to work. Musk knows that, he's just counting on stupid people to buy into the SpaceX IPO on hype.

Re: Data centers in space makes no sense

#898

Post by foobiekr »

gwbas1c wrote: post #877
tgtweak wrote: post #767

The crux of it is that radiative cooling in space is dependent on exposed surface, not total surface area like a radiator or heatsink on earth - this means if you just put an existing finned heatsink in space it would radiate most of it's heat back to itself - the only net cooling you'd have is the amount that can radiate outwards without hitting itself. For a benchmark - the IIS uses about 4500sqft (420 sqm) of radi…

Makes me wonder: Back in the early 1990s I read some children's futurist book that suggested that we might send solar panels to space that would then beam energy via microwaves to the surface. The book was more fantasy than science, so I took it with a huge grain of salt and appreciated it for its entertainment value. But do you think schemes that try to direct solar energy to the surface are more practical then runn…

Space based power arrays with microwave transmission to massive ground fields has been discussed for nearly sixty years. It doesn't make economic sense, at all.

https://caseyhandmer.wordpress.com/2019/08/20/space-based-so...

I would love it to be a thing, but it is not a thing.

Re: Data centers in space makes no sense

#899

Post by danans »

mike_hearn wrote: post #582
elamje wrote: post #353

I was talking to someone about this the other day. I was part of a team at NASA that developed a cooling system for the ISS and this whole premise makes no sense to me. 1. Getting things to space is incredibly expensive 2. Ingress/egress are almost always a major bottleneck - how is bandwidth cheaper in space? 3. Chips must be “Rad-hard” - that is do more error correcting from ionizing radiation - there were entire t…

It sounds hard but it shouldn't not make sense. 1. Solving cost of launching mass has been the entire premise of SpaceX since day one and they have the track record. 2. Ingress/egress aren't at all bottlenecks for inferencing. The bytes you get before you max out a context window are trivial, especially after compression. If you're thinking about latency, chat latencies are already quite high and there's going to be…

> Solving cost of launching mass has been the entire premise of SpaceX since day one and they have the track record.

They have to solve for it being cheaper to launch and operate in space vs building and operating a datacenter with its own power generation on Earth.

Post reply on HN