Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

I had thought that Starlink would become extremely compelling when the servers were in orbit as well, but maybe that’s naive. Cubesats with massive arrays of active storage might be far too difficult (aka costly) to protect properly.


Putting servers in orbit is a really, really bad idea. Firstly, it would be wildly inefficient, just due to the unavoidable delay both ways. You expect delay over a long distance network, but you want the server to be positioned and cabled up to minimize latency. Just locating a satellite requires quite a bit of overhead, so treating them as servers rather than clients would create a huge amount of latency. As a failover for ground-based servers in a nuclear war scenario, it could make sense, but they're also literally flying over the airspace of hostile nations who, in a war, have the capability to take them out. Mixing any kind of civilian control onto a server embedded in a flying artifact over an enemy nation is, obviously, a recipe for disaster in a hot war. Take all of that and the fact that the bandwidth is stone-age and spotty depending on its position, and there's no satellite you'd want to use to set up a website selling alpaca sweaters. (Watch: A few years from now we'll find out that the US Space Command runs some second strike end-of-world command control server off a satellite; that still only proves it's too late to contact the fucker when you need it).


> Firstly, it would be wildly inefficient, just due to the unavoidable delay both ways

The point I was thinking about is a scenario where Starlink satellites communicate with each other via laser (already starting to happen), and then communicate with the end user via the satellite over them. Because we're talking about speed-of-light transmission between sats, data in the Starlink network can theoretically cover "ground" (aka miles/km) faster than ground-based ISPs.

Then it makes sense to deploy servers within that network so that two Starlink users can have extremely low latency from user to server to other user (the slowest part being the earth to sat latencies, one for each user).


One of the issues with putting servers in orbit is cooling; you can't just use fans in space. On the other hand, real estate is pretty cheap. Servicing is hard, though, and micrometeorites are another risk. Plus launch costs being high, and radiation an issue, I don't see it happening any time soon outside of very specific areas.


Radiation cooling is pretty dramatic in space. With an isolated radiation shield/mirror from the sun and a decent sized heatsink, you can have a lot of cooling power on hand. A server isn't going to be pumping out nearly as much heat as a rocket engine, and launch vehicles don't tend to overheat.


Forget cooling for a minute. Cooling dissipates energy but you need to collect the energy first and worry about powering the server. It’s going to be a solar-plus-battery system, which is heavy and expensive, with substantial launch costs.


Not sure you need a big battery when you have almost 24/7 sunlight, depending on the altitude. Of course, latency is another issue.


You can’t just put an SSD or whatever in orbit and expect reasonable read latencies at all times. It’s in orbit. It moves. Half the time it’s on the wrong side of the planet.




Consider applying for YC's Winter 2026 batch! Applications are open till Nov 10

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: