[AvAn12]

Serious question. Is there any technology to capture the excess thermal energy from data centers and run some of it back into the grid? Or drive some kind of desalination process? Or do anything else useful with this “surplus” heat energy?

[miunau]

Helsinki has many DCs connected to the district heating network, but it isn't realistic in places that don't have an existing network as creating one in the first place is a huge political/nimby issue. Amsterdam has been trying and failing for years.

[lytfyre]

Vancouver has a plant that harvests heat from sewage to provide district heating and hot water (https://vancouver.ca/home-property-development/how-the-utili...) - you don't need super high temperatures for it to be useful. During construction there was talk that the Telus building downtown's in house data centre providing heat to the attached condo building (https://www.datacenterknowledge.com/servers/telus-warms-cond...) - I'm unsure if that actually went ahead.

Fundamentally, a limit on doing it at scale is that it for efficiency it requires the heat to be consumed near the production - and the bulk of large power intense data centres are not located in the midst of high density residential neighbourhoods with a demand for heat.

[roryirvine]

It's low-grade heat, so isn't worth much.

If you're going to be doing cogeneration on-site, it can be worth considering a Combined Heating, Cooling, and Power system - but the benefits tend to be fairly marginal.

In the future, there's a possibility of extending the "lights out datacentre" concept, and going fully automated. If you don't need to accommodate humans, you can run much higher temperature gradients.

With a gradient of around 200 K, for instance, you might expect to recover somewhere between 30-35% of your total energy input.

The UK actually ought to be a good choice for an experiment along those lines, given its long history with gas-cooled nuclear systems - sadly, the engineers involved have mostly all retired by now...

[fluorinerocket]

Yes, direct immersion cooling coupled with an organic rankine cycle could do this. But you won't recover much electricity because of the relatively low temperature of the heat source- 60 to 70 deg c dielectric fluid.

[pjc50]

Not really, because you're pumping it against the thermal gradient to start with. Low temperature difference heat is one of the more worthless things in the universe.

The only way you could make this viable would be to change silicon processes to those capable of running at significantly over 100C. This incurs a big efficiency penalty, but then you can start boiling water directly off the die and letting the steam move itself, perhaps to some sort of Stirling engine condenser cycle, with a lot less pumping losses.