Immersion Cooling is a well proven technology in many industries today, most especially when it comes to high power transformers and EV battery packs, it’s the most efficient way to thermally and electrically protect high heat density components.
Computer hardware has been immersion cooled since the early 1960’s with some of the first supercomputers being fully submerged into a dielectric liquid. The main reason for this approach not going mainstream was most probably because we simply didn’t need to do it. We took the path of less resistance. Lower density chips are better off cooled by air but Moore’s Law has been constantly met and now we’re in a very different situation where some major trends are aligning.
What is Immersion Cooling?
Also known as liquid submersion cooling, it is the practice of submerging computer components (or full servers) in a thermally, but not electrically, conductive liquid (dielectric coolant). Still rarely used for the cooling of IT Hardware, this method is slowly becoming popular with innovative datacenters the world over.
IT Hardware or servers cooled in this manner don’t require fans and the heat exchange between the warm coolant and cool water circuit usually occurs through a heat exchanger (i.e. heater core or radiator). Some extreme density supercomputers such as the Cray-2 and Cray T90 use large liquid-to-chilled liquid heat exchangers for heat removal.
There are two types of Immersion Cooling: single-phase and two-phase.
Single-phase Immersion Cooling
Single-Phase coolant never changes state, it never boils or freezes and always remains in a liquid form. The coolant gets pumped to a heat-exchanger where heat is transferred to a cooler water-circuit. This technique uses “open baths”, as there’s little (or no) risk of the coolant evaporating:
Discover the practical and economic benefits of Immersion Cooling
Download the eBook