Intelligent in-rack pump or compressor unit for datacenter cooling systems
摘要
說明書
In at least one embodiment, one or more neural networks may be trained to make inferences by prior associated heat features or cooling requirements from computing devices, servers, or racks, and cooling capacity or capabilities indicated by a fluid source of a local cooling loop, such as by an intelligent in-rack pump or compressor unit having a specific cooling capability that is above a forced air cooling capability, but that may be below a cooling capability of a secondary cooling loop. In at least one embodiment, prior cooling requirements satisfied by a two-phase fluid cooling loop may be used to cause one or more neural networks to make similar inferences for future similar cooling requirements (in consideration of small variations there from) to be satisfied by adjusting one or more flow controllers to engage a two-phase fluid cooling loop.
