Back to results
US 11,953,957 B2Granted
Liquid flow distribution using one or more neural networks
AssigneeNVIDIA Corporation
InventorAli Heydari
Life of this patent
Estimating the term…
Abstract
Systems and methods for cooling a computer environment are disclosed. In at least one embodiment, one or more neural networks can be used to adjust one or more flow control valves, of a liquid cooling system for a data center, to control a variation in liquid flow rate across the data center.
Claims30
A processor, comprising:
- one or more circuits to use a plurality of neural networks, each associated with a respective flow control valve of a plurality of flow control valves that controls flow of coolant for one of a plurality of different components of a data center, to at least one of a) predict a coolant state at the plurality of different components or b) adjust the coolant to cool the plurality of different components independently based, at least in part, on sensor data and one or more cooling requirements of the plurality of different components.
A system, comprising:
- a control system to use a plurality of neural networks, each associated with a respective flow control valve of a plurality of flow control valves that controls flow of coolant for one of a plurality of different components of a data center, to at least one of a) predict a coolant state at the plurality of different components or b) adjust the coolant to cool the plurality of different components independently based, at least in part, on sensor data and one or more cooling requirements of the plurality of different components.
A system comprising:
- one or more processors to use a plurality of neural networks, each associated with a respective flow control valve of a plurality of flow control valves that controls flow of coolant for one of a plurality of different components of a data center, to at least one of a) predict a coolant state at the plurality of different components or b) adjust the coolant to cool the plurality of different components independently based, at least in part, on sensor data and one or more cooling requirements of the plurality of different components.
A method comprising:
- using a plurality of neural networks, each associated with a respective flow control valve of a plurality of flow control valves that controls flow of coolant for one of a plurality of different components of a data center, to at least one of a) predict a coolant state at the plurality of different components or b) adjust the coolant to cool the plurality of different components independently based, at least in part, on sensor data and one or more cooling requirements of the plurality of different components.
A machine-readable medium having stored thereon a set of instructions, which if performed by one or more processors, cause the one or more processors to at least:
- use a plurality of neural networks, each associated with a respective flow control valve of a plurality of flow control valves that controls flow of coolant for one of a plurality of different components of a data center, to at least one of a) predict a coolant state at the plurality of different components or b) adjust the coolant to cool a plurality of different components independently based, at least in part, on sensor data and one or more cooling requirements of the plurality of different components.
Dependencies are inferred from the claim text.