In-row cooling unit with interchangeable heat exchangers

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Datacenter cooling systems face challenges in efficiently managing varying cooling requirements due to changing computing loads, particularly in high heat density areas like those around GPUs, CPUs, and switches, where existing systems often struggle to optimize between liquid and air cooling effectively.

Innovation Solution

The implementation of an in-row cooling unit with interchangeable heat exchangers (IHEs) that can switch between air and liquid cooling modes, using primary coolant to cool both secondary coolant and air, and integrating flow controllers to optimize heat removal from both air and liquid-cooled components.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If traditional separate air cooling and liquid cooling systems are used, then each cooling method can be applied to its suitable components, but the system complexity increases and flexibility to adapt to varying cooling demands decreases

Engineering Contradiction:
Improveflexibility to adapt to varying cooling demandsVSAvoidsystem complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent combines air cooling and liquid cooling systems into a single integrated in-row cooling unit. The housing contains both air cooling components (fans, air inlets/outlets) and liquid cooling components (heat exchangers, coolant flow paths) that work together as one unified system, reducing the need for separate cooling installations while providing flexible adaptation to varying cooling demands through a single controllable unit

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The in-row cooling unit is designed to perform multiple cooling functions simultaneously - it can cool air for general components and provide liquid cooling for high-heat-density components like GPUs and switches through interchangeable heat exchangers. The system can operate in different modes (air cooling only, liquid cooling only, or combined) to adapt to varying cooling requirements of different server components within the same rack

Inventive Principle:
Principle #6Universality (Multi-functionality)

2Productivity

If fixed cooling capacity systems are used, then system design is simplified, but the ability to respond to changing computing loads and heat density requirements is reduced

Engineering Contradiction:
Improveresponse to changing computing loadsVSAvoidinterchangeable heat exchanger mechanism
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The system incorporates interchangeable heat exchangers that can be swapped based on cooling requirements. The liquid cooling heat exchangers can be installed when high heat density components are present, and removed or replaced when such components are absent, allowing the cooling capacity to dynamically match the actual thermal load of the server rack

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system allows changing the cooling parameters by swapping heat exchangers with different specifications. When high-performance cooling is needed, heat exchangers with higher thermal conductivity and larger surface area can be installed. When cooling demands are lower, different heat exchanger configurations can be used, optimizing the cooling performance to match the actual computational load

Inventive Principle:
Principle #35Parameter changes

3Temperature

If liquid cooling is used for all components, then cooling efficiency for high heat density components improves, but energy consumption and system complexity increase for components that don't require liquid cooling

Engineering Contradiction:
Improvecooling efficiency for high heat density componentsVSAvoidenergy consumption
Core Design Contradiction:
TemperatureVSUse of energy by moving object

Solution Approach 1:

The system applies different cooling methods to different locations and components based on their specific thermal requirements. Liquid cooling via heat exchangers is applied locally to high-heat-density components like GPUs and switches that require it, while air cooling is used for other components with lower thermal demands, optimizing energy consumption by avoiding over-cooling of components that don't need liquid cooling

Inventive Principle:
Principle #3Local quality

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

This solution allows for flexible and efficient cooling management, addressing the varying cooling demands by seamlessly transitioning between air and liquid cooling, thereby optimizing energy use and maintaining optimal temperatures across high heat density components.

Implementation Method 1

a heat exchanger to exchange heat between the secondary coolant and the primary coolant

Methodology Applied
Scientific EffectThermal conduction: Conduction (thermal)

Implementation Method 2

Datacenter cooling systems use fans to circulate air through server components

Methodology Applied
Scientific EffectForced convection: Forced Convection

Implementation Method 3

The area external to the datacenter may include a cooling tower or other external heat exchanger that receives heated coolant from the datacenter and that disperses the heat by forced air or other means to the environment

Methodology Applied
Scientific EffectEvaporative cooling: Evaporative Cooler

Data Source

PatentUS12016154B2In-row cooling unit with interchangeable heat exchangers
Publication Date: 2024.06.18 NVIDIA CORP
  • US12016154B2 patent drawing
  • US12016154B2 patent drawing
  • US12016154B2 patent drawing

AI summary

Systems and methods for cooling a datacenter are disclosed. In at least one embodiment, an in-row cooling unit is located within a row of racks and between racks so that it can use an interchangeable heat exchanger (IHE) to receive a primary coolant and can use one or more flow controllers to provide a first part of the primary coolant to cool a secondary coolant that is to be distributed to at least one cold plate, and to provide a second part of the primary coolant to cool air to be circulated through at least one server tray or rack.