Datacenter Liquid Cooling Flow Control for Temperature Balance

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing datacenter cooling technologies face challenges in effectively controlling and balancing the temperature of cooling liquids supplied to and returned from rack-mounted processing assemblies, which affects cooling efficiency.

Innovation Solution

A method and system that utilize a dry cooling unit and smart control valves to dynamically adjust the flow rate of cooling liquids based on detected temperatures and pressure flows, ensuring optimal temperature differential between supplied and returned liquids.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Temperature

If conventional liquid cooling arrangements are used without dynamic flow control, then the system structure is simple, but the temperature control precision and cooling efficiency deteriorate

Engineering Contradiction:
Improvetemperature control precisionVSAvoidcooling system complexity
Core Design Contradiction:
TemperatureVSDevice complexity

Solution Approach 1:

The cooling system is segmented into multiple independent zones, each equipped with its own smart control valve. This allows individual temperature control for each rack or section, enabling precise temperature management without requiring complete system redesign.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

Static cooling systems are transformed into dynamic systems by introducing smart control valves that automatically adjust flow rates based on real-time temperature and pressure feedback. This dynamic adaptation enables precise temperature control while maintaining system simplicity through automated control logic.

Inventive Principle:
Principle #15Dynamics

2Stability of the object's composition

If uniform cooling flow is provided to all racks, then the system operation is simple, but the temperature balance and cooling efficiency worsen due to varying heat loads

Engineering Contradiction:
Improvetemperature balanceVSAvoidflow rate control
Core Design Contradiction:
Stability of the object's compositionVSEase of operation

Solution Approach 1:

Each rack or cooling zone is provided with localized flow control capabilities through smart valves. This enables each zone to receive the specific flow rate it needs based on its local heat load characteristics, achieving temperature balance without requiring complex centralized control.

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

Temperature and pressure sensors provide continuous feedback to the smart control valves, which automatically adjust flow rates to maintain optimal temperature balance. This closed-loop feedback system achieves superior temperature distribution while keeping operation simple through automated control.

Inventive Principle:
Principle #23Feedback

3Reliability

If high flow rates are used throughout the system, then cooling capacity is sufficient, but energy consumption and pump power requirements increase

Engineering Contradiction:
Improvecooling effectivenessVSAvoidpump energy consumption
Core Design Contradiction:
ReliabilityVSUse of energy by moving object

Solution Approach 1:

The system transitions from constant high flow rates to dynamic flow rate adjustment. Smart control valves modulate flow rates in real-time based on actual cooling demands, ensuring sufficient cooling effectiveness while minimizing pump energy consumption through optimized flow distribution.

Inventive Principle:
Principle #15Dynamics

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

The solution enhances cooling efficiency by maintaining an optimal temperature differential, preventing overheating, and ensuring efficient heat dissipation, thereby improving the overall performance of datacenter liquid cooling systems.

Implementation Method 1

the at least one liquid cooling block being arranged to be in respective thermal contact with the at least one heat-generating electronic processing element

Methodology Applied
Scientific EffectThermal conduction: Conduction (thermal)

Implementation Method 2

the received cooling liquid absorbs the generated heat and the heated liquid is circulated, via the cooling loop arrangement, back to cooling liquid source for re-cooling

Methodology Applied
Scientific EffectConvection: Convection

Data Source

PatentUS20250056772A1Intelligent temperature control and balance of datacenter liquid cooling arrangements
Publication Date: 2025.02.13 OVH
  • US20250056772A1 patent drawing
  • US20250056772A1 patent drawing
  • US20250056772A1 patent drawing

AI summary

A liquid cooling method and system for cooling rack-mounted processing assemblies is presented that provides a dry cooling unit, a first liquid distribution circuit to convey the cooling liquid and a second liquid distribution circuit to convey the heated liquid from the rack-mounted processing assemblies, in which each of the rack-mounted data processing assemblies comprises a smart control valve designed to be pressure independent and control the flow rate of the cooling fluid based on detected temperatures and pressure flows. Each of the smart control valves operative to measure current liquid flow rates, current input cooling liquid temperatures, and current output heated liquid temperatures and calculate a current differential temperature, determine a relationship between the current differential temperature and a target temperature value, and dynamically adjust the liquid flow rate of the smart control valve based on the determined relationship and the current liquid flow rate and current input cooling liquid temperature.