Zone-Based CFD Thermal Management for Adaptive Data Center Cooling

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing thermal management systems in data centers require excessive resource deployment and manual recalibration due to varying cooling needs across different zones, leading to inefficiency and high power consumption, as they lack precise real-time monitoring and adaptive control.

Innovation Solution

A system utilizing real-time computational fluid dynamics (CFD) modeling to generate an environmental model of a data center, allowing for zone-based thermal management by adjusting CRAC unit setpoints to maintain optimal temperature and humidity without manual recalibration, using processors and memory to simulate airflow and temperature conditions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If a conservative approach with excessive air conditioning resources is deployed to maintain temperature ranges, then temperature control reliability is improved, but energy consumption and resource deployment costs increase

Engineering Contradiction:
Improvetemperature control reliabilityVSAvoidenergy consumption
Core Design Contradiction:
ReliabilityVSUse of energy by moving object

Solution Approach 1:

The data center is divided into multiple thermal zones based on heat generation patterns and cooling requirements. Each zone is independently modeled and managed, allowing targeted cooling resources to be allocated precisely where needed rather than uniformly across the entire space, thereby reducing overall energy consumption while maintaining temperature control reliability.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system implements dynamic thermal management by continuously updating CFD models with real-time data about equipment operation, environmental conditions, and cooling system performance. This enables adaptive adjustment of cooling setpoints and resource allocation in response to changing thermal conditions, optimizing energy consumption while maintaining reliable temperature control.

Inventive Principle:
Principle #15Dynamics

2Measurement precision

If numerous temperature sensors are deployed throughout the data center to accurately map airflow and temperature conditions, then measurement precision is improved, but device complexity and deployment costs increase

Engineering Contradiction:
Improvetemperature and airflow measurement precisionVSAvoidsensor deployment complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

Instead of physically deploying numerous sensors throughout the data center, the system creates a virtual copy of the physical environment through high-fidelity CFD modeling. This digital twin replicates temperature fields, airflow patterns, and thermal conditions, providing precise measurement data without the complexity of extensive physical sensor infrastructure.

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The system replaces the mechanical sensor deployment and physical measurement infrastructure with computational modeling and simulation. By substituting physical sensing with virtual sensing through CFD, the system achieves equivalent or superior measurement precision while eliminating the complexity of sensor installation, maintenance, and calibration.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

3Adaptability or versatility

If the data center configuration changes (addition, removal, or repositioning of equipment), then adaptability is improved, but the need for manual recalibration and sensor reinstallation increases

Engineering Contradiction:
Improveconfiguration change adaptabilityVSAvoidrecalibration time
Core Design Contradiction:
Adaptability or versatilityVSLoss of time

Solution Approach 1:

The system performs preliminary updates to the CFD model when configuration changes occur, such as equipment addition, removal, or repositioning. By pre-adjusting the virtual model to reflect new conditions, the system prepares thermal management strategies in advance, eliminating the need for manual recalibration and sensor reinstallation after changes are made.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The thermal management system is self-updating and self-adjusting. When configuration changes occur, the system automatically incorporates these changes into the CFD model and recalculates thermal conditions, generating new cooling strategies without requiring manual intervention. This self-service capability maintains adaptability while eliminating time-consuming recalibration processes.

Inventive Principle:
Principle #25Self-service

4Loss of energy

If zone-based thermal management is implemented to address varying cooling needs, then energy efficiency is improved, but the complexity of modeling and control increases

Engineering Contradiction:
Improveenergy efficiencyVSAvoidmodeling and control complexity
Core Design Contradiction:
Loss of energyVSDevice complexity

Solution Approach 1:

The data center is segmented into thermal zones that are independently modeled and controlled. This segmentation allows the complex thermal management problem to be broken down into smaller, manageable sub-problems, each with its own simplified CFD model and control strategy, reducing overall system complexity while improving energy efficiency.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The CFD modeling framework and control system are designed as universal, reusable components that can be applied across all thermal zones. By creating a standardized multi-functional platform for modeling, simulation, and control, the system reduces complexity through reuse and standardization rather than requiring unique custom solutions for each zone.

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

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

Enables efficient, proactive thermal management by minimizing energy consumption and adapting to changes within the data center without the need for manual recalibration, ensuring uninterrupted operation and reducing resource deployment.

Implementation Method 1

real time computational fluid dynamics (CFD) modeling to generate an environmental model of a data center, allowing for zone-based thermal management by adjusting CRAC unit setpoints to maintain optimal temperature and humidity without manual recalibration, using processors and memory to simulate airflow and temperature conditions

Methodology Applied
Scientific EffectComputational fluid dynamics: Convection

Implementation Method 2

CRAC units providing thermal management of the data center by circulating chilled air therethrough

Methodology Applied
Scientific EffectForced convection: Forced Convection

Data Source

PatentEP4601429A1Zone-based thermal management of interior spaces via real time computational fluid dynamics (CFD) modeling
Publication Date: 2025.08.13 VERTIV CORP
  • EP4601429A1 patent drawingFigure 1
  • EP4601429A1 patent drawingFigure 2
  • EP4601429A1 patent drawingFigure 3A

AI summary

A system and method for thermal management of a data center or like environment provides parameters including a dimension set of the environment, an equipment configuration of servers or other IT devices operating within the environment, a computer room air conditioner (CRAC) configuration of CRAC units operating within the environment, and a policy set defining zones within the environment and required environmental conditions (e.g., temperature, humidity) for each zone. A CRAC control loop or like controller generates an environmental model of the environment based on these parameters and infers current environmental conditions on a zone-by-zone basis. If, for example, inferred conditions in one or more zones sufficiently deviate from, or trend toward deviation from, the required conditions for said zones, the controller may adjust one or more CRAC setpoints to maintain said zones within required temperature and/or humidity ranges.