Thermal Management For Data Centers 2026-2036: Technologies, Markets, and Opportunities

Granular ten-year forecast for data center cooling technologies and components, including air cooling, single-phase/two-phase D2C/immersion cooling and their associated components. Comprehensive analysis of TIM2 for data center components.

Show All Description Contents, Table & Figures List FAQs Pricing Related Content
With the increasing demand for high-performance computing in sectors like AI, cloud computing, and crypto mining, the thermal design power (TDP) of chips has risen significantly over the past 16 years. Nivida's B300 GPU, released in early 2025, has already demonstrated a TDP of 1400W with its NV rack demanding a total power of 140kW. With the roadmap released by Nvidia on its next-generation Rubin chip and similar upcoming competitors such as MI400, IDTechEx believes we will soon see chips with TDP over 1500kW. This upward trend in TDP has propelled a need for more efficient thermal management systems at both the micro (inside semiconductor packaging, on-chip, and on-server) and macro (server rack and facility) levels. In recent years, leading data center hyperscalers and colocators have collaborated with various cooling component suppliers, server ODMs (original design manufacturers), system integrators, and fabless designers, to launch innovative pilot projects and commercialize ready-to-use cooling solutions, aiming to enhance cooling performance and meet sustainability targets by adopting more efficient cooling solutions.
 
IDTechEx's report, "Thermal Management for Data Centers 2026-2036" covers a granular market forecast of data center cooling technologies segmented cooling technology (e.g., single-phase direct-to-chip (D2C), two-phase D2C, single-phase immersion, and two-phase immersion). The report conducts in-depth technical and commercial of essential components for liquid cooling, along with a breakdown of the cooling value chain, technological barriers of different cooling methods, cost analysis of players in different value chain positions, value chain consolidation potentials, and roadmap for the future cooling strategy.
 
In addition to technical analysis, a comprehensive commercial landscape, such as, data center cooling value chain, partnerships between players across the value chain, a summary of liquid cooling suppliers for leading players, and competitive landscape analysis has also been analyzed.
 
The report delivers an in-depth volume and market size forecast for liquid cooling, categorized by components including piping/valves/monitoring, CDUs for immersion, immersion coolant, immersion tanks, heat sinks, 3D vapor chambers, CDUs for D2C, sidecar, rear door heat exchanger (RDHx), fans, quick disconnects, manifolds, and cold plate systems (including cold plates, hoses, pipes, and fluid distribution networks within servers). It also offers a detailed forecast for immersion cooling, segmented by immersion tanks, immersion coolant, CDUs, and related piping, valves, and monitoring systems. Additionally, the forecast is further divided by single-phase and two-phase cooling technologies.
 
The report also provides a 10-year outlook on the use of thermal interface materials (TIM) for data center components, including TIM2s and TIM1s/TIM1.5s for advanced processors. Moreover, it includes a forecast of liquid cooling adoption, differentiating between AI and non-AI applications, to highlight the industries expected to present the most significant opportunities.
 
Cooling Overview
Data center cooling methods can be broadly categorized into air cooling and liquid cooling, depending on the cooling medium employed. Air cooling relies on air conditioning and/or fans, utilizing convection to dissipate heat from the servers. It has been widely adopted due to its long and successful track record. However, the low specific heat of air makes it challenging to meet the increasing cooling capacity requirements. Additionally, as data center users strive to maximize rack space utilization by densely packing servers (typically 1U servers), the air gaps between servers become narrower, which further reduces the efficiency of air cooling.
 
Liquid cooling, on the other hand, takes advantage of the higher specific heat of liquid to achieve superior cooling performance. Depending on the which components the fluids contact, liquid cooling can be classified into direct-to-chip/cold plate cooling, spray cooling, and immersion cooling. Direct-to-chip cooling involves mounting a cold plate with coolant fluid directly on top of heat sources such as GPUs, with a thermal interface material (TIM) applied in between. Cold plate cooling (including both single-phase and two-phase cold plates) can achieve a partial power use effectiveness (pPUE) ranging from 1.02 to 1.20, depending on the specific configuration.
 
An emerging alternative is immersion cooling where the servers are fully submerged in coolant fluids, enabling direct contact between the heat sources and the coolant, thereby achieving the best cooling performance with the lowest pPUE of 1.01. However, its widespread adoption is still limited due to challenges such as high upfront costs (in terms of US$/Watt), maintenance, and complexities of retrofitting the server boards. Nevertheless, immersion cooling holds potential for long-term energy savings thanks to their efficient thermal dissipation, which is not only economically beneficial given the current context of energy crisis but also helps the large companies to achieve their sustainability goals in the long run.
 
IDTechEx's comparative analysis of the 10-year total cost of ownership (TCO) between D2C cooling, 1-PIC and 2-PIC immersion across four regions reveals that over the course of 10 years, D2C on average has a 13% lower TCO than 1-PIC immersion and 9.4% lower than 2-PIC immersion, subject to the assumptions listed in the report. This report also highlights strategic collaborations and pilot projects between data center end-users, server OEMs, and immersion cooling vendors, as well as other barriers hindering the widespread adoption of immersion cooling. Market adoption (hardware units) and revenue forecasts are provided for air, cold-plate, and immersion cooling through to 2036.
 
Liquid cooling can also be classified into single-phase and two-phase cooling. Two-phase cooling generally exhibits greater effectiveness, but it also presents challenges such as regulations regarding two-phase immersion refrigerant based on perfluoroalkyl and polyfluoroalkyl substances (PFAS), mechanical strength requirements for fluid containers to withstand increased pressure during phase changes, fluid loss due to vaporization, pressure drop with increasing flow rate, and high maintenance complexities and costs. The fundamental operating principles of single- and two-phase cooling is different where single-phase cooling relies on the dissipating the heat through convection whereas two-phase coolant primarily rely on dissipating the heat through the latent heat during the phase change. This report provides an analysis of different liquid cooling vendors, coolant fluid suppliers, and data center end-users, offering insights into the opportunities and threats associated with single-phase and two-phase direct-to-chip/cold plate and immersion cooling.
 
As 2.5D and 3D packaging technologies advance, there is a growing need for high-performance TIM1 materials in advanced semiconductor packaging, along with potential microfluidic cooling solutions. IDTechEx's report, "Thermal Management for Data Centers 2026-2036" provides an analysis of TIM1 materials for advanced semiconductor packaging and forecasts its market size from 2026 to 2036.
 
Source: Benchmarking analysis of cooling solutions for data centers. Source: IDTechEx's "Thermal Management for Data Centers 2026-2036"
IDTechEx anticipates rapid growth in the adoption of liquid cooling, driven by factors such as the increasing power of data centers, the rise of hyperscale data centers, the availability of ready-to-use liquid cooling solutions, high flexibility and ability to retrofit, and the market trends driven by large players such as Nvidia. Specifically, cold plate cooling is expected to experience the largest growth due to its cost effectiveness and compatibility with existing air-cooled data centers, eliminating the need for extensive retrofitting to accommodate immersion cooling solutions.
 
In line with these projections, this report offers a detailed 10-year revenue forecast for hardware related to liquid cooling in data centers segmented AI and non-AI applications. Within non-AI applications, IDTechEx also splits the forecasts of cold plate cooling by server rack power.
 
Market Opportunities
With greater adoption of liquid cooling, new opportunities are emerging, leading to strengthened collaborations among companies involved in the data center cooling supply chain. Component suppliers such as coolant distribution units (CDUs) vendors, pump vendors, and coolant fluid suppliers are expected benefit from the increased adoption of liquid cooling. CDUs and pumps are critical components for controlling the flow rate in liquid cooling systems. Factors such as pressure drop need to be carefully considered. This report introduces various commercial in-rack and in-row CDUs, accompanied by a comprehensive comparison of coolant fluids based on their dynamic viscosity, density, specific heat, thermal conductivity, as well as required pipe length and pipe diameter.
 
One of the emerging trends in vertical integration is seen in the data center cooling value chain, which is intricate and extensive. Although many liquid cooling solution suppliers advocate for increased collaboration across the value chain, the current landscape remains fragmented and chaotic, requiring extensive work from system integrations to integrate every component together into a data center. IDTechEx has identified potential opportunities for market consolidation, with server OEMs beginning to offer comprehensive rack-level cooling solutions. These solutions encompass various components, including cold plates on servers, server racks, and essential parts such as manifolds, CDUs, and QDs. IDTechEx has also summarizes the liquid cooling component supply chain, with leading players, their capacity, and collaboration across companies in the value chain.
 
Source: IDTechEx, Thermal Management for Data Centers 2026-2036
Key Aspects
This report provides critical market intelligence on data center cooling technologies across multiple solution categories. This includes:
 
  • An updated forecast of data center power demand from 2026 to 2036, including key assumptions and methodology.
  • A comprehensive review of liquid cooling economics, including payback time analysis, benchmarking of CAPEX and OPEX across four case studies, and value chain assessment of adoption drivers.
  • A full market characterization of single-phase direct-to-chip (D2C) cooling, including thermal cost analysis of cold plate systems, rack-level power distribution impacts, and a forecast from 2025 to 2036 covering cold plates, quick disconnects, fans, CDUs, and manifolds (both market size in US$ and sales volume in units). This also includes analysis of market share between single-phase and two-phase D2C cooling.
  • An overview of two-phase direct-to-chip cooling, covering adoption drivers and barriers, as well as its adoption timeline in relation to processor TDP evolution.
  • A detailed assessment of single-phase immersion cooling, including the use of TIMs, a forecast from 2026 to 2036 (covering coolant, tanks, CDUs, and associated infrastructure such as piping and monitoring), and market share comparisons with two-phase immersion cooling.
  • A review of two-phase immersion cooling, focusing on barriers to adoption and potential technology bottlenecks.
  • A new chapter on microfluidic cooling, including its research frontiers, use cases for advanced chips, forecasts for microfluidic-cooled semiconductor packaging units, and a review of technical barriers.
  • A new dedicated sub-chapter on coolant, including a market forecast to 2036, compatibility analysis with materials (plastics, metals, hoses/pipes) across immersion and D2C solutions, and cost comparisons of single- vs. two-phase coolants.
  • An updated analysis of thermal interface materials (TIMs), including TIMs for immersion cooling, TIM1 and TIM1.5 for advanced semiconductor packaging, market forecasts for TIM1/1.5, and an updated market sizing for TIM2 in data centers.
  • Expanded coverage of coolant distribution units (CDUs), including liquid-to-liquid cooling configurations, commercial examples, energy savings vs. liquid-to-air systems, component-level analysis (pumps, filters, sensors), and emerging trends in in-row and in-rack CDUs.
  • A new chapter on quick disconnects (QDs), including cost analysis and market trends.
  • A review of supply chain dynamics, partnerships, and cooling roadmaps, including supplier capacity for cold plates, market share of leading suppliers, server supply chain breakdown (ODMs, chassis, CPUs, switches, and thermal components), Nvidia's liquid cooling suppliers by component, and updated cost benchmarks across cooling elements.
  • Market and commercial opportunity analysis, including value chain collaboration by data center type (hyperscalers, colocators, enterprise), granular cooling component cost breakdowns (cold plates, fans, CDUs, QDs, etc.), and total cost of ownership (TCO) and payback time evaluations.
Report MetricsDetails
Historic Data2022 - 2025
CAGRThe global market for liquid cooling components for data centers will grow at a CAGR of 13% between 2026 and 2036.
Forecast Period2026 - 2036
Forecast UnitsUS$, unit, m2
Regions CoveredWorldwide
Segments CoveredAir cooling, single-phase direct-to-chip cooling, two-phase direct-to-chip cooling, single-phase immersion, two-phase immersion, microfluidic cooling, thermal interface materials, coolant for liquid cooling, liquid cooling components (piping/valves/monitoring, CDUs for immersion, immersion coolant, immersion tanks, heat sinks, 3D vapor chambers, CDUs for direct-to-chip cooling, sidecar, rear-door heat exchanger (RDHx), manifolds, fans, quick disconnects, cold plates).
Analyst access from IDTechEx
All report purchases include up to 30 minutes telephone time with an expert analyst who will help you link key findings in the report to the business issues you're addressing. This needs to be used within three months of purchasing the report.
Further information
If you have any questions about this report, please do not hesitate to contact our report team at research@IDTechEx.com or call one of our sales managers:

AMERICAS (USA): +1 617 577 7890
ASIA (Japan and Korea): +81 3 3216 7209
EUROPE (UK) +44 1223 812300
1.EXECUTIVE SUMMARY
1.1.TDP Trend: Historic Data and Forecast Data - GPU
1.2.TDP Trend: Historic Data and Forecast Data - CPU
1.3.Ever increasing data center power demand and thermal demand
1.4.Cooling Methods Overview
1.5.Different Cooling on Chip Level
1.6.Yearly Revenue Forecast By Cooling Method: 2022-2036
1.7.Summary of Yearly Revenue Forecast for Liquid Cooling: 2022-2036
1.8.Summary of Yearly Revenue Forecast for Liquid Cooling Data: 2022-2036
1.9.Cost analysis of cooling systems
1.10.Yearly Immersion Cooling Revenue Forecast: 2022 - 2036
1.11.Cooling Technology Comparison
1.12.Data Center Efficiency - Analytical Evolution
1.13.Air Cooling
1.14.Liquid Cooling - Direct-to-Chip/Cold Plate and Immersion
1.15.Liquid Cooling - Single-Phase and Two-Phase
1.16.Heat dissipation path for two-phase D2C cooling
1.17.Yearly Number of Single- and Two-Phase Cold Plates Forecast: 2022-2036
1.18.Immersion Tank Yearly Number Forecast: 2022-2036
1.19.Coolant Comparison
1.20.Coolant Comparison - PFAS Regulations
1.21.Coolant Distribution Units (CDU)
1.22.Heat Transfer - Thermal Interface Materials (TIMs) (1)
1.23.Heat Transfer - Thermal Interface Materials (TIMs) (2)
1.24.Cooling cost analysis
1.25.OPEX and TCO Estimation
1.26.Pricing of Direct-to-Chip, Immersion and Air Cooling - US$/Watt
2.INTRODUCTION
2.1.Overview
2.1.1.Ever increasing data center power demand and thermal demand
2.1.2.Data Center Equipment - Top Level Overview
2.1.3.Data Center Server Rack and Server Structure
2.1.4.Power Use Effectiveness
2.1.5.Data Center Switch Topology - Three Layer and Spine-Leaf Architecture
2.1.6.K-ary Fat Tree Topology
2.2.Data Center Thermal Management Overview
2.2.1.Thermal Management Needs for Data Centers
2.2.2.Significant Consequences for Data Center Downtime
2.2.3.Data Center Location Choice
2.2.4.Increasing TDP Drives More Efficient Thermal Management
2.2.5.Overview of Thermal Management Methods for Data Centers
2.2.6.Thermal Management Categorization
2.3.Thermal Design Power (TDO) Evolution
2.3.1.Historic Data of TDP - GPU
2.3.2.TDP Trend: Historic Data and Forecast Data - CPU
2.3.3.Nvidia's Chips TDP Trend
3.THERMAL MANAGEMENT METHODS
3.1.Introduction to Data Center Cooling Classification
3.2.Cooling Technology Comparison (1)
3.3.Cooling Technology Comparison (2)
3.4.Air Cooling
3.5.Hybrid Liquid-to-Air Cooling
3.6.Hybrid Liquid-to-Liquid Cooling
3.7.Hybrid Liquid-to-Refrigerant Cooling
3.8.Hybrid Refrigerant-to-Refrigerant Cooling
4.AIR COOLING
4.1.Overview
4.1.1.Introduction to Air Cooling (1)
4.1.2.Introduction to Air Cooling (2)
4.1.3.Benefits and Drawbacks of Air-Cooling Methods
4.1.4.Use Case: Row-Level Cooling Liebert® CRV CRD25
4.1.5.Overview: RDHx
4.1.6.Hybrid Air-to-Liquid Cooling - nVent
4.1.7.Cooling Tower - Adiabatic Cooling
4.1.8.Balance Between Water Use and Power Use - Case by Case in Practice
4.1.9.Use Case: Jaeggi - Adiabatic and Hybrid Dry Coolers
4.1.10.Trend for Air Cooling in Data Centers
4.2.Air Cooling Forecasts
4.2.1.Percentage of Air-Cooled Racks
4.2.2.TCO Comparison
5.LIQUID COOLING OVERVIEW
5.1.Liquid Cooling and Immersion Cooling
5.2.Comparison of Liquid Cooling Technologies (1)
5.3.Comparison of Liquid Cooling Technologies (2)
5.4.Liquid Cooling - Power Limitation of Different Cooling on Rack Level
5.5.Different Cooling on Chip Level
5.6.Data Center By Power
5.7.Liquid-Cooled Data Center Server Rack by Power
5.8.Liquid-Cooled Data Center Server Rack by Power
6.COLD PLATES
6.1.Overview
6.1.1.Cold Plate/Direct to Chip Cooling - Standalone Cold Plate
6.1.2.Liquid Cooling Cold Plates
6.1.3.Cold Plate/Direct to Chip Cooling in Server Boards
6.1.4.Benefits and Drawbacks of Cold Plate Cooling
6.1.5.Cold Plate Requirements
6.1.6.Considerations for Cold Plate Design (1)
6.1.7.Considerations for Cold Plate Design (2)
6.1.8.Thermal Cost Analysis of Cold Plate System - (1)
6.1.9.Thermal Cost Analysis of Cold Plate System - (2)
6.1.10.Performance comparison of single-phase and two-phase D2C cooling
6.1.11.Cooling power density of single- and two-phase D2C cooling
6.1.12.Liquid Cooling Technology Definitions (1)
6.1.13.Liquid Cooling Technology Definitions (2)
6.2.Single-Phase Cold Plate
6.2.1.Single-Phase Cold Plate Considerations
6.2.2.IEI Integration Corp
6.2.3.Why Single-Phase Cold Plate Might Dominate
6.2.4.Use case: Nvidia silicone photonics co-packaged optics cold plate cooling
6.3.Two-Phase Cold Plate
6.3.1.Two-phase D2C - higher thermal performance but different hardware designs
6.3.2.Benefits of two-phase D2C (1/3)
6.3.3.Benefits of two-phase D2C (2/3)
6.3.4.Benefits of two-phase D2C (3/3)
6.3.5.Heat dissipation path for two-phase D2C cooling
6.3.6.Wieland Group - Two-Phase Evaporator/Cold Plate
6.3.7.Passive Cold Plate Cooling - Frigel & Neurok Thermocon
6.3.8.Examples: Direct-to-Chip Cooling
6.3.9.Tyson - Passive Two-Phase Cooling
6.3.10.Passive Loop Heat Pipes (LHP)
6.3.11.Use Case: Calyos
6.3.12.Direct Water-Cooled Server - ABB
6.3.13.Cold plate and component material selection for 2-phase cold plates
6.3.14.Thermal performance testing results - Accelsius
6.4.Cold Plate Forecast
6.4.1.Yearly Number of Cold Plate for AI and Non-AI Forecast: 2022-2036
6.4.2.Yearly Number of Single- and Two-Phase Cold Plates Forecast: 2022-2036
6.4.3.Market Share Forecast of Single- and Two-Phase Cold Plate: 2022-2036
6.4.4.Yearly Number of Cold Plate For Non-AI (mainly HPC) Forecast: 2026-2036
6.4.5.Yearly Number of Cold Plate For Non-AI (mainly HPC) Forecast Data Table: 2026-2036
6.4.6.Total Cost Analysis of Cold Plate (Cold plate + QD + Manifold, Hoses, etc.)
6.4.7.GPU and CPU Cold Plate System Forecast: 2025-2036
6.4.8.Yearly Revenue Forecast Summary of Cold Plate: 2022-2036
6.4.9.Yearly Cold Plate Revenue Forecast: 2022-2036
6.4.10.Yearly Revenue of Cold Plate of CPU and GPU: 2025-2035
6.5.Summary of Cold Plate Cooling
6.5.1.Overview: Cold Plate
6.5.2.Cold Plate Structure
6.5.3.Benefits and Challenges of Cold Plate Cooling (1)
6.5.4.Benefits and Challenges of Cold Plate Cooling (2)
6.5.5.Limitations of Cold Plate Cooling
6.5.6.Summary of Cold Plate Cooling - Considerations
6.5.7.Thermal Cost Analysis of Cold Plate System - (1)
6.5.8.Thermal Cost Analysis of Cold Plate System - (2)
7.SPRAY COOLING
7.1.Introduction to Spray Cooling
7.2.Advanced Liquid Cooling Technologies (ALCT) - Spray Cooling
8.IMMERSION COOLING
8.1.Overview
8.1.1.Single-Phase and Two-Phase Immersion - Overview (1)
8.1.2.Single-Phase Immersion Cooling (2)
8.1.3.SWOT: Single-Phase Immersion Cooling
8.1.4.Overview: Two-Phase Immersion Cooling
8.1.5.SWOT: Two-Phase Immersion Cooling
8.2.Single Phase
8.2.1.Use Case: Iceotope - Direct-to-Chip + Immersion
8.2.2.Use Case: LiquidCool Solutions - (1)
8.2.3.Use Case: LiquidCool Solutions - (2)
8.2.4.Use Case: Green Revolution Cooling (GRC)
8.2.5.nVent/Iceotope and LiquidCool Solutions - Limited Differentiation
8.2.6.DCX Liquid Cooling - Immersion
8.3.Two-Phase
8.3.1.Wieland - Two-Phase Immersion Cooling
8.3.2.Two-Phase Cooling - Phase Out Before Starting to Take Off?
8.3.3.Roadmap of Two-Phase Immersion Cooling
8.3.4.Roadmap of Single-Phase Immersion Cooling
8.3.5.Examples: Immersion
8.3.6.Use-Case: Iceotope and Meta
8.3.7.Use-Case: Microsoft
8.3.8.Use-Case: Microsoft Halted its Underwater Data Centers
8.3.9.Asperitas
8.3.10.Gigabyte
8.3.11.Summary (1) - Benefits of Immersion Cooling
8.3.12.Summary (2) - Challenges of Immersion Cooling
8.3.13.Cost Saving Comparison - Immersion and Air Cooling
8.3.14.Comparison of Liquid Cooling Methods
8.3.15.Pricing of Direct-to-Chip, Immersion and Air Cooling - US$/Watt
8.3.16.Immersion Tank Yearly Number Forecast: 2022-2035
8.3.17.Immersion Cooling Revenue Forecast: 2022-2036
9.MICROFLUIDIC COOLING
9.1.1.Benchmark Cooling Technologies for HPC
9.1.2.Microfluidic Overview
9.1.3.Benchmark of Cooling Configurations for HPC Packages
9.1.4.Microchannel studies - performance benchmark
9.1.5.Design Principles and Challenges of Microchannel Heat Sink Architecture - 1
9.1.6.Design Principles and Challenges of Microchannel Heat Sink Architecture - 2
9.1.7.Wafer-Level Microchannel Integration for Cooling
9.1.8.Thermal Design Considerations and Coolant Selection for Microchannel Systems
9.1.9.Barriers to Microchannel Integration and System Adoption
9.1.10.Microsoft - Integrated Silicon Microfluidic Cooling
9.1.11.Microfluidics Cooling Heatsink Structure and Manufacture
9.1.12.On-package liquid cooling for HPC
9.1.13.imec - microfluidic cooling (1/2)
9.1.14.imec - microfluidic cooling (2/2)
9.1.15.Intel foundry thermal capabilities with TIM options and in-package liquid cooling
9.1.16.IBM z17
9.1.17.Microfluidic cooling ASP unit forecast: 2026-2036
10.COOLANT
10.1.Immersion Coolant
10.1.1.Introduction to Cooling Fluid
10.1.2.Coolant Fluid Comparison - Operating Temperature
10.1.3.Thermal conductivity of coolant
10.1.4.Trend - Decline in Fluorinated Chemicals?
10.1.5.Immersion Coolant Liquid Suppliers
10.1.6.Engineered Fluids - Why Better Than Oils
10.1.7.What is the Roadmap for Coolant in Two-Phase Cooling?
10.1.8.Honeywell R-1233zd and Chemours' Opteon SF33
10.1.9.Demand for Immersion Coolant Standardization - FOMs
10.1.10.Figures of Merit (FOM)
10.1.11.Force Convection FOM for Single-Phase Immersion
10.1.12.FOM3 - Viscosity for Pressure Drop
10.1.13.Density
10.1.14.Signal Integrity Evaluations
10.1.15.Global Warming Potential (GWP)
10.1.16.Material Compatibility Guide - Immersion Coolant and TIMs/Adhesives
10.1.17.Material Compatibility Guide - Seals/Gaskets/O-Rings and Immersion Coolant
10.1.18.Material Compatibility Guide - Plastics and Immersion Coolant
10.1.19.Material Compatibility Guide - Pipe & Fitting and Immersion Coolant
10.1.20.Material Compatibility Guide - Metal and Immersion Coolant
10.1.21.Yearly Coolant Volume for Immersion: 2022-2036
10.1.22.Overview of PFAS Types, Post-PFAS Blends, PFAS-Free Data Center Coolant Alternatives
10.1.23.Mapping Refrigerants in Use and Technology Trends
10.1.24.Adoption Forecasts and Performance Assessment
10.1.25.Comparative Advantages and Limitations
10.1.26.Regulatory barriers
10.1.27.Classes of different refrigerants
10.2.D2C Coolant
10.2.1.Refrigerants for two-phase DLC (1/2)
10.2.2.Refrigerants for two-phase DLC (2/2)
10.2.3.Compatibility for thermoplastics and elastomers
10.2.4.Properties of PG-based coolant for single-phase D2C
11.SUPPLY CHAIN, PARTNERSHIPS AND ROADMAP
11.1.1.Data Center Cooling Value Chain
11.1.2.Cooling Solution Partner
11.1.3.Summary of a few cooling solution suppliers
11.1.4.Summary of key companies and their customers
11.1.5.Summary of key ODMs and Cooling Component Suppliers
11.1.6.Market Share of Cold Plate Suppliers
11.1.7.Server Supply Chain
11.1.8.Cost Analysis of Server Cooling Components
11.1.9.Nvidia's Liquid Cooling Supply Chain - 2025
11.1.10.Intel and Submer - Heat Reuse and Immersion Cooling
11.1.11.Iceotope, Intel and HPE
11.1.12.Iceotope, Schneider Electric, and Avnet - Liquid Cooled Data Center
11.1.13.GRC and Intel
11.1.14.GRC and Dell - Edge Deployment
11.1.15.Iceotope and Meta
11.1.16.Development of New Immersion Coolant - ElectroSafe
11.1.17.Partnership - how does the value chain look like?
11.1.18.Roadmap of Liquid Cooling Adoption
11.1.19.Data Center Cooling Solution - Roadmap
12.TOTAL COST OF OWNERSHIP ANALYSIS
12.1.Cooling cost analysis
12.2.OPEX and TCO Estimation
12.3.TCO Comparison - Payback Time
12.4.Pricing of Direct-to-Chip, Immersion and Air Cooling - US$/Watt
12.5.TCO Analysis of D2C with Chiller
12.6.TCO Analysis of 1-PIC with Chiller
12.7.TCO Analysis - 10 Year
12.8.Cooling System Cost - Direct to Chip Cooling Hardware
12.9.Immersion Cooling Cost - Componentry and Facility Level
12.10.Cooling System Cost - CDUs Hardware
12.11.Cost - Fluids
12.12.Cooling System Cost - Thermal Interface Materials
13.COOLANT DISTRIBUTION UNITS (CDUS)
13.1.Overview
13.1.1.Overview
13.1.2.Trend of in-row and in-rack CDUs
13.1.3.Redundancy - (1)
13.1.4.Redundancy - (2)
13.1.5.Liquid-to-Liquid (also known as L2L) CDUs
13.1.6.Liquid-to-Air CDUs
13.1.7.Summary of Liquid-to-Liquid and Liquid-to-Air Cooling
13.1.8.Vertiv - Liebert® XDU 60 Heat Exchanger and CDU - (1)
13.1.9.Vertiv - Liebert® XDU Heat Exchanger and CDU - (2)
13.1.10.CDU - nVent
13.1.11.CDU - CoolIT - Teardown (1)
13.1.12.CDU - CoolIT - Teardown (2)
13.1.13.CDU - CoolIT - Teardown (3)
13.1.14.CDU Teardown - Motivair
13.1.15.LiquidStack's Liquid-to-Liquid Coolant Distribution Unit (CDU)
13.1.16.Boyd - Cold Plate and CDUs (1/2)
13.1.17.Boyd - Cold Plate and CDUs (2/2)
13.1.18.CDU - Cooling Capacity Evaluation
13.1.19.Revenue Forecast of CDU: 2022-2036
13.2.Main Pump
13.2.1.Overview
13.2.2.Redundancy Analysis
13.3.Filtering
13.3.1.Overview
13.3.2.Filters - Schematic Drawing
13.3.3.Filters
13.4.Sensors
13.4.1.Overview of Sensors
13.4.2.Leakage Detection Sensors - Overview
13.4.3.Leakage Detection Sensors on Server Nodes (1)
13.4.4.Leakage Detection Sensors on Server Nodes (2)
13.5.Quick Disconnects (QDs)
13.5.1.Overview of QDs
13.5.2.Wetted materials
13.5.3.Quick disconnects - costs and operating requirements
13.6.Heat Reuse
13.6.1.Overview of the Heat Reuse in Data Center Cooling
13.6.2.Use Case: Amazon Data Center Heat Reuse
13.6.3.Facebook (Now Meta) Data Center Heat Reuse
13.6.4.Tencent - Tianjin Data Center Heat For Municipal Heating
13.6.5.Return on Investment of Heat Reuse
13.6.6.More Examples of Heat Reuse
13.6.7.More Examples of Heat Reuse
14.HEAT TRANSFER - THERMAL INTERFACE MATERIALS (TIMS)
14.1.TIM2 Overview
14.1.1.Thermal Interface Materials in Data Centers
14.1.2.Common Types of TIMs in Data Centers - Line Card Level
14.1.3.TIMs in Data Centers - Line Card Level - Transceivers
14.1.4.TIMs in Server Boards
14.1.5.Server Board Layout
14.1.6.TIMs for Data Center - Server Boards, Switches and Routers
14.1.7.Data Center Switch Players
14.1.8.How TIMs are Used in Data Center Switches - FS N8560-32C 32x 100GbE Switch
14.1.9.WS-SUP720 Supervisor 720 Module
14.1.10.Ubiquiti UniFi USW-Leaf Switch
14.1.11.FS S5850-48S6Q 48x 10GbE and 6x 40GbE Switch
14.1.12.Cisco Nexus 7700 Supervisor 2E module
14.1.13.TIMs for Power Supply Converters (1): AC-DC and DC-DC
14.1.14.Data Center Power Supply System
14.1.15.TIMs for Data Center Power Supplies (2)
14.1.16.TIMs for Data Center Power Supplies (3)
14.1.17.TIMs in Data Center Power Supplies (4)
14.1.18.How TIMs are Used in Data Center Power Supplies (5)
14.1.19.How TIMs are Used in data center power supply (6)
14.1.20.TIMs for Data Centers - Power Supply Converters
14.1.21.Differences Between TIM Forms - (1)
14.1.22.Differences Between TIM Forms - (2)
14.1.23.Novel material - Laminar Metal Form with High Softness (1)
14.1.24.Novel material - Laminar Metal Form with High Softness (2)
14.1.25.TIM Trends in Data Centers
14.1.26.Estimating the TIM Areas in Server Boards
14.1.27.Servers Number Forecast: 2021-2035
14.1.28.TIM Requirement in Immersion Cooling
14.1.29.Common TIMs for Immersion Cooling
14.1.30.Area of TIM per Switch
14.1.31.TIM Area for Leaf and Spine Switch
14.1.32.Yearly TIM Area for Leaf and Spine Switch Forecast: 2026-2036
14.1.33.TIM Consumption in Data Center Power Supplies
14.1.34.Forecast summary - Yearly TIM Area (m2) Forecast for Different Data Center Components: 2026-2036
14.1.35.Forecast summary - Yearly TIM Revenue (US$ millions) Forecast for Data Center Components: 2026-2036
14.2.TIM1 and TIM1.5 in advanced semiconductor packaging
14.2.1.Thermal interface material inside the packaging - TIM1
14.2.2.Potential TIM1 options in the future
14.2.3.TIM1 Considerations
14.2.4.Indium foil TIM1 - issues with multiple reflow process
14.2.5.Traditional and mature product - Shin-Estu X-23 series for BGA
14.2.6.Thermal Gel - Shin-Etsu MicroSi
14.2.7.TIM1 and TIM1.5 market size forecast for ASP: 2026-2036
15.FORECAST SUMMARY
15.1.Yearly Revenue Forecast By Cooling Method: 2022-2036
15.2.Yearly Revenue Forecast By Cooling Method - Data Table: 2022-2036
15.3.Summary of Yearly Revenue Forecast for Liquid Cooling: 2022-2036
15.4.Summary of Yearly Revenue Forecast for Liquid Cooling Data: 2022-2036
15.5.Summary of Yearly Volume Forecast for Liquid Cooling: 2022-2036
15.6.Summary of Yearly Volume Forecast for Cooling - Data Table: 2022-2036
16.PROFILES
16.1.Accelsius — Two-Phase Direct-to-Chip Cooling
16.2.Amazon AWS Data Center
16.3.Arieca
16.4.Arieca
16.5.Asperitas Immersed Computing
16.6.Calyos: Data Center Applications
16.7.Engineered Fluids
16.8.Green Revolution Cooling (GRC)
16.9.Henkel: microTIM and data centers
16.10.LiquidCool Solutions — Chassis-Based Immersion Cooling
16.11.LiSAT
16.12.LiSAT
16.13.Nano-Join
16.14.NeoFan
16.15.Neurok Thermocon Inc
16.16.Parker Lord: Dispensable Gap Fillers
16.17.Resonac Holdings
16.18.Sumitomo Chemical Co., Ltd
16.19.Taybo (Shanghai) Environmental Technology Co., Ltd
16.20.Tyson
16.21.Vertiv Holdings - Data Center Liquid Cooling
16.22.ZutaCore
 

About IDTechEx reports

What are the qualifications of the people conducting IDTechEx research?

Content produced by IDTechEx is researched and written by our technical analysts, each with a PhD or master's degree in their specialist field, and all of whom are employees. All our analysts are well-connected in their fields, intensively covering their sectors, revealing hard-to-find information you can trust.

How does IDTechEx gather data for its reports?

By directly interviewing and profiling companies across the supply chain. IDTechEx analysts interview companies by engaging directly with senior management and technology development executives across the supply chain, leading to revealing insights that may otherwise be inaccessible.
 
Further, as a global team, we travel extensively to industry events and companies to conduct in-depth, face-to-face interviews. We also engage with industry associations and follow public company filings as secondary sources. We conduct patent analysis and track regulatory changes and incentives. We consistently build on our decades-long research of emerging technologies.
 
We assess emerging technologies against existing solutions, evaluate market demand and provide data-driven forecasts based on our models. This provides a clear, unbiased outlook on the future of each technology or industry that we cover.

What is your forecast methodology?

We take into account the following information and data points where relevant to create our forecasts:
  • Historic data, based on our own databases of products, companies' sales data, information from associations, company reports and validation of our prior market figures with companies in the industry.
  • Current and announced manufacturing capacities
  • Company production targets
  • Direct input from companies as we interview them as to their growth expectations, moderated by our analysts
  • Planned or active government incentives and regulations
  • Assessment of the capabilities and price of the technology based on our benchmarking over the forecast period, versus that of competitive solutions
  • Teardown data (e.g. to assess volume of materials used)
  • From a top-down view: the total addressable market
  • Forecasts can be based on an s-curve methodology where appropriate, taking into account the above factors
  • Key assumptions and discussion of what can impact the forecast are covered in the report.

How can I be confident about the quality of work in IDTechEx reports?

Based on our technical analysts and their research methodology, for over 25 years our work has regularly received superb feedback from our global clients. Our research business has grown year-on-year.
 
Recent customer feedback includes:
"It's my first go-to platform"
- Dr. Didi Xu, Head of Foresight - Future Technologies, Freudenberg Technology Innovation
 
"Their expertise allows us to make data-driven, strategic decisions and ensures we remain aligned with the latest trends and opportunities in the market."
- Ralf Hug, Global Head of Product Management & Marketing, Marquardt

What differentiates IDTechEx reports?

Our team of in-house technical analysts immerse themselves in industries over many years, building deep expertise and engaging directly with key industry players to uncover hard-to-find insights. We appraise technologies in the landscape of competitive solutions and then assess their market demand based on voice-of-the-customer feedback, all from an impartial point of view. This approach delivers exceptional value to our customers—providing high-quality independent content while saving customers time, resources, and money.

Why should we pick IDTechEx research over AI research?

A crucial value of IDTechEx research is that it provides information, assessments and forecasts based on interviews with key people in the industry, assessed by technical experts. AI is trained only on content publicly available on the web, which may not be reliable, in depth, nor contain the latest insights based on the experience of those actively involved in a technology or industry, despite the confident prose.

How can I justify the ROI of this report?

Consider the cost of the IDTechEx report versus the time and resources required to gather the same quality of insights yourself. IDTechEx analysts have built up an extensive contact network over many years; we invest in attending key events and interviewing companies around the world; and our analysts are trained in appraising technologies and markets.
 
Each report provides an independent, expert-led technical and market appraisal, giving you access to actionable information immediately, rather than you having to spend months or years on your own market research.

Can I speak to analysts about the report content?

All report purchases include up to 30 minutes of telephone time with an expert analyst who will help you link key findings in the report to the business issues you're addressing. This needs to be used within three months of purchasing the report.

What is the difference between a report and subscription?

A subscription from IDTechEx can include more reports, access to an online information platform with continuously updated information from our analysts, and access to analysts directly.

Before purchasing, I have some questions about the report, can I speak to someone?

Please email research@idtechex.com stating your location and we will quickly respond.

About IDTechEx

Who are IDTechEx's customers?

IDTechEx has served over 35,000 customers globally. These range from large corporations to ambitious start-ups, and from Governments to research centers. Our customers use our work to make informed decisions and save time and resources.

Where is IDTechEx established?

IDTechEx was established in 1999, and is headquartered in Cambridge, UK. Since then, the company has significantly expanded and operates globally, having served customers in over 80 countries. Subsidiary companies are based in the USA, Germany and Japan.

Questions about purchasing a report

How do I pay?

In most locations reports can be purchased by credit card, or else by direct bank payment.

How and when do I receive access to IDTechEx reports?

When paying successfully by credit card, reports can be accessed immediately. For new customers, when paying by bank transfer, reports will usually be released when the payment is received. Report access will be notified by email.

How do I assign additional users to the report?

Users can be assigned in the report ordering process, or at a later time by email.

Can I speak to someone about purchasing a report?

Please email research@idtechex.com stating your location and we will quickly respond.
 

Ordering Information

Thermal Management For Data Centers 2026-2036: Technologies, Markets, and Opportunities

£$¥
Electronic (1-5 users)
£5,650.00
Electronic (6-10 users)
£8,050.00
Electronic and 1 Hardcopy (1-5 users)
£6,450.00
Electronic and 1 Hardcopy (6-10 users)
£8,850.00
Electronic (1-5 users)
€6,400.00
Electronic (6-10 users)
€9,200.00
Electronic and 1 Hardcopy (1-5 users)
€7,400.00
Electronic and 1 Hardcopy (6-10 users)
€10,200.00
Electronic (1-5 users)
$7,500.00
Electronic (6-10 users)
$10,750.00
Electronic and 1 Hardcopy (1-5 users)
$8,600.00
Electronic and 1 Hardcopy (6-10 users)
$11,850.00
Electronic (1-5 users)
元54,000.00
Electronic (6-10 users)
元76,000.00
Electronic and 1 Hardcopy (1-5 users)
元61,000.00
Electronic and 1 Hardcopy (6-10 users)
元84,000.00
Electronic (1-5 users)
¥990,000
Electronic (6-10 users)
¥1,406,000
Electronic and 1 Hardcopy (1-5 users)
¥1,140,000
Electronic and 1 Hardcopy (6-10 users)
¥1,556,000
Electronic (1-5 users)
₩10,500,000
Electronic (6-10 users)
₩15,000,000
Electronic and 1 Hardcopy (1-5 users)
₩12,100,000
Electronic and 1 Hardcopy (6-10 users)
₩16,600,000
Click here to enquire about additional licenses.
If you are a reseller/distributor please contact us before ordering.
お問合せ、見積および請求書が必要な方はm.murakoshi@idtechex.com までご連絡ください。
The market size of data center liquid cooling components will exceed US$40 billion by 2036.

Report Statistics

Slides 364
Forecasts to 2036
Published Oct 2025
 

Preview Content

pdf Document Sample pages
 

Customer Testimonial

quote graphic
"The resources provided by IDTechEx, such as their insightful reports and analysis, engaging webinars, and knowledgeable analysts, serve as valuable tools and information sources... Their expertise allows us to make data-driven, strategic decisions and ensures we remain aligned with the latest trends and opportunities in the market."
Global Head of Product Management and Marketing
Marquardt GmbH
 
 
 
ISBN: 9781835701515

Subscription Enquiry