Innovations in Data Center Power and Cooling Solutions

Circular thinking: A new imperative for data centre cooling

In this article for DCNN, Todd Scheving, Business Development Director – Global Data Center at A-Gas, outlines why a circular approach to refrigerant management is becoming increasingly important as data centre operators balance cooling requirements with sustainability and supply considerations: The AI revolution has sparked heated debate about data centre cooling. Refrigerant decisions are emerging earlier in the value chain, spurring pressing procurement and sustainability conversations. This is for good reason: the choices operators make today will shape emission footprints for the next decade. Maintaining a circular approach to data centre cooling is more important than ever. The industry is feeling the effects. Firms are engaging with refrigerant suppliers far earlier in the planning process, integrating their sustainability teams. Questions about supply security and reclaim options are now a fixture in project conversations. In short, sustainability targets are turning refrigerants into strategic assets that must be managed. This reclassification from commodity to asset matters. Managing refrigerants holistically reveals hidden problems. Often, the solutions involve maintaining a circular approach to cooling: recover, reclaim, and destroy only what cannot be restored to spec. Reclaimed refrigerants have a significantly lower carbon footprint than virgin alternatives because the molecules already exist. Rather than venting (which is illegal across North America and the European Union) or leaving them in storage, the goal is to keep refrigerants in circulation. Circular thinking is the environmentally responsible path and, increasingly, the economically rational one. End-of-life handling is responsible for much of the industry's emission problem. Unfortunately, despite it being illegal, venting is often a by-product of strict time constraints during decommissioning or servicing. The solution is to engage dedicated, high-speed refrigerant recovery teams to recover refrigerants and deliver them to reclaimers for reprocessing for future reuse. Recovery is the future of cooling. There are enough HFCs (hydrofluorocarbons) already installed today to meet industry needs for the foreseeable future, provided they are managed responsibly. The infrastructure exists; operators must now partner with recovery teams to treat refrigerants like the strategic assets they were always meant to be. For more from A-Gas, click here.

STULZ introduces fourth-generation cooling units

STULZ, a manufacturer of mission-critical air conditioning technology, has introduced the fourth generation of its TelAir and WallAir cooling series for edge, 5G, and critical infrastructure applications. The TelAir 4 and WallAir 4 units use R454C refrigerant, integrated free cooling, and an EN 378-compliant safety architecture. They are designed for edge data centres, telecommunications containers, shelters, and radio stations. The units are available with two installation concepts: TelAir 4 is designed for indoor installation, whilst WallAir 4 can be mounted externally on a container wall. Anika Do, Global Product Manager at STULZ, explains that, "Both are available in two standard enclosure sizes and four cooling capacity classes, ranging from 6–17kW." The units are designed to address increasing thermal densities and the requirements of the amended European F-Gas Regulation (EU) 2024/573. Free cooling cuts energy use STULZ says the units can reduce operating costs by up to 80% when using combined free cooling and mixed-mode operation. The electronically commutated (EC) fans also comply with the requirements of the upcoming ErP 2027 Ecodesign Directive. Both models operate from -20°C to +54°C, while an optional winter kit can extend operation down to -40°C. Customers can choose between on/off systems with a thermostatic expansion valve, or continuously modulating EC inverter compressors paired with an electronic expansion valve. Both configurations have hermetically sealed refrigeration circuits. The units also feature a multi-stage safety architecture designed for A2L refrigerants such as R454C. In the event of a refrigerant leak, the evaporator fan can increase to maximum speed to dilute and extract refrigerant gases. A two-stage sensor system activates maximum fan speed and shuts down other power consumers at 10% of the lower flammability limit (LFL). At 20% LFL, the unit is fully disconnected from the power supply. Meanwhile, an enclosed IP54 control cabinet is designed to eliminate potential ignition sources. TelAir 4 supports downflow and displacement airflow concepts, with optional adjustable outlet grilles for horizontal or vertical air distribution. WallAir 4 uses displacement cooling to provide direct cold air stratification within the room. Additionally, TelAir 4 specifically can be installed within a wall, providing protection against weather and vandalism, whilst also reducing noise emissions for use in residential and mixed-use areas. Both units use the E² BASIC controller, which includes an ethernet interface, Modbus, and multiple inputs and outputs for integration with building management and data centre infrastructure management (DCIM) systems. Password-protected access levels are included, alongside inputs for monitoring fire, smoke, and intrusion alarms. Anika continues, "For the fourth generation of the TelAir and WallAir cooling series, we set out to create two distinct cooling solutions that deliver outstanding flexibility across a wide range of edge, 5G, and critical infrastructure applications. "By combining cutting edge technology with modern design, ease of use, energy efficiency and reliability, we have achieved that goal. The new units are available to order immediately, with STULZ account managers able to provide further information and tailored advice." For more from STULZ, click here.

aquatherm blue powers cooling at Novva’s data centre

At the hyperscale Novva data centre near Salt Lake City, USA, the operator’s cooling strategy is designed for maximum reliability and future orientation. The core of the waterless cooling concept is the PP‑RCT piping system aquatherm blue, which circulates the cooling medium in a closed loop and makes traditional evaporation cooling – and its high water consumption – unnecessary. Corrosion- and incrustation-free pipes ensure stable flow rates over the long term and significantly reduce leakage risks – a key factor for protecting critical IT infrastructure. Thanks to their low weight and welded joints, aquatherm blue could be integrated into the extensive underfloor construction. To learn more about the project at Novva data centre, click here. For more from aquatherm, click here.

AI boom drives global power demand

Artificial intelligence and data centre expansion are reshaping global power markets, creating infrastructure constraints and changing investment priorities, according to global commercial real estate and investment management company JLL. North American data centre capacity is projected to nearly double from 57GW to 109GW by 2030, with hyperscalers expected to spend $200 billion (£148 billion) on capital expenditure in 2026, a 51% increase on 2025. JLL’s global Energy & Infrastructure Advisory platform says securing reliable power infrastructure has consequently become a key constraint for the AI economy. Transmission infrastructure, originally designed around large, centralised power stations, is also facing pressure from the growth of renewable energy sources. This has contributed to grid congestion across major markets in the USA, Europe, and Asia Pacific. Interconnection queues for new renewable projects now extend to four years or more in some regions, while some areas have paused new connections entirely. The impact varies between markets. In the USA, interconnection reform and exposure to merchant power are influencing deal structures. European regulatory frameworks are changing at different rates between member states, whilst data centre construction is outpacing grid planning in several Asia Pacific markets. "We've seen a generational shift in power demand as a result of data centres and AI," says Steven Jack, Head of Energy & Infrastructure Advisory, EMEA at JLL. "This was not on the radar until very recently. Utilities that were forecasting modest growth are now grappling with figures nearly double their previous estimates. "For any energy developer, without a grid connection, you don't have a project. For investors, this grid congestion translates directly into risk, but it also creates a scarcity premium for assets that provide or secure grid access. "In a world of geopolitical uncertainty, generating your own power is about energy sovereignty or energy autonomy and it's simply the cheapest way to produce power today." Battery storage gains importance Battery energy storage systems (BESS) are emerging as key infrastructure for managing grid constraints and renewable energy intermittency. "Batteries are a very important component and asset in that balancing act," notes Matt Eastwick, Group Head and Senior Managing Director, Energy & Infrastructure Advisory, US at JLL. "They act as shock absorbers for constrained grids, charging when power is cheap and abundant, then discharging when demand and price are high. "We're in a brave new world. Power demand is rising faster than grids were built to handle. Capital is available, but certainty is harder to find. In this environment, winners will be those who factor grid constraints and power availability into their investment decisions from day one." Grid access challenges are also prompting close partnerships between energy developers and data centre operators. Technology companies are increasingly becoming direct participants in energy markets, including through the acquisition of operating renewable assets to secure power supplies. James Cameron, Head of Energy & Infrastructure, APAC, JLL, explains, "In liberalised markets in Asia Pacific (such as Australia, India, Japan, and the Philippines), status and location of grid connection is the first question for investors and has the largest valuation impact for development assets. "In Australia, where legislation is expected to require that data centre developers ensure new renewable power generation matches additional capacity, we're seeing a range of innovative models, from joint ventures to [the] inclusion of batteries in data centre design to facilitate grid connection. "While the solution will differ depending on circumstances, it is clear we will see many more partnership opportunities and innovative solutions between data centre and energy clients across the region." JLL says power access has increasingly become a factor in the viability and valuation of data centre and energy assets, with investors looking beyond conventional power generation to assets that can provide greater flexibility and certainty in constrained markets. For more from JLL, click here.

When power is a constraint, cooling is an opportunity

In this article for DCNN, ExxonMobil’s Glen Sharkowicz (Director Strategic Market Development, Immersion Cooling) and Betsy Cossette (Immersion Cooling Market Development Manager) assess how immersion cooling could help data centre operators overcome power constraints, improve thermal efficiency, and extract more compute capacity from existing infrastructure: Immersion cooling offers relief from the growing energy bottleneck AI is accelerating demand for one of the industry’s most constrained resources: power. Across the United States, major players are aggressively pursuing the energy needed for ambitious new projects. If accessing enough power is difficult now, forecasts do not show much relief ahead. The International Energy Agency projects that global data centre electricity consumption will more than double by 2030, reaching roughly 945TWh, with the United States accounting for nearly half of the electricity demand growth over that period. When power becomes a bottleneck, timelines slip, expansion costs rise, and access to compute is constrained. In the AI race, those delays can set companies back years. CBRE has reported that power availability can extend data centre construction timelines by two to four years and, in some cases, by as many as six. The logic is simple: when power is the primary constraint, every megawatt counts. As processor power rises and AI deployments scale, operators are re-evaluating long-held assumptions about how data centres should be cooled. Direct-to-chip moved the market forward; AI is now changing that equation. Modern systems are generating more heat in less space, and thermal pressure now extends beyond CPUs and GPUs to memory, power delivery, and other system elements. Heat affects how much supporting infrastructure must be built around the IT load. It influences how much of a site’s total power can be directed to compute rather than cooling overhead. Direct-to-chip cooling has been an important bridge technology for high-density environments. McKinsey notes that compared with air cooling, operators can run the same tasks on the same equipment with a 31% lower energy bill using direct-to-chip cooling. But, as densities continue to rise, the limitations of cooling only certain hot components become more apparent. For one, liquid cooling systems can introduce significant plumbing complexity. In 2024, Uptime Institute data cited by industry observers showed that liquid cooling system failures contributed to 13% of significant outages. Immersion extends the opportunity Instead of targeting only the hottest chips, immersion cooling places the system in a thermally stable liquid environment designed to cool the full assembly more comprehensively, which itself can reduce temperature variation, lower dependence on fans and heavy air handling, and simplify the environment needed to support high-density compute. With immersion becoming more mainstream, the most likely path forward is a hybrid approach in which cooling strategies are tailored to specific business and application needs. What’s more, immersion cooling can reduce TCO compared with direct-to-chip and air cooling. When AI is driving revenue, the ability to shift energy from cooling to compute can have outsized business impact. A recent survey by KPMG found that 55% of hyperscalers and data centre developers would be willing to pay up to 50% more on electricity costs to expand capacity. When power is the limiting factor in data centre growth, the central question becomes how to get the most compute from the power already available. Immersion cooling is an answer. Immersion cooling can offer meaningful savings relative to cold plate cooling in AI-focused environments. If less power must be devoted to cooling overhead, more can be directed to compute. Power is scarce and time is expensive, so these effects can materially change the return profile of an AI infrastructure investment. Reliability is part of the ROI equation Operators need confidence that the environment will be stable, maintainable, and supportable over time. Downtime, service complexity, and unplanned maintenance can quickly erode the value of any savings. Immersion cooling can help address those concerns by creating a more thermally stable operating environment and reducing some of the infrastructure complexity that contributes to service burden. At the 2025 OCP EMEA Summit, findings presented showed that immersion cooling offered the following advantages: • Higher server reliability• Reduced downtime• Lower maintenance requirements The case extends beyond the rack Water use, physical footprint, and local operating impact of data centres are becoming more prominent considerations in siting, permitting, and long-term planning. Immersion cooling can potentially lower water consumption compared to other cooling strategies, alongside improved thermal management and lower cost. A 2025 Nature study found that advanced cooling methods such as cold plates and immersion cooling can reduce blue water consumption by 31–52% in data centres, depending on conditions. Traditional fan-heavy data centre environments can create significant noise pollution. Immersion cooling can help reduce that burden by lowering reliance on fan-driven airflow. In some configurations, immersion systems have been measured below 50dB, which is materially quieter than conventional data centre cooling environments. Immersion cooling can help maximise power to revenue It’s important to consider how much value a cooling strategy can unlock from the power, space, water, and capital already available. Implementing immersion cooling can help address thermal management at the system level and ties that improvement to core business outcomes: lower operating costs, less infrastructure burden, improved reliability, and the potential for more compute capacity within the same power envelope. Immersion cooling offers a way to turn constrained power into scalable growth, and it belongs in today’s infrastructure planning discussion. For organisations exploring how to maximise performance from constrained power, it is a conversation worth having now. For more from ExxonMobil, click here.

KROHNE introduces data centre liquid cooling flowmeters

KROHNE, a German manufacturer of process instrumentation and flow measurement technology, is targeting data centre cooling efficiency with its flow measurement technology, including chilled water and liquid-to-chip applications, as operators manage increasing power and rack densities. The company’s electromagnetic and ultrasonic flowmeters measure liquid flow in cooling water loops, secondary circuits, and heat recovery systems. This data can then be used to monitor coolant distribution, manage pump and valve operation, and assess thermal performance. In liquid-to-chip cooling systems, flow measurement can help operators monitor glycol-water and other coolant circuits supplying individual racks and processors. Accurate flow data can also support automated control systems that adjust pump speeds and valve positions according to cooling requirements. Flow measurement supports heat recovery According to KROHNE, one data centre project using hybrid liquid cooling and waste heat recovery deployed approximately 40 KROHNE OPTIFLUX 4100 electromagnetic flowmeters to measure glycol-water flow through cooling circuits ranging from DN100 to DN250. The measurements are used to monitor heat dissipation and system efficiency, as well as support a thermal management system that captures waste heat for use in district heating networks. KROHNE also supplies flowmeters and temperature sensors for heating circuits, heat exchangers, and district heating connections. Measuring heat and cold transfer can help operators assess system performance and monitor the results of efficiency measures. The company cites other applications where flow and temperature measurement has been used to track hot and chilled water between geothermal probes, heat pumps, and concrete core conditioning systems. In one building-scale installation, the monitoring contributed to reduced natural gas consumption. KROHNE says its flowmeters are designed for long-term operation in demanding industrial environments, with applications including chemical processing and wastewater treatment. The technology can be integrated with existing monitoring and control systems used for data centre energy management.

iON+, ACCURE to streamline BESS data access

iON+, the data and asset performance management platform developed by Conrad Energy, has partnered with battery analytics provider ACCURE Battery Intelligence to simplify data access from battery energy storage system (BESS) assets. Under the partnership, iON+ will provide data services to ACCURE customers through a data bridge that extracts and records high-frequency data from BESS systems. The service will transfer data from BESS assets to the ACCURE platform in near real time. It can also return corrected values, including State of Energy (SoE), which can be used to inform dispatch and trading decisions. Corrected battery data supports trading The partnership is intended to reduce the time required to integrate BESS data, allowing iON+ to transfer high-frequency information from customers’ portfolios into ACCURE’s analytics platform. ACCURE says correcting SoE can make additional energy available for trading and reduce penalties associated with overstating available energy. The approach has been used at Gore Street Capital’s 75MW Dogfish BESS in Texas. ACCURE says analysis of operating data indicated an annual benefit of more than $110,000 (£80,655), equivalent to around a 5% increase against average BESS trading revenues in ERCOT. Corrected values went live at the site in July 2026 without additional hardware. ACCURE’s platform monitors battery performance down to cell level, with the company’s engineers working with asset owners and operators to identify issues such as imbalance. Rhys Kirk, Chief Technology Officer at iON+, says, “We are delighted to have formalised this mutually beneficial partnership with ACCURE. We have been working with ACCURE for some time and know from first-hand experience the breadth and quality of their analytics.” Yannick Gindroz, Head of Partnerships at ACCURE, says, “The iON+ team’s experience in extracting and transferring high-granularity data made them an obvious partner for us. In our industry, visibility is everything, and so we are always looking for ways to show our customers more of what their assets are doing.”

FlexSysAI launches platform to manage DC energy demand

Australian energy technology company FlexSysAI has launched a platform designed to make data centre power demand more flexible by shifting GPU-based AI workloads between locations and times without affecting service. The platform connects electricity market and grid conditions with AI workload balancing, allowing compute to be shifted to locations where electricity is cheaper and more abundant. Non-critical workloads can also be reduced when the grid is under strain and electricity prices are high. FlexSysAI says the approach could help data centre operators connect to the grid sooner, reduce electricity costs, access renewable power when it is available, and receive payments for supporting grid operations. The company was founded by energy specialists, technologists, and entrepreneurs including Victor Feoktistov (pictured above), Angelo Perera, and Sean Senvirtne. The team has developed its demand response technology over several years and secured a retail licence providing customers with direct access to energy markets. Australia provides test market for flexible computing FlexSysAI is initially targeting Australia, where the electricity grid, growing data centre demand, and high penetration of renewable generation provide a testing environment for the platform. The company says it is exploring adoption with multiple data centres in Australia. It is backed by EnergyLab and Sean Senvirtne, and is part of NVIDIA’s Inception programme. The launch comes as governments consider approaches to managing increasing data centre electricity demand. The Australian Energy Market Commission recently recommended a national framework that includes operational flexibility as one potential approach to managing demand. FlexSysAI co-founder Victor Feoktistov says, “Data centres need a strategy for the power crunch that is holding back the sector. Physical grid constraints are beginning to bite and time to power is already a major constraint for operators. "These pressures are likely to worsen over the next two to three years, while regulatory pressure is moving even faster as more jurisdictions look to require flexibility from large energy users. “Operators stay in control, see a live price for flexibility, and choose when to shift workloads while connecting to the grid sooner and getting ahead of mandatory requirements that continue to emerge across key markets.” Angelo Perera, Chief Technology Officer at FlexSysAI, adds, “We are starting in Australia’s National Electricity Market as it has one of the world’s most challenging grids, and its structure and volatility strongly reward smarter, more flexible demand. "This makes Australia an ideal market to prove the technology before deploying it globally as we provide a long-term solution to the accelerating electricity demand problem.” FlexSysAI has formally stated it intends to expand into international markets as data centre electricity demand increases.

Echelon, Trinovium to develop liquid cooling technology

Echelon Data Centres, a developer and operator of hyperscale data centres, has entered into a collaboration with clinical diagnostics company Trinovium, a subsidiary of Trinity Biotech, to develop liquid cooling technologies for AI and high-density computing environments. The collaboration will focus on cooling requirements created by increasing computing and power densities in data centres, including the management and monitoring of coolant used in liquid cooling systems. As operating temperatures and demands increase, factors including corrosion, particulate contamination, fluid degradation, and microbial growth can affect the reliability of cooling systems. The collaboration combines Echelon's experience in designing, developing, and operating hyperscale data centre infrastructure with Trinovium's expertise in high-purity fluid manufacturing and analytical technologies. Under the agreement, the companies will develop and refine liquid cooling technologies based on the requirements of Echelon's hyperscale and AI infrastructure portfolio, which currently includes more than 700MW of capacity in development and more than 1.4GW of secured capacity across Ireland, the UK, Italy, and other markets. Trinovium was established to apply Trinity Biotech's experience in healthcare-grade fluid manufacturing to AI infrastructure. Its initial direct-to-chip cooling formulation is based on high-purity aqueous chemistry, corrosion inhibition, and coolant system protection, alongside consistency and traceability. Monitoring liquid cooling systems Alongside its cooling fluid, Trinovium is developing a fluid health and system intelligence platform using analytical technologies from Trinity Biotech, including connected electrochemical sensing and mass spectrometry. The platform is intended to monitor corrosion and scaling, particulate contamination, and microbial growth and biofilm formation, providing information about the condition of liquid cooling systems. Development is expected to begin shortly, with initial work covering direct-to-chip cooling fluids, thermal management systems, and modular liquid cooling technologies for AI and high-performance computing. Niall Molloy, CEO of Echelon Data Centres, comments, “AI is changing the infrastructure requirements of data centres. As more computing power is concentrated into smaller spaces, managing the heat it generates becomes an increasingly important engineering challenge. “Liquid cooling will be an important part of meeting that challenge, but it is not simply about moving heat more efficiently; the quality, stability, and monitoring of the fluids within those systems will also be important to their long-term reliability.” John Gillard, CEO of Trinity Biotech, adds, “The rapid growth of AI is creating unprecedented demand for advanced cooling technologies capable of supporting increasingly dense and power-hungry computing environments. “By combining Trinovium’s capabilities in high-performance fluid design, precision manufacturing, and advanced analytics with Echelon’s hyperscale data centre expertise, we believe we can accelerate the development of innovative liquid cooling solutions designed specifically for the next generation of AI infrastructure.” For more from Echelon, click here.

Schneider Electric launches Easy UPS 3S Pro

Global energy technology company Schneider Electric has launched the Easy UPS 3S Pro, a three-phase uninterruptible power supply (UPS) designed for critical applications in small and medium-sized data centres, as well as for telecommunications, commercial buildings, healthcare facilities, manufacturing, and transport. Available in 10–40kVA capacities, the UPS supports internal and external battery configurations and is now available across IEC markets, including Europe, the Middle East, and Africa (EMEA). The system provides efficiency of more than 96% in double-conversion mode and up to 99% in ECO mode. It has a compact form factor and integrated breakers intended to simplify installation and commissioning. Thierry Chamayou, Vice President, Cloud & Service Providers, EMEA at Schneider Electric, says, “Today’s businesses require resilient and efficient power protection solutions that are simple to deploy and manage. “Easy UPS 3S Pro has been designed to make business continuity easy by combining reliable power protection, simplified installation, and integrated monitoring capabilities in a highly cost-effective package for customers and channel partners alike.” UPS designed for simplified maintenance The Easy UPS 3S Pro includes an Easy Loop test function, allowing UPS performance to be verified without a load bank. Front, side, and rear access is provided for maintenance. Other features include an enhanced human-machine interface, a wide operating temperature range, embedded dust filters, and conformal coating. The UPS can be operated in parallel for capacity expansion or N+1 redundancy, whilst shared battery configurations can be used across multiple units. An embedded Network Management Card enables remote monitoring and management through Schneider Electric's EcoStruxure IT software, while BACnet support allows integration with building management systems. The Secure Network Management Card is certified to IEC 62443-4-2, providing cybersecurity controls for connected infrastructure. For more from Schneider Electric, click here.