AI servers, driven by Nvidia’s GB200 superchip, have experienced significant growth. The cutting-edge B200 chip, due to its high thermal design power, requires direct-to-chip cooling. Supermicro announced that it had shipped over 2000 direct-liquid-cooled AI server racks by the end of August 2024, and it has expanded its manufacturing capacity to 5000 racks per month. Supermicro reported that it has around 75% of the liquid-cooled AI server rack market, and IDTechEx believes that this production capacity expansion will lead to a surge in liquid-cooled server racks, as well as the number of cold plates. The projections for the number of cold plates for AI servers in IDTechEx’s new report, “Thermal Management for Data Centers 2025-2035: Technologies, Markets, and Opportunities”, align with Supermicro’s latest announcement.

IDTechEx believes that this production capacity expansion is expected to drive a rapid increase in the deployment of liquid-cooled racks across the AI and high-performance computing (HPC) sectors, along with a notable rise in the use of cold plates. Cold plates are integral to direct-liquid-cooling systems, as they are responsible for absorbing and dissipating the significant heat generated by high-performance chips like Nvidia’s B200. IDTechEx’s recent research into thermal management for data centers echoes Supermicro’s projections, highlighting the increasing importance of liquid cooling technologies in managing the heat loads associated with next-generation AI and HPC hardware.

Direct-to-chip (D2C) cooling, also known as cold plate cooling, is a sophisticated cooling method wherein a cold plate is mounted directly onto the chip (GPU or CPU). The plate facilitates the transfer of heat from the chip to a circulating coolant, which then dissipates the heat. D2C cooling can be divided into two main categories: single-phase and two-phase systems, depending on the type of coolant used. Single-phase D2C typically uses a water-glycol mixture, which circulates through the system and transfers heat away from the chip via convection. This type of cooling is efficient for systems with moderate TDPs, as the coolant remains in a liquid state throughout the process. In contrast, two-phase D2C cooling uses a coolant like fluorinated refrigerant, which absorbs heat through a phase change. As the coolant transitions from liquid to gas, it provides significantly greater cooling power, making it well-suited for systems with extremely high TDPs.

The rapid increase in chip TDPs is driving the demand for more advanced cooling solutions. AI and HPC applications, in particular, are pushing the limits of current cooling technologies, as these workloads require chips with significantly higher power consumption to handle complex computations. Nvidia’s GPU roadmap, combined with Intel’s recent announcement of its Falcon Shores GPU — expected to have a TDP of 1,500W — suggests that GPUs and CPUs with TDPs exceeding 1,500W likely become common within the next one to two years. IDTechEx predicts that this ongoing rise in TDP will eventually lead to a shift from single-phase to two-phase D2C cooling systems, as the latter offers superior heat dissipation capabilities required for these high-power chips despite the unclear timeline.

In addition to direct-to-chip cooling, immersion cooling has garnered significant attention as an alternative solution for high-performance systems. Similar to D2C, immersion cooling can be split into two categories: single-phase immersion cooling (1-PIC) and two-phase immersion cooling (2-PIC). However, unlike D2C, immersion cooling involves submerging the entire server into a bath of coolant, which absorbs heat directly from all components. This method is highly effective for cooling densely packed systems with high power requirements, as it eliminates the need for air-based cooling entirely. In single-phase immersion cooling, the coolant remains in a liquid state, similar to single-phase D2C. Two-phase immersion, however, leverages a phase change in the coolant, similar to two-phase D2C, to provide even more efficient heat dissipation.

While immersion cooling offers numerous advantages in terms of thermal efficiency, it comes with several challenges. The process of submerging servers requires extensive retrofitting of existing infrastructure, as well as rigorous material compatibility tests to ensure that the components can withstand prolonged exposure to the coolant. This results in higher upfront costs compared to D2C cooling systems. Additionally, immersion cooling systems, especially two-phase variants, face regulatory challenges. For example, 3M’s Novec products, commonly used as two-phase coolants, are set to be discontinued by the end of 2025. As of now, no PFAS-free or “forever chemical”-free two-phase coolants have been officially announced, adding another layer of complexity for companies considering immersion cooling solutions.

Cooling in data centers occurs at various levels, ranging from chip-level to facility-level cooling. Each level requires different cooling strategies, with technologies like D2C and immersion cooling primarily focusing on chip, server, and rack-level thermal management. At the room and facility levels, air-based cooling remains the most common approach in 2024. Computer room air conditioning (CRAC) units and computer room air handling (CRAH) units are widely used to cool entire server rooms or data center floors. However, the growing heat loads generated by high-performance AI and HPC systems are pushing the limits of air cooling, prompting the adoption of more efficient liquid-based solutions.

One such solution is liquid-to-liquid (L2L) cooling, which is becoming increasingly popular for facility-level heat management. In L2L cooling, a cooling distribution unit (CDU) transfers heat from one liquid loop to another, enhancing heat exchange efficiency. This system is particularly effective for data centers dealing with higher heat loads from AI and HPC workloads. Supermicro’s CEO has predicted that liquid-cooled data centers, which currently represent around 1% of the market, will grow to 30% by 2026. IDTechEx shares this optimistic outlook, noting that while L2L cooling is gaining traction, its widespread adoption will likely be concentrated in newly constructed data centers due to the significant retrofitting required for existing facilities. However, many existing data centers, particularly those using CRAH units, already have facility water systems in place, which can be leveraged for L2L cooling retrofits. These existing water systems are often the starting point for upgrading older data centers to accommodate more advanced liquid cooling technologies.

In conclusion, the rapid rise of AI and HPC applications is driving a fundamental shift in data center cooling strategies. As chips like Nvidia’s B200 and Intel’s Falcon Shores GPU push the limits of thermal design power, direct-to-chip and immersion cooling solutions are becoming critical to managing the heat loads in modern data centers. This unprecedented transition brings significant opportunities to players in the data center cooling value chain, including but not limited to coolant suppliers, server makers, system integrators, cold plate manufacturers, materials suppliers, and cooling equipment (e.g., HVAC) suppliers. More details about the opportunities can be found in the research report.

To learn more about the report, Thermal Management for Data Centers 2025-2035: Technologies, Markets, and Opportunities, including downloadable sample pages, visit IDTechEx.

For the full portfolio of thermal management market research available from IDTechEx, visit IDTechEx Thermal.

Upcoming free-to-attend webinar

Data Center Liquid Cooling — 6-Fold Market Size Expansion in 10 Years

Yulin Wang, senior technology analyst at IDTechEx and author of this article, will be presenting a free-to-attend webinar on the topic on Wednesday 30 October 2024 – Data Center Liquid Cooling – 6-Fold Market Size Expansion in 10 Years.

The webinar will include:

• Air cooling overview
• Direct-to-chip cooling: An exploration of technical barriers and advantages of single- and two-phase D2C cooling
• Immersion cooling: An examination of single-phase and two-phase immersion and their technical and commercial barriers.
• Coolant comparison and regulations: A comparative analysis of coolants used in liquid cooling systems, including costs, regulatory requirements and operating temperature
• Data center cooling value chain and liquid cooling on the data center facility level
• Cost analysis of data center cooling
• Thermal interface materials: An overview of the critical TIMs in efficient heat transfer within cooling systems
• Market size forecast and future opportunities

IDTechEx will be holding exactly the same webinar three times in one day. Click here to register for the session most convenient for you. If you are unable to make the date, IDTechEx says to register anyway to receive the links to the on-demand recording (available for a limited time) and webinar slides as soon as they are available.

The post The rise of AI drives six-fold surge in liquid cooling technology for data centers; IDTechEx webinar Oct. 30 appeared first on FMLink.

The new page offers a comprehensive range of technical materials, including publications, standards, guidelines and research papers, all developed by ASHRAE’s renowned experts. These resources address various aspects of data center design and operation, such as cooling, power distribution, energy efficiency and thermal management. ASHRAE’s goal is to empower professionals with the knowledge needed to optimize data center performance and make informed decisions.

2024-25 ASHRAE President M. Dennis Knight, P.E., BEMP, Fellow Life Member ASHRAE, remarked:

With the rapid growth of digital infrastructure, the demand for cloud computing, AI and big data continues to soar. Efficient cooling systems are essential to cutting operational costs and reducing environmental impact. ASHRAE understands the unique challenges of data center cooling and is proud to offer this platform, providing professionals with the latest industry knowledge and resources in one place.

Key highlights of the Data Center Resources page include:

• ASHRAE Technical Committee 9.9 Datacom Encyclopedia: A collection of essential knowledge about important datacom topics such as facility design considerations, ITE design considerations, environmental guidelines, cooling technologies, energy efficiency in a central hub and more (Annual subscription fee required for access)
• Data Center Standards and Guidance: Foundational guidance such as ANSI/ASHRAE Standard 90.4-2022, Energy Standard for Data Centers and ASHRAE Standard 127-2020, Methods of Testing for Rating Air-Conditioning Units Serving Data Center (DC) and Other Information Technology Equipment, as well as new resources, such as updated data center chapters from the ASHRAE Handbook
• ASHRAE Datacom Series: A staple in the data center industry for nearly two decades; provides comprehensive treatment of data center cooling and related subjects

In addition to technical resources, the page offers links to relevant ASHRAE conferences, events, and professional development opportunities. By connecting professionals with industry experts and fostering knowledge exchange, ASHRAE aims to facilitate continuous learning and professional development within the data center community.

For more information about ASHRAE’s new Data Center Resource Page, visit ASHRAE.

The post Find critical data center cooling and efficiency best practices on ASHRAE’s new hub appeared first on FMLink.

Quality Uptime, headquartered in Bethel, CT, is a leading independent uninterrupted power supply system (UPS) maintenance and UPS battery maintenance company providing customized preventive and emergency service programs for mission-critical data centers and other facilities nationwide. Quality Uptime and its more than 130 employees will become part of ABM’s Mission Critical Solutions group within its Technical Solutions segment. Quality Uptime will initially maintain its brand identity while leveraging ABM’s resources and expertise in electrification infrastructure and microgrids to enhance its services and reach new customers.

With the addition of Quality Uptime, ABM’s Mission Critical Solutions group will offer comprehensive and complementary critical infrastructure solutions for data centers and similar crucial facilities, including electrical testing (NETA), electrical switchgear maintenance, breaker testing, UPS service and maintenance, and battery and power distribution unit service and maintenance. These services complement ABM’s existing robust offerings in microgrid design and construction services, critical cooling, technical project management, facility engineering and cleaning services, resulting in a self-performance model that is an industry leader.

Scott Salmirs, president and chief executive officer of ABM, stated:

The acquisition of Quality Uptime is expected to double ABM’s mission critical-related revenue in the first full year of ownership, driven by the surge in artificial intelligence and related investments in data center infrastructure.

Consistent with our ELEVATE strategy, we believe this investment positions ABM to further participate in the long-term proliferation of data centers, which already represents a multi-billion-dollar market. The addition of Quality Uptime aligns with our vision to drive innovation and deliver comprehensive solutions to our clients, and we are excited to welcome their CEO John Raio and this talented and experienced team to ABM.

John Raio, chief executive officer of Quality Uptime, remarked:

Joining ABM represents an exciting new chapter for us. Our clients and team will benefit from ABM’s scale and expanded suite of services, as well as the combined expertise of both organizations. We are excited about the opportunities this combination creates and are committed to continuing our tradition of excellence and innovation in the data center industry.

ABM is one of the world’s largest providers of integrated facility solutions. A driving force for a cleaner, healthier, and more sustainable world, ABM provides essential services and forward-looking solutions that improve the spaces and places that matter most. From curbside to rooftop, ABM provides comprehensive facility services that includes janitorial, engineering, parking, electrical and lighting, energy solutions, HVAC and mechanical, landscape and turf, and mission-critical solutions. ABM delivers these custom facility solutions to properties across a wide range of industries — from commercial office buildings to universities, airports, hospitals, data centers, manufacturing plants and distribution centers, entertainment venues and more. Founded in 1909, ABM serves over 20,000 clients, with more than 100,000 team members in 350+ offices throughout the United States, United Kingdom and other international locations.

Supporting a national client base across multiple industries, Quality Uptime Services provides uninterrupted power supply system (“UPS”) and battery preventive maintenance through a team of factory-trained field service engineers. With over 9 million square feet of raised floor under contract and industry-leading customer retention, clients confidently engage Quality Uptime to maintain 100% uptime.

The post ABM acquires Quality Uptime for preventive and emergency services for mission-critical facilities nationwide appeared first on FMLink.

Andy Cvengros, managing director, JLL, remarked:

After the pandemic removed the four walls of the workplace, our new world of hybrid work has created an unprecedented need for digital technology. Employees are looking to their companies to create a seamless experience wherever they choose to work, requiring intelligent technology solutions to bridge the gap between the physical and the digital. As this reliance on digital technology increases, the data center industry is experiencing impressive growth and catching the eyes of investors and lenders as a strong, alternative asset class that has been relatively unimpacted by continued economic uncertainty.

With internet usage almost universal, the need for more robust connectivity and innovative data storage solutions continues to drive high investor demand, where the global colocation data center market size is forecasted to grow 11.3% from 2021-2026. The U.S. is seeing strong appetite compared to other regions and accounts for 52% of all data center transactions from 2018 to 2022. Additionally, the U.S. had 1,633 megawatts (mw) of absorption in 2022 for the six U.S. primary markets: Chicago, Dallas-Fort Worth, New Jersey, Northern California, Northern Virginia and Phoenix. These markets also have 1,939 mw under construction.

As the demand for digital IT infrastructure continues to increase, hyperscalers and edge are poised to be the fastest-growing segments of the data center industry. In fact, the hyperscale market is expected to grow 20% from 2021 to 2026, as more major tech companies look to meet surging demand for data processing and storage requirements. With 314 new hyperscale sites globally in development today, that number is expected to surpass 1,000 by the end of 2024 — up from around 500 sites just five years ago. Fifty-three percent of hyperscale capacity is in the U.S., according to Uptime Institute.

The goldrush of AI today is driving growth even further. Following the rapid development of AI tools like ChatGPT, the potential of generative AI to transform industries in 2023 is expected to accelerate demand for computing power in data centers. With AI offering increased data usage and computing efficiency benefits, half of all cloud data centers are expected to use AI by 2025.

Despite this strong demand, however, the skills shortage for high-tech talent will remain a challenge for the data center market’s continued growth. According to the Uptime Institute’s annual data center survey, nearly half of the workforce is approaching retirement within the next decade, and younger workers without the necessary technical skills are unable to fill new roles quickly enough to keep pace with sector growth.

As operators look to aggressively grow and deepen their bench of expert talent to avoid an industry-wide talent shortage, there will be increased focus on mass training programs for high-tech jobs. Government instituted programs will be to key keeping the data center talent pipeline full, including most recently with the CHIPS for America Act that offers grants and loans to help boost the education pipeline across the technology ecosystem, including data centers.

Matt Landek, managing director, Data Centers & Telecom, Work Dynamics, JLL said:

At a time when our increasingly digital world is exploding with demand, data center operators are discovering that younger generations pose an entirely new recruitment challenge. To help futureproof the industry and mitigate the labor pipeline drying up, scaling robust training and recruitment programs will be key in 2023 and beyond to build a stronger, more diverse pipeline of young talent.

The report also explores corporations and governments focusing on ramping up efforts to close the gap between environmental commitments and action in the race to net-zero. The data center industry is facing increased pressure for more transparency of climate mitigation efforts and has been working toward more sustainable operations. Being one of the most energy-intensive building types, data centers collectively account for approximately 2% of the total U.S. electricity use, and, at the end of 2021, global data center energy consumption reached 190.8 terawatt hours — 2.2 times more than 2020.

To incentivize a more transparent and standardized approach toward sustainability, climate legislation momentum and self-regulatory initiatives are driving technology improvements and new sources of power. From the Inflation Reduction Act that extends tax credits for sustainable energy sources to the SEC proposing new climate-related disclosure requirements for public companies. First-mover operators who react swiftly to improve efficiency with both energy and water usage stand to benefit as environmental impacts remain top-of-mind for leading companies and investors.

Find more results from the new Global Data Center Outlook at JLL.

The post Data center demand continues to surge, with workforce and energy challenges on the rise, finds JLL appeared first on FMLink.

With cloud computing and the ongoing acceleration of technological developments, an increasing number of businesses are turning their attention towards larger and more efficient hyperscale facilities to scale and meet their data storage needs.

Industry 4.0 (the fourth Industrial Revolution, focusing on interconnectivity, machine learning and real-time data) is here. And it’s undoubtedly hyperscaling that forms the backbone of this new era.

Yet, hyperscale data centers are up against increasing pressure, especially in a world with growing environmental concerns, soaring rates of energy consumption and sky high energy costs.

Data center managers are now turning to next-gen DCIM (Data Center Infrastructure Management) and implementing renewable energy sources in an effort to reverse the negative and costly effects of data centers.

What are the challenges faced by hyperscale data centers?

Hyperscale data centers are, as their name suggests, big. They benefit from both the advantages of bespoke engineering and economy of scale and therefore are able to outperform regular enterprise data centers.

The volume of data, storage capacity and computing power a hyperscale center can process is also significantly higher than an enterprise data center. Along with the sheer size of hyperscale data centers comes their own set of sizable challenges.

Energy management

In recent years, environmental guidelines to reduce emissions and go carbon neutral by 2030 have been introduced to balance all data centers’ rapidly increasing global share of energy consumption.

With the environmental implications of hyperscale data centers in particular at the forefront of governing bodies’ minds, effective data center management is required to improve energy efficiency

An essential, and power-guzzling, part of data center management is cooling. The vast amount of energy consumed by data centers can result in excessive heat generation which it is vital to control in order to protect systems from overheating and failing.

To overcome this, some hyperscale facilities are considering taking advantage of “free cooling” to save on their cooling costs by migrating their data centers to cooler climates. Others are finding smart DCIM to optimize their cooling and energy usage.

Energy costs

You’ll typically find hyperscale data centers located in areas with access to cheap energy and lots of space, such as rural areas or industrial parks.

All those extra servers mean cooling is a significant challenge, and hyperscale data centers are designed to have high ceilings and lots of open space to allow for efficient cooling, alongside the usual cooling methods. The cost of cooling, as well as running racks upon racks of servers, is still extremely pricey.

Power outages / resiliency

Recovery times for outages are limited to staff’s ability to respond on the ground. Once an alert has been sent, more often than not downtime is already happening, costing valuable time and money.

With outages becoming more and more common in hyperscale data centers, being able to react quickly to downtime — or even prevent it in the first place — is incredibly important.

Sustainability

Climate neutrality and sustainability is the big one. Hyperscale data centers need an accurate system to track sustainability goals and measure global impact.

The best way to achieve sustainability is to work on energy efficiency, which, as we mentioned earlier, is a huge task in itself. Renewable energy sources and better energy monitoring is the way for a more sustainable future. Easier said than done!

Security

The sheer amounts of valuable data held at hyperscale data centers makes them an extremely attractive target to hackers.

A cyberattack could be devastating, resulting in downtime, fines and huge financial losses, which not only affect hyperscale data centers themselves but also the hundreds, thousands or even millions of users.

Sophisticated security systems need to be in place to detect cyberattacks as well as measures to respond to them and minimize disruption.

Space utilization

All data centers waste a vast amount of their valuable energy budget on energy-squandering idle and obsolete servers. Among thousands or even hundreds of thousands of servers, it’s not glaringly obvious when servers are running unused or whether energy ought to be diverted elsewhere.

Without an accurate overview of all assets, it’s impossible to properly manage obsolete and outdated equipment that will be eating into energy budgets.

What are the benefits of an environmentally friendly hyperscale data center?

Quick action needs to be taken to rectify past eco damage and reduce data centers’ carbon footprint, particularly hyperscale data center’s colossal contribution.

The UN’s 2021 IPCC Report has taken the first step and advised critical and drastic measures must be taken against our effect on climate change, leading to operating bodies setting carbo neutral goals by 2030.

As we know from last year, heatwaves across the globe brought some data centers to a standstill when multiple servers failed due to high temperatures.

Environmental monitoring keeps data centers running smoothly and prevents any unexpected outages or irregularities that can cause damaging downtime or data loss.

It’s absolutely crucial to monitor environmental factors like temperature and humidity to enable quick action if equipment malfunctions. The added benefit of environmental monitoring is that it also offers the opportunity to reduce energy wastage through efficient cooling processes.

DCIM is the solution to hyperscale data centers’ challenges

Although hyperscale data centers are more efficient and emission sensitive than traditional data centers, they are still undeniably absolutely massive… and anything that big uses a lot of resources.

The size of the physical space and computing power within places immense demands on power for operating, processing and cooling. With the help of DCIM to monitor and manage the performance of their computing resources, hyperscale data centers are evolving to be more efficient and emission sensitive.

While maintaining the highest standards of performance possible, hyperscale data centers can remain compliant with industry regulations through a closely monitored data center environment allowing for necessary adjustments to be made. In this way, you can be sure of uninterrupted uptime and data security.

With enormous facilities and endless rows of servers, DCIM:

• Optimizes ever-increasing demands on power
• Enhances cooling and other data center elements to maintain a consistent level of service delivery
• Ensures that all components within such a huge facility are working seamlessly together for maximum efficiency
• Reduces those sky-high costs and increases profits
• Keeps hyperscale data centers running smoothly
• Alerts operators when a threshold has been reached
• Ensures maximum uptime
• Enables improved visibility into the performance of each and every individual component and system
• Offers detailed analytics and reporting capabilities
• Allows proactive monitoring of any potential issues and corrective action being taken before they become critical
• Provides essential insights into how the infrastructure is being used
• Allows for more effective planning and utilization of resources.

And if you want to truly transform, future-proof and optimize your hyperscale data center to the max, next-gen DCIM by Assetspire is a way forward. It will help you work smarter, manage vital components, save energy and, most beneficially, save money! Assetspire’s DCIM software represents a new opportunity to effectively maximize control and visibility of your critical hyperscale data center space.

The post How can DCIM optimize hyperscale data centers for facilities managers? appeared first on FMLink.

Posted by Janet Stroud

Data center construction, in particular, is expected to grow at a high rate through 2028 and beyond, accelerating the demand for cooling solutions with an emphasis on energy efficiency and sustainability. The combined capabilities of Daikin and Alliance Air address these industry requirements, including chiller-to-computer room air-handler (CRAH) systems that help mitigate a data center’s environmental impact. These systems provide an ideal balance of energy and water conservation.

Jeff Drees, president and CEO of Daikin Applied, stated:

Alliance Air has differentiated itself for its manufacturing acumen, creative designs, and nimble work and delivery. While this acquisition does, indeed, uniquely diversify and strengthen our portfolio, the true advantage is to our customers, especially those with hyper-scale and colocation data centers. The integration with the Alliance Air team will be rapid and seamless so we can bring these benefits to our customers quickly.

Alliance Air’s precision and speed are enabled by its total wrap-around services that deliver comprehensive customer support — from engineering assistance to design, testing and field services. In addition to data center cooling, the merged operations will serve an array of applications that require custom designs, such as hospitals, manufacturing facilities and labs.

Luis Plascencia, who will continue as president and general manager of Alliance Air Products, remarked:

Our customers need cost-effective, energy-efficient solutions that can evolve with their individual needs and larger industry trends. As the number one air-conditioning company in the world, Daikin has the experience and know-how that will allow us to collectively scale with our customers. We’re bringing together exceptional talent, technology and services that truly offer it all — flexibility, reliability, efficiency and sustainability.

Customers can expect enhanced agility to better serve their design and delivery needs, coupled with 360-degree service and a local approach backed by Daikin’s global resources and recognition, says the company.

Visit Alliance Air Products to learn more about the company and its equipment and services. For additional information on Daikin Applied, and its full range of commercial and industrial HVAC equipment and solutions, visit the company’s website. Also, follow Daikin Applied on LinkedIn for the latest on HVAC technology, services and trends.

The post Daikin Applied acquires custom air-handler manufacturer Alliance Air Products to provide end-to-end mission-critical HVAC solutions appeared first on FMLink.

Andy Lawrence, executive director of Research, Uptime Institute Intelligence, stated:

The global digital infrastructure sector continues to enjoy strong growth and expansion, despite the many obstacles operators are facing today. We’ve seen the industry invest in increased resiliency and reliability, but there’s still work to be done when it comes to improving efficiency, environmental sustainability, outage prevention, staffing pipelines and more.

Uptime’s annual Global Data Center Survey is considered the largest and most comprehensive in the digital infrastructure industry. It provides detailed insights into the digital critical infrastructure landscape and a sense of its future trajectory.

Key findings from the 2022 report include:

• Many data center operators are unprepared for mounting sustainability requirements and regulations – Most respondents say they report on overall data center power use and PUE, but many still are not tracking critical environmental metrics. Although 63% of operators believe authorities in their region will require them to publicly report environmental data in the next five years, just 37% collect and report carbon emissions data (a slight increase over 33% in 2021) and only 39% currently report their water use (a 12% drop compared to 2021). New laws, standards, and requirements will force operators to address these gaps and establish more stringent sustainability tracking and reporting practices in the coming years.

• PUE progress is in stasis for now, and future efficiency gains must focus on IT power – The average annual power usage effectiveness (PUE) reported in 2022 was 1.55. This represents a slight improvement over the 2021 average of 1.57, which is consistent with the trend of marginal PUE gains Uptime has observed annually since 2014. Going forward, achieving substantial data center efficiency improvements will require a new focus on IT efficiency, along with metrics to track and report progress.

• More operators are investing to bolster data center resiliency – Data center owners and operators are making significant investments in the resiliency of their physical infrastructure, with about 40% of respondents reporting increased redundancy levels at their primary data centers in the past three to five years. Power and cooling systems have received similar attention, with a third of operators upgrading either or both.
• Outages are becoming more expensive and are still far too frequent – The share of all outages costing operators over $1 million has reached 25%, a significant increase from 15% in 2021. In 2022, 60% of operators reported experiencing an outage (regardless of severity) in the past three years — down from 69% in 2021 and 78% in 2020. Although the data indicates a trend toward improved outage rates, the frequency of outages is still much too high, and with more than two-thirds now costing operators upwards of $100,000, the consequences are getting worse.

• Operators’ confidence in public cloud is on the rise, despite ongoing outage risks – As the perception of improved visibility into cloud operational resiliency grows, organizations are more likely to trust the cloud for mission-critical workloads. In 2022, just 63% of operators are not placing mission-critical workloads into a public cloud, a substantial drop from almost 75% in 2019. That trust might be misplaced, given that more than one-third of respondents report that public cloud availability zone outages (which are relativity common) would cause significant performance issues.
• Data center equipment vendors optimistic despite demand pressures and lingering supply chain problems – Three-quarters of vendors project year-over-year revenue growth in 2022 despite reporting dampened revenues due to persistent Covid-induced supply chain issues. Nearly half of respondents involved with data center construction have suffered significant delays (or other events) in their supply chains, while one-third have experienced moderate issues.
• Problems attracting and retaining qualified staff are worsening – Over half (53%) of data center operators report difficulty finding qualified employees in 2022 — up from 47% in 2021 and 38% in 2018. And 42% of respondents report issues with staff being hired away (in most cases to data center competitors) – a massive increase over just 17% in 2018, which demonstrates the growing challenge of employee retention throughout the sector.

Uptime’s 2022 Global Data Center Survey also includes findings on industry attitudes toward nuclear energy, server refresh rates, rack density trends and much more. Uptime conducts its annual survey online and by email. This year’s study took place in H1 2022 and includes responses from approximately 800 data center owners and operators responsible for managing infrastructure at the world’s largest IT organizations. It also includes insights from 700 data center suppliers, designers and advisors worldwide.

Download the complete Uptime Institute Global Data Center Survey 2022 report here, and register for the webinar covering its key trends and takeaways on September 28th at 11:00 a.m. ET.

For over 25 years, Uptime Institute has established benchmarks for data center performance, resilience, sustainability and efficiency, which provide customers assurance that their digital infrastructure can perform across a wide array of operating conditions at a level consistent with their business needs. Uptime’s Tier Standard is the IT industry’s widely adopted global standard for the design, construction and operation of data centers – the backbone of the digital economy. With its Tier Standard and Certifications, Management & Operations reviews, SCIRA-FSI financial sector risk assessment, broad range of additional risk and performance assessments, Intelligence research services, and accredited training courses completed by over 10,000 data center professionals, Uptime has helped thousands of companies in over 100 countries to optimize critical IT assets while managing costs, resources and efficiency.

The post Uptime Institute’s 2022 Global Data Center Survey reveals gains in resilience and reliability, but challenges with sustainability and outages appeared first on FMLink.

The launch of this comprehensive executive advisory series is the latest step in Uptime’s longstanding and expanding program to inform, guide and support sustainability efforts within the sector — and it comes at a critical time for digital infrastructure operators, says the group. Governments worldwide are beginning to establish new regulations and promulgate new policies to discourage unsustainable data center growth, drive procurement of low-carbon data center services, and move toward net-zero carbon emissions goals.

However, research by Uptime clearly shows that most organizations have not put in place many of the strategies, processes and controls they will need to meet all stakeholder expectations and legislator demands. According to Uptime’s 2021 Global Data Center Survey, most organizations tend to only compile and report on power-related sustainability metrics, while far too few are tracking other key elements such as water use (just 51%), greenhouse gas (GHG) emissions (just 33%), and IT efficiency (just 25%).

The first report in the series, Creating a Sustainability Strategy, defines the key elements to include in a sustainability strategy, the actions necessary for a successful implementation, and the processes required to measure progress against goals and objectives.

The complete series of six reports takes managers through the key areas that must be addressed in an environmental sustainability strategy, ranging from creating the strategy, reducing energy consumption, buying renewable energy, tracking and reporting carbon emissions, managing water consumption, and equipment reuse and recycling. The advisory series also provides guidance on compliance with and the adoption of critical standards and legislative initiatives, many of which are both confused and confusing.

Andy Lawrence, founding member and executive director, Uptime Intelligence, stated:

As sustainability requirements become more demanding, digital infrastructure operators must be prepared with a comprehensive, actionable sustainability strategy.

Jay Dietrich, research director of Sustainability, Uptime Intelligence, and lead author of the report series, added:

This advisory series is a “how-to” guide to implementing effective environmental sustainability initiatives that span all facilities and IT operations and address the needs of all stakeholders inside and outside the organization.

Uptime has been advising operators of digital infrastructure on sustainability and efficiency since 2007, the year of the first Uptime Institute Green Data Center forum. Through its Sustainability Consulting Services and related offerings, Uptime advises some of the world’s largest digital infrastructure owners and operators, many vendors and equipment manufacturers, regulators and policymakers to help the sector design, build and operate digital infrastructure sustainably — without compromising resiliency.

Upcoming reports in the series:

• Glossary of Digital Infrastructure Sustainability — This document explains the key terms used by those defining, regulating, and applying digital infrastructure sustainability strategies.
• Three Sustainability Elements: Water, the Circular Economy and Siting — This report discusses three important elements of the sustainability strategy: water use; siting, including design and certification; and reuse, disposal, and recycling. Addressing these elements can significantly reduce the environmental impact of digital infrastructure.
• Navigating Regulations and Standards — Critical digital infrastructure is subject to an expanding set of regulations, directives and standards, with varying levels of maturity and acceptance. Most are voluntary, but more are becoming mandatory.
• IT Efficiency: The Critical Core of Digital Sustainability — A digital sustainability strategy should incorporate both the facilities and IT operations, even for colocation operators. This report covers strategies, software tools and metrics that can help drive up IT efficiency.
• Tackling Greenhouse Gases — Operators of digital infrastructure must have a greenhouse gas emissions reduction goal that takes into account Scope 1, 2 and 3 emissions — and they must report these reductions in accordance with agreed policy.
• Reducing the Energy Footprint — The first objective of a sustainability plan is to minimize energy use through efficiency measures. Further benefits will be realized by replacing electricity from nonrenewable sources with renewably generated energy.

Upcoming digital infrastructure sustainability webinars

Uptime will be hosting a webinar series to deliver in-depth insights and to facilitate discussions following the release of each report. Scheduled for Tuesday, May 10 at 9:00 a.m. PDT, the first webinar will cover the Creating a Sustainability Strategy report. The second webinar will take place on Tuesday, June 7 at 9:00 a.m. PDT and will explore both the Tackling Greenhouse Gases and Reducing the Energy Footprint reports. The webinar schedule is available online.

Uptime Institute Network Members, touted as the world’s largest group of data center owners and operators, will have exclusive access to the complete contents of each installment of the report series upon release, while non-members will have access to executive summary copies.

The Executive Summary of the first report is available online to download, as will be each subsequent report.

Learn more about Uptime Institute Network Membership and request a free guest trial on the group’s website.

For over 25 years, Uptime Institute has served as a standard for data center reliability, sustainability, and efficiency, providing customers assurance that their digital infrastructure can perform at a level that is consistent with their business needs across a wide array of operating conditions. With its data center Tier Standard & Certifications (for the proper design, construction, and operation of data centers), Management & Operations reviews, broad range of related risk and performance assessments, and accredited educational curriculum completed by over 10,000 data center professionals, New York-headquartered Uptime Institute has helped thousands of companies in over 100 countries to optimize critical IT assets while managing costs, resources, and efficiency.

The post Uptime Institute launches a strategic and practical guide for data center sustainability appeared first on FMLink.

Vertiv CEO Rob Johnson predicted:

As we move into 2022, data center operators and suppliers will actively pursue strategies that can make a real difference in addressing the climate crisis. For our part, we continue to focus on energy efficiency across our portfolio, as well as alternative and renewable energy technologies and zero-carbon energy sources, to prioritize water-free cooling technologies, and to partner with research leaders and our customers to focus on impactful sustainability efforts.

The actions data center decision-makers take on these fronts will have a profound impact on the digital economy in 2022 and beyond, says Vertiv. The urgency of these challenges is reflected in the 2022 trends identified by Vertiv’s experts. Those trends are highlighted below.

Data centers tackle sustainability and the climate crisis

The data center industry has taken steps toward more climate-friendly practices in recent years, but operators will join the climate effort more purposefully in 2022. On the operational front, Vertiv experts predict some organizations will embrace sustainable energy strategies that utilize a digital solution that matches energy use with 100% renewable energy and ultimately operates on 24/7 sustainable energy. Such hybrid distributed energy systems can provide both AC and DC power, which adds options to improve efficiencies and eventually allows data centers to operate carbon-free.

Fuel cells, renewable assets, and long-duration energy storage systems, including battery energy storage systems (BESS) and lithium-ion batteries*, all will play a vital role in providing sustainable, resilient, and reliable outcomes. Thermal systems that use zero water are in demand, and we will see refrigerants with high global warming potential (GWP) phased down in favor of low-GWP refrigerants.

More immediately, extreme weather events related to climate change will influence decisions around where and how to build new data centers and telecommunications networks. Other factors, including the reliability and affordability of the grid, regional temperatures, availability of water and renewable and locally generated sustainable energy, and regulations that ration utility power and limit the amount of power afforded to data centers, play a part in the decision-making as well.

These extreme weather events will drive more robust infrastructure systems across the Information and Communications Technology (ICT) space, which will need to be carefully aligned with sustainability goals. In 2022, data center and telecom operators will wrestle with these issues — and ever-present latency questions — and will drive a need for solutions that can address all of these challenges.

*Important note on lithium-ion batteries: Vertiv experts expect the lithium battery recycling infrastructure (PDF file) to expand in 2022 and eliminate one of the few remaining barriers to widespread adoption of lithium-ion batteries in the data center.

Artificial intelligence (AI) gets real

As today’s networks get more complex and more distributed and the augmented and virtual reality demands of the metaverse become more prominent, the need for real-time computing and decision-making becomes more critical. This real-time need is sensitive to latencies, and under the increasingly common hybrid model of enterprise, public and private clouds, colocation, and edge, full-time manual management is impractical, if not impossible. Artificial Intelligence (AI) and machine learning will be critical to optimizing the performance of these networks.

It will take focus and time to collect the right data, build the right models, and train the network platform to make the right decisions. However, the programming tools have become simplified enough that data scientists are able to point computing resources at a problem without having to be experts in programming or hardware. The availability of AI hardware from established vendors, cloud options for the same, a simplified toolchain, and an educational focus on data science has put AI in play for even smaller companies. It all adds up to accelerated AI adoption in 2022.

As with every technological advance, there are ripple effects. The increase in AI will unavoidably increase computing and heat densities and, by extension, accelerate the adoption of liquid cooling. Among other challenges: lowering the barrier to entry places a premium on choosing the right vendors, platforms and systems to trust.

The post-pandemic data center takes shape

Some 2.9 gigawatts worth of new data center construction is under way globally — up from 1.6 gigawatts in 2020 (Cushman & Wakefield). Those data centers will be the first built specifically to meet the needs of a post-Covid world. More activity will be focused at the edge, where VMware projects a dramatic shift in workload distribution — from 5% currently to 30% over the next five years.

Availability will remain the top priority, even at the edge, but lower latency is a rising need to support healthy buildings, smart cities, distributed energy resources, and 5G. 2022 will see increased investment in the edge to support this new normal (remote work, increased reliance on ecommerce and telehealth, video streaming) and the continuing rollout of 5G.

Drive toward integration

Various data center equipment providers have been embracing integrated systems that allow for modular capacity additions for years, with integrated racks and rows among today’s most popular data center offerings. In 2022, we’ll see the next step in integration as data centers work with providers to better integrate larger systems — all components of the power infrastructure, for example — and deliver seamless interoperability.

The benefits of integration as a concept are well known — reduced construction and deployment costs, flexible capacity management — and applying the same approach across larger systems delivers speed. Rack-based power solutions are early accelerators of integration momentum.

For more information on the 2022 Data Center Trends: Data Centers Tackle Sustainability and the Climate Crisis report and the complete Vertiv portfolio of solutions for data center and communication networks, visit the company’s website. Columbus, Ohio-based Vertiv offers a portfolio of power, cooling and IT infrastructure solutions and services in more than 130 countries.

The post Climate resiliency and sustainability top the 2022 data center trends to watch, says Vertiv appeared first on FMLink.

Joseph Goffman, principal deputy assistant administrator for EPA’s Office of Air and Radiation, stated:

The data center computing sector is growing rapidly. Reducing the sector’s annual 70 billion-plus kWh use is essential to fighting the climate crisis. The Energy Star updates EPA is announcing today will lead the industry towards greater innovation and deep carbon savings.

Ten years ago, data center energy use was predicted to grow exponentially as digital computing expanded. However, gains in energy efficiency — both at the network hardware and storage level, as well as at the building level — have mostly offset this growth, says the EPA. Between 2010 and 2018, data center computing grew by 500 percent, while data center energy use only grew by six percent. Energy Star played a significant role in this progress, but much more is required as digital computing data needs continue to grow rapidly.

EPA’s Energy Star program has been a critical player in the drive to improve the energy efficiency of data centers. Data center equipment that earns the Energy Star label is independently certified to meet strict efficiency specifications set by the EPA. For example, labeled computer servers are on average 30% more efficient than non-certified products. In addition to servers, eligible products include uninterruptible power supplies (UPSs), data center storage, and large network equipment like switches and routers.

Earlier this year, EPA released an updated Energy Star specification for data center storage products, adding active-mode requirements and requiring more efficient power supplies. The program also added new how-to content and case studies to its website.

Energy Star also provides data center owners and operators with a 1-100 ENERGY STAR score that rates the energy efficiency of their entire facility compared to similar facilities nationwide, as well as Energy Star certification to those that outperform their peers.

More than 190 data centers representing nearly 30 million square feet of floor space have earned EPA’s Energy Star certification. The Energy Star score for data centers was first launched in 2010 and is based on 2008 survey data. Since then, the number of data centers has grown substantially, and much work has been done to improve their energy efficiency.

This fall, to ensure that the Energy Star score continues to give data center owners and operators an up-to-date picture of their performance, EPA will partner with The Green Grid, a leading data center industry association, to conduct a survey of data centers’ energy and water use. EPA intends to use the survey results to update its 1-100 Energy Star score for data centers.

Data centers are one of the most energy-intensive building types, consuming 10 to 50 times more energy per square foot than a typical office building. In 2014, data centers in the U.S. consumed an estimated 70 billion kWh, representing about 1.8% of total U.S. electricity consumption. Based on estimates in 2016, U.S. data centers were projected to consume approximately 73 billion kWh in 2020.

See a list of ENERGY STAR certified data centers.

Learn more about ENERGY STAR certified data center products.

Learn more about ENERGY STAR for data centers.

The post Find out how these Energy Star initiatives can help improve your data center efficiency appeared first on FMLink.