Europe’s data infrastructure has become a board-level priority

As regulatory pressure intensifies and concerns over digital sovereignty grow, European organisations are reassessing the foundations of their data infrastructure. Joost Rommelaere (Senior Digital and Cybersecurity Expert) and Baudouin Corlùy (Chief Market Development Officer at LCL Data Centers) join the conversation to explain the strategic importance of data centers and their role in digital transformation.

Rommelaere notes that data centers are essential, yet ideally invisible. “It’s important and not important at the same time. They just have to be there: reliable, available, and well-connected,” he says. A CIO should not have to think about them at all. That expectation, he argues, is precisely why the choice of cloud and data center strategy has evolved into a board-level concern.

Corlùy notes that sustainability, sovereignty, and compliance now dominate executive conversations as well. Regulations such as NIS2 and DORA highlight how infrastructure decisions are increasingly intersected with political, societal, and geopolitical considerations. “The data center decision isn’t just a digital transformation choice. It’s a political one,” he says.

Their message for CIOs and executives is clear: infrastructure choices shape competitiveness, digital resilience, and strategic autonomy.

Listen to the full dialogue now.

AI tends to appear in the news as a rapid stream of new models and breakthroughs that seem to outpace each other every few months. But its long-term future depends on what sits beneath them: the power systems that feed it, the architectures that carry its weight, the rules that govern data-sharing, and the geopolitics that determine who gains from it. In this episode, two experts who work with these challenges every day explain how these structural forces play out in real-world AI projects.

Michael Verveckken, Managing Director at Fujitsu Belgium, shares insights from advanced genomics and high-performance computing projects, where AI accelerates diagnostics yet demands secure, local, and energy-efficient infrastructure for highly sensitive data. He challenges the long-held assumption that “bigger is better” and argues for more modular, sustainable architectures.

Martin Canter, AI and Data Expert at FARI in Brussels, explains how digital twins make cities more resilient, but also require vast datasets and true interoperability. He highlights the importance of European data spaces, governance frameworks, and testing facilities to build trustworthy AI at scale, without falling into the illusion of absolute technological sovereignty.

Tune in for a conversation where practical leadership and expert insight combine to deliver genuine depth and perspective into this topic.

Listen to the full dialogue now.

We’ve all been there: a webpage that takes just a little too long to load, or a video that pauses to buffer at the most inconvenient time. Behind these small delays lies something invisible but impactful: latency. It’s the fraction of time it takes for data to travel across a network. While it may only last a few milliseconds, it can still affect how users experience digital services.

As expectations for seamless digital performance rise, reducing latency isn’t just a technical concern. It’s a business priority. One way companies address this is by bringing infrastructure closer to their users through local data centers.

This article explains what latency is, why the difference between high and low latency matters, how geography influences performance, and what role global versus local data centers play.

What is latency and why does it matter?

Whenever data travels across a network, there is always a small delay. This phenomenon is called latency. It refers to the time it takes for information to move from one point to another. Latency can never be completely eliminated, as it is an inherent part of digital communication. The key difference lies in whether latency is high or low.

• High latency makes digital services feel slow: apps respond sluggishly, videos buffer, or cloud services don’t load smoothly.
• Low latency creates a fluid experience, where interactions feel instantaneous.

The difference may be measured in milliseconds, but its impact is tangible. In financial trading, healthcare imaging, or online gaming, low latency is not just a convenience, it is a strategic advantage.

Global vs. local data centers

A major factor in latency is geography. The farther data must travel, the longer the delay. Even with modern high-speed fibre networks, signals moving across continents accumulate extra milliseconds. For example, a user in Belgium connecting to a server in the U.S. may face a delay of 100 to 150 milliseconds.

For some applications this is acceptable, but for time-sensitive services it can influence performance. That is why many organisations are bringing infrastructure closer to their users through regional or local data centers. Shorter physical distance translates directly into shorter response times.

A familiar example is Netflix. The streaming giant stores popular content inside local ISP networks. For users, this means streaming from servers just a few kilometres away, instead of across the Atlantic. A difference that virtually eliminates buffering.

By moving resources closer to end users, companies reduce latency, meet regulatory requirements, and improve overall user experience.

The sustainability dilemma of edge data centers

Pursuing lower latency through distributed infrastructure, often called edge computing, means placing smaller data centers closer to users. While edge computing boosts performance, it’s often less energy-efficient than running workloads in large, centralised data centers. That’s because hyperscale facilities are designed for operational efficiency, especially in terms of power and cooling, benefiting from:

• Ideal climates for natural cooling, such as using outside air or low ambient temperatures to reduce reliance on mechanical cooling
• Advanced cooling technologies, like liquid cooling or AI-driven airflow management, which optimize energy use when natural cooling alone is not sufficient
• Beneficial power usage effectiveness (PUE) ratings (a metric that indicates how efficiently a data center uses energy)
• Green innovations like waste-heat recycling, where excess heat is captured and repurposed

Smaller edge sites often operate with higher PUE scores and lower utilization rates compared to hyperscale facilities. This is mainly because they lack the same economies of scale: large data centers can spread cooling, power management, and infrastructure costs across a much higher volume of workloads. Local facilities, by contrast, are designed for proximity and responsiveness rather than maximum density. When underutilized, they may consume proportionally more energy per workload, which is why aligning capacity with actual demand is so important. As organizations push for lower latency, this balance between performance and sustainability has become one of the most relevant discussions in the data center industry today.

Build or partner? A strategic choice

When it comes to local infrastructure, businesses face a key choice: build their own data center or partner with a colocation provider.

Owning a facility gives full control. But that control comes at a price. Power, cooling, security, and upgrades all require constant investment. Smaller setups also miss out on economies of scale, making each unit of compute more expensive. As time passes, older infrastructure struggles to meet new efficiency standards, especially with rising pressure from EU climate goals.

Colocation avoids many of the headaches of running your own facility.

Unlike in-house server rooms, colocation data centers are built and operated as a core business, not as a side activity. This means they come with the highest standards for reliability and compliance: from obtaining the right certifications, to providing redundancy not only in power but also across multiple geographically separated sites (often more than 15 km apart), as well as robust physical security and safety measures.

For businesses, this translates into peace of mind. Instead of investing time and resources in building and maintaining infrastructure themselves, they can rely on partners whose sole focus is operating data centers. Need to expand? Just rent more rack space. Shared facilities spread costs across multiple tenants, unlocking advanced features like efficient cooling, 24/7 monitoring, and sustainability practices, which are not top of mind, nor feasible for companies.

For most organisations, the logic is simple: working with established colocation partners offers low-latency access and enterprise-grade reliability, without the cost and complexity of running everything in-house.

Brussels as a strategic, neutral hub

As organisations weigh options for data center placement, whether self-built, collocated, or cloud-based, Brussels is gaining recognition as a strategic data center location in Europe.

While traditional FLAP markets (Frankfurt, London, Amsterdam, Paris) remain key, they’ve started to face limits. Years of rapid growth have led to space and expansion challenges, such as stricter permitting in Amsterdam and Frankfurt due to power grid pressure, or limited availability of suitable land near London and Paris. Brussels, by contrast, offers room to grow, without compromising on performance.

Its location is a major advantage. Within 400 km of Europe’s core hubs, Brussels sits at a crossroads of dense fibre routes. These connections enable sub-10 millisecond latency to neighbouring regions, making it ideal for regional service delivery.

For Belgian businesses, this means strong local performance and easy global reach. The city also benefits from the stability of EU regulations and a neutral geopolitical profile. Two factors increasingly valued in infrastructure planning.

Smarter infrastructure, better outcomes

Staying ahead in the digital world requires infrastructure choices that carefully balance speed, efficiency, and sustainability.

Whether built in-house or delivered through trusted partners, local data centers are becoming vital. They offer the responsiveness users expect, especially in settings where fast, reliable service matters most. For example, in financial hubs where milliseconds make a difference in trading, in healthcare settings that rely on real-time imaging and telemedicine, or in gaming and media platforms where user experience depends on instant response.

Looking ahead, it’s clear: organisations that weigh both performance and environmental impact will lead the way. After all, great infrastructure isn’t just about power and uptime. It’s about making choices that work. For business, users, and the planet.

We’ve all heard it: “make sure to save it in the cloud.” But what is the cloud, really? Is it some magical, floating entity, or something more grounded? At its core, the term “cloud” refers to a network of servers, real, physical machines housed in data centers and connected by tangible infrastructure. Understanding this fundamental truth is essential for making informed decisions about infrastructure, sustainability, and operational resilience.

Bringing the cloud back down to earth

It’s tempting to think of the cloud as some vague or ethereal concept, but in reality, it’s entirely physical. Every digital activity you perform in the cloud, whether it’s running software, storing files, or processing data, relies on real servers housed in data centers around the world. These facilities provide the essential power, cooling, connectivity, and security that make cloud computing possible.

As IBM puts it, a data center is simply “a physical room, building or facility that houses IT infrastructure such as servers and storage devices for building, running and delivering applications and services.” Major cloud providers like Microsoft (Azure), Google (Cloud), and Amazon (AWS) operate enormous data centers filled with racks of computing equipment. But the cloud isn’t limited to global tech giants or large companies. Organisations of all sizes, including public institutions and startups, also use the cloud. Some choose to run their own cloud environments, called private clouds, using infrastructure they manage themselves, either on-site or in shared facilities known as colocation data centers, where space and resources are rented but not owned. In every case, the cloud “lives” on real machines. Not in thin air.

Public, private, hybrid and multicloud

One useful way to understand the cloud is to look at the different types of cloud environments (public, private, hybrid, and multicloud) based on who manages the infrastructure and how it’s used. While these models vary in structure and control, they all rely on physical equipment in data centers.

• Public cloud services, offered by providers such as Microsoft (Azure), Amazon (AWS), and Google (Google Cloud), give users access to computing power and storage over the internet. These providers install and manage their own hardware in professional data centers, which they may either own or lease from specialized facility operators. While users don’t know exactly where their data is stored, they benefit from massive scale, flexibility, and global reach.

• Private cloud refers to a cloud environment used exclusively by one organisation or institution. It can be set up in a data center the organisation manages itself, or hosted by a third party. Unlike public cloud, the infrastructure is reserved for a single user group. Private clouds use similar technologies as public clouds. One of these is virtualisation: a method that allows multiple virtual computers to run on a single physical machine. The key difference is that private clouds offer more direct control over data, security, and performance. Organisations using a private cloud know exactly where their data is stored, as it is hosted on their own infrastructure.

• Hybrid cloud blends the two. For example, an organisation may store sensitive data in a private environment while using the public cloud for less critical or highly variable workloads. This approach allows flexibility, combining the strengths of both models.

• Multicloud means using cloud services from more than one provider, such as combining Microsoft Azure for certain tools, Amazon Web Services for data storage, and Google Cloud for analytics. This strategy helps organisations avoid relying too heavily on a single vendor and allows them to choose the best service for each specific need.

Regardless of the model, the cloud always relies on physical infrastructure (racks of equipment, network connections, and cooling systems) housed in secure, professionally maintained data centers.

From rivals to allies

Today, cloud and on-premises infrastructure are no longer seen as competing options. Most organisations now follow a hybrid approach, combining cloud services with on-site systems to build flexible and resilient IT environments.

This strategy offers several clear benefits. By keeping critical or sensitive applications in a private cloud (hosted either on-premises or in a professional data center), organisations maintain greater control over security, compliance, and performance. At the same time, they use the public cloud for scalable workloads, such as data processing or web applications, that need to grow quickly and cost-effectively.

As Microsoft’s Tiziano Durante puts it: “When we say hybrid, I see a hybrid model where the cloud runs on a hyperscale data center and the on-prem infrastructure is hosted in an enterprise data center.”  IT teams are increasingly combining in-house infrastructure or colocation in a professional data center with public cloud services. This hybrid approach enhances flexibility and resilience. Energy efficiency has become a key driver, encouraging organisations to move their IT infrastructure to specialised data centers.

Why sustainability is driving cloud adoption

Sustainability has become a major reason, alongside flexibility, scalability, security, and cost control, for organisations to move to the cloud. Beyond the operational advantages, modern cloud data centers are also built with energy efficiency in mind.

Compared to outdated server rooms in office buildings, centralised cloud facilities typically consume less power and generate lower emissions. They are professionally managed, optimised for performance, and increasingly powered by renewable energy. Independent research shows that centralising IT workloads in cloud environments can significantly reduce carbon footprints and improve overall energy efficiency.

In addition, cloud providers benefit from economies of scale, advanced cooling techniques, and intelligent resource management—capabilities that are hard to replicate in small-scale, on-site setups. In contrast, aging local servers often run inefficiently, leading to unnecessary energy use and maintenance costs.

For many organisations, evaluating whether to maintain their own infrastructure now includes sustainability as a strategic factor, alongside performance, governance, and long-term viability.

The cloud is built on real infrastructure

So, what is the cloud, really? It’s not an abstract or floating concept, it’s a network of real computers housed in real, physical data centers. Public, private, or hybrid clouds are simply different ways of organising that infrastructure. In every case, it all runs on data center foundations.

Data Center University, cloud, what is the cloud, public cloud, private cloud, hybrid cloud, multicloud, data centers, IT infrastructure, colocation, servers, sustainability, energy efficiency, AI, cloud adoption

Data centers and IT services are more connected than ever. Both are crucial in keeping modern businesses running smoothly. But despite how closely they work together, many people still confuse one for the other. In reality, data centers and IT play very different roles. So what does a data center actually do, and what doesn’t it do? Let’s break it down in this article.

Data centers provide the environment, not the IT

It’s easy to assume a data center takes care of all things IT-related. But that’s not quite the case. A data center provides the physical infrastructure: space, power, cooling, connectivity, and on-site technical support.

IT, on the other hand, involves the management of data, applications, networks, and end-user services. These tasks are typically handled by businesses themselves or by dedicated IT service providers. Think of the data center as the highly technological building, while the IT is everything that happens inside.

In short, data centers create the stable foundation IT systems need to function. Without one, modern IT environments simply wouldn’t be sustainable.

3 Common misconceptions about data centers and IT

1.     “Data centers manage the data.”

Not quite. While data lives inside a data center, the data center company itself doesn’t manage it. The business using the space is responsible for its own data, and installing, maintaining, securing, and managing it. The data center company ensures everything around it works smoothly, but it doesn’t touch the data.

2.     “Everybody working in a data center is an IT expert.”

While some data center staff specialize in IT systems for internal needs, the majority of personnel focus on infrastructure. These include electricians, service technicians, cooling engineers, and system operators. Their job? Keep the systems running, the power flowing, and the environment stable, rather than providing external IT consulting or services.

3.     “Data centers and software development go hand in hand.”

Not really. Software developers usually work remotely or in offices. The professionals you’ll find in a data center are often field engineers: people who physically install or maintain servers, cables, or other hardware. In many cases, the software team never even steps foot inside the facility.

What role does IT play inside a data center?

Even though data centers don’t offer IT services to clients, they absolutely rely on IT systems to run their own operations. Behind the scenes, there’s a lot going on. Internal IT and OT (Operational Technology) systems manage:

• Power infrastructure, like UPS units and backup generators
• Cooling systems, such as CRAH and CRAC units, chillers, and pumps
• Environmental monitoring tools and sensors
• Access control, video surveillance, and alarm systems
• Platforms for real-time alerts, diagnostics, and performance reporting

These are critical systems. They need to be up and running 24/7. A dedicated team is typically in charge of keeping them secure, efficient, and scalable. If you’ve ever wondered how data centers stay online during a power outage or catch temperature spikes before they become a problem, this is how.

Supporting IT without being IT

You can see how the lines between data centers and IT get blurry. They are deeply interconnected, and both are essential to digital infrastructure. But they’re not the same thing. A data center doesn’t provide IT services. It provides the environment those services rely on.

That distinction matters. Understanding the separation between physical infrastructure and IT operations can help businesses clarify responsibilities, avoid confusion, and make better decisions about their setup. And isn’t that what good infrastructure is all about: clarity, reliability, and trust?

Keywords: data centers, IT services, infrastructure vs IT, IT misconceptions, digital infrastructure, power and cooling, server hosting, OT systems, IT support, UPS backup, environmental monitoring, data management

Crisis readiness: from theory to practice

Cybersecurity is no longer a niche topic. With regulations like DORA and NIS2, many companies now have roadmaps in place. But how do you make sure these plans hold up when the pressure is on? We spoke with cybersecurity and AI expert Axel Legay, and Fednot CIO Bjorn Van Reet, about putting strategy into practice and integrating the human factor.

“When a crisis hits, your team needs to be trained and ready to act under pressure,” says Axel Legay. “And just as important, someone should be prepared to step forward as a spokesperson to clearly communicate the situation externally. Sharing knowledge, both within your organisation and beyond, is essential.”

Bjorn Van Reet agrees: “No two crises are the same. While practice doesn’t make perfect, it helps your team stay composed when the unexpected happens. Knowledge sharing is crucial, and so is involving the right experts. Keeping everything in-house can create blind spots. External partners, like specialised data centers, bring valuable neutrality and experience to the table.”

In this episode, we also touch on the role of AI, how changing regulations are both a challenge and a catalyst, the value of diverse teams, and the lightning speed of technological evolution. “In computer science, the near future means a few months, not a few years,” says Axel Legay.

Tune in for an insightful conversation on cybersecurity and resilience. Enjoy the listen!

Are you equipped for what’s next?

Cloud, on-premises or hybrid? As digital acceleration continues and compliance requirements grow stricter, choosing the right infrastructure model has become a strategic priority. In this first episode of Data Center Dialogues, we explore hybrid cloud strategy with Tiziano Durante (Cloud Region Lead at Microsoft) and Koen Van Loo (CIO & CDO at Group S).

While hybrid offers a pragmatic bridge between legacy and cloud-native systems, one trend is becoming clear: traditional on-premise data centers will gradually give way to professional, scalable and compliant infrastructure. Or as Tiziano puts it: “The server under the desk is no longer an option. So how can we work together to build the best fit for the company and stay in the fast lane, without making rushed decisions?”

We also dive into lessons learned from past challenges, the growing importance of data sovereignty, and key concepts such as latency and residency.

Tune in for a dynamic and forward-looking discussion on infrastructure decisions. Enjoy the listen!

As businesses grow ever more reliant on seamless connectivity, carrier-neutral data centers have become essential to modern IT infrastructure. But what exactly does carrier neutrality mean, and why is it a game-changer for contemporary enterprises?

What is carrier neutrality?

Choosing the right data center is a crucial decision, and one key factor to consider is carrier neutrality. But what does that mean, and why does it matter? Carrier neutrality refers to a data center’s independence from any single telecom provider, giving businesses the freedom to connect with multiple network carriers, cloud providers, and internet exchanges.

Unlike vendor-specific facilities that tie businesses to one provider, carrier-neutral data centers create an open marketplace where organisations can choose from multiple network carriers, cloud providers, and internet exchanges. This competitive environment not only enhances performance and scalability but also allows businesses to scale their connectivity based on their needs, without restrictions.

Five key takeaways of a carrier-neutral data center

1.     Greater connectivity and flexibility

One of the biggest takeaways of carrier-neutral data centers is the freedom to choose and change providers. Organisations can select the best connectivity solutions tailored to their needs, considering factors like performance, pricing, and geographical reach.

Furthermore, with cloud adoption at an all-time high, many carrier-neutral facilities offer direct connections to major cloud providers such as AWS, Microsoft Azure, and Google Cloud. These high-speed, low-latency links ensure optimal performance for mission-critical applications.

2.     Built-in redundancy for maximum uptime

In today’s digital economy, downtime is simply not an option. Carrier-neutral data centers host multiple network providers on-site, ensuring that if one carrier faces an outage, traffic can be automatically rerouted through an alternative provider. This level of redundancy enhances business continuity and safeguards both reputation and revenue streams, ensuring that operations run like a well-oiled machine and maximizing uptime.

The critical importance of redundancy in data centers

Redundancy is vital for modern data centers. Learn how N+1, 2N, and geo-redundancy reduce downtime and keep services reliable and…

This redundancy is further bolstered by meet-me rooms (MMRs), dedicated spaces where businesses can establish direct, redundant interconnections with multiple carriers. Additionally, cross-connects within these data centers allow organisations to bypass the public internet, improving security and reducing costs for industries that rely on real-time data transfer, such as finance and AI-driven applications.

3.     Competitive pricing and cost efficiency

In a non-neutral data center, businesses often find themselves with limited options for connectivity services, which can lead to higher costs and the dreaded vendor lock-in. However, carrier-neutral facilities create a competitive marketplace where providers must distinguish themselves through pricing, service quality, and innovation.

With multiple carriers under one roof, businesses can negotiate for better deals and select services that fit their budget and requirements. Plus, as new providers enter the market, customers enjoy the benefits of improved rates, enhanced services, and the latest technologies. It’s a win-win situation.

4.     Future-proof scalability

As businesses expand, their IT and connectivity requirements evolve. Carrier-neutral data centers are built to support long-term expansion. This is particularly crucial for organisations venturing into new markets, as the ability to tailor connectivity solutions guarantees a smooth transition. Whether an organisation needs to boost bandwidth, change providers, or integrate new cloud solutions, they can do so effortlessly without the hassle of migrating infrastructure. This flexibility ensures that organisations stay agile in an ever-evolving digital landscape

5.     Global reach and market expansion.

Finally, carrier-neutral facilities provide access to major internet exchanges such as AMS-IX (Amsterdam Internet Exchange) and NL-IX (Neutral Interconnect Exchange), enabling businesses to expand their footprint across multiple regions with optimised performance. This is particularly valuable for organisations looking to enter new markets while maintaining high-speed, reliable connectivity.

The future of data center connectivity

Carrier neutrality is more than just a technical choice; it’s a strategic decision that empowers businesses with flexibility, resilience, and cost savings. As the demand for high-speed connectivity and seamless cloud integration grows, carrier-neutral data centers will play a pivotal role in shaping the future of digital infrastructure.

Winter brings unique challenges, particularly for critical infrastructures like data centers. These facilities rely on precise environmental conditions to operate effectively. Cold weather can disrupt sensitive cooling systems, damage essential equipment, and complicate on-site maintenance due to snow or ice, making proactive preparation crucial. Preventive maintenance, strict procedures, and round-the-clock monitoring are essential to ensure flawless and reliable operation in harsh winter conditions.

The biggest challenge for a data center in winter are subzero temperatures. Freezing water in cooling circuits is one of the most significant risks because it can block the flow of coolant and cause pipes to burst. This damage to essential components can potentially lead to prolonged downtime across the entire facility.

Outdoor generators, which are often exposed to the elements, require additional attention. For example, extreme cold can cause fuel to thicken, making it difficult for the generator to start, while snow or ice buildup can block ventilation or damage components. These issues highlight the necessity of addressing specific challenges that arise during winter.

Prevention is key

Strict procedures and preventive maintenance, supported by technologies such as automated monitoring systems, predictive maintenance tools, and insulated pipe solutions, can effectively mitigate winter risks. Critical installations should be thoroughly inspected before the winter season. Cooling systems require protection to prevent freezing, stagnant water in pipes must be removed, and batteries for cooling cells should function efficiently to ensure smooth operation. Filters should also be inspected, and all standard periodic tests completed to maintain system integrity.

Verifying fuel levels, checking for leaks, and updating emergency procedures are essential tasks that should be completed well before the onset of frost. Ensuring the site itself is prepared is also important; this includes inspecting roofs, water pipes, drains, and ensuring supplies of road salt are adequately stocked for icy conditions. A standard procedure checklist can help ensure that every aspect of the site is winter-ready.

Training and preparation make the difference

Operational team training is vital to the success of these preventive measures. Regular training sessions and updates ensure that teams are familiar with standard procedures and prepared for potential emergencies. Scenario-based training exercises can improve readiness for unexpected incidents. While this involves considerable effort, it is critical to keeping data center operations running smoothly during even the harshest winters.

Round-the-clock monitoring

Continuous monitoring plays a crucial role in stability during winter as well. Round-the-clock-monitoring systems can track hundreds of parameters, alerting the team to anomalies immediately. During the winter months, special attention should be given to temperature fluctuations within the facility. Monitoring the temperature in all rooms allows for prompt intervention if deviations occur, always ensuring stable and reliable operations.

A continuous process of improvement

Preparing a data center for winter is not a one-time action but a continuous cycle of evaluation, adaptation, and readiness to ensure long-term resilience. A combination of preventive measures, strict monitoring, and well-trained teams ensures data centers remain resilient, regardless of weather conditions. By maintaining this level of preparation, data centers can consistently uphold operational reliability, even during the most severe winter conditions. Regular post-winter evaluations can identify areas for improvement, ensuring even better preparation for the future.

Redundancy is crucial to modern data centers, essential for ensuring high availability and reliability of services. Redundancy means that multiple installations are provided for the same critical components, such as power supply, climate control, connectivity, monitoring, security, and backups. Power outages and other service interruptions are expensive, so data centers must avoid unplanned downtime at all costs. Redundancy is one of the key factors in achieving that.

The (double) strength of redundancy

Redundancy offers indispensable assurance to data centers and their customers. Firstly, it increases reliability: systems continue to function despite possible failures or interruptions. Additionally, it improves availability: data center services stay active, even during maintenance or component failures. This helps mitigate risks and is crucial for business-critical applications and the uptime of our data centers.

According to Uptime Institute’s 2022 Global Data Center Survey, published in 2023, more operators are investing in their resiliency. About 40% of respondents reported that they were increasing the redundancy levels at their primary data centers. Power and cooling systems have received similar attention, with a third of operators upgrading either or both.

While providing redundant systems equals spending more on the hardware needed, the high cost of data center downtime can often justify these investments to a certain extent. Redundancy minimises the risk of these high costs by ensuring operations and uptime for customers.

Redundancy options

In a modern data center, there are many possibilities for which components can be installed in a redundant way. In this section, we will list the most common options.

Power

An example of power-related redundancy would be independent power circuits. In this case, A and B supplies will be provided, fully separated. This ensures devices remain functional even if one supply fails. Further support for these power circuits could come from redundant UPS (Uninterruptible Power Supply) systems and emergency generators in case of a power outage.

When regular power supply fails, the UPS immediately detects this disruption and switches to battery power to maintain a consistent power supply. Emergency generators do not start operating immediately; they require some time to start up, which can be up to a few minutes. When they are operational, they will take over from the UPS. So even though there are backup systems provided in case of a power outage, these separate systems might also have a redundant equivalent.

Cooling and security

The cooling systems in data centers often have more capacity than necessary, with independent units, preventing a failure in one unit from impacting customer operations. If one of the units fails, there cannot be any risk of overheating, as that can cause the servers to malfunction. That’s why it’s safer to also provide redundant cooling units. The same applies to other security systems (including fire suppression systems, physical and digital security) and system monitoring. It’s a data centers’ core to ensure everything runs safely and optimally for our customers, making redundancy essential.

Connectivity

Additionally, connectivity options are best designed with redundant entry points throughout the building. This is to avoid single points of failure, or intersections where both redundant lines cross, meaning that if one line is disrupted, there does not have to be loss of connection. Some data centers even offer two redundant meet-me rooms, which are fully independent of each other.

An even more specific aspect of redundancy are patches or cross-connects, physical connections between a telecom operator and the customer. From the meet-me room, cross-connects connect to various racks, cages, or suites in the data center where end customers have their equipment. Data centers can opt for redundant structured cabling or connectivity cabling to both meet-me rooms. This backup ensures that if a connection in one part of the data center fails, an alternative connection is available, ensuring service continuity. This is especially important for companies whose end customers have 24/7 access to their services.

Levels of redundancy

Now that we know which components can be redundant, we can look at the different possible levels of redundancy. Redundancy in data centers is categorised into different levels to indicate how robust a system is against failures. Terms such as N+1, N+2, 2N, and 2N+1 are commonly used to describe these levels. But what do these terms mean?

N+1 Redundancy:

N stands for the number of components required to ensure basic functionality. +1 means there is one additional component beyond the necessary number.

For example, if a data center needs 3 cooling units to maintain optimal temperature, an N+1 setup would mean there are 4 cooling units; one extra as a backup in case one of the units fails.

N+2 Redundancy:

This involves two extra components beyond the basic requirement. It offers a higher level of safety as more backups are available. For instance, if two of the required components fail simultaneously, the system will still function.

2N Redundancy:

This is a completely duplicated setup of all required components. So, if a data center needs 5 cooling units, a 2N configuration would have a total of 10 units.

This level of redundancy ensures very high availability because the entire system can continue to operate, even if half of the components fail.

2N+1 Redundancy:

This is similar to 2N redundancy but includes an additional component.

In the example with the cooling units, this means there is not only a duplicate set of 5 units (equalling the 10 mentioned above) but also an extra server as further backup, so 11 in total.

These levels of redundancy ensure that a data center can operate reliably, even under unforeseen circumstances such as technical failures. The higher the level of redundancy, the lower the chance of downtime, but this also comes with higher costs. Choosing the right level of redundancy can also depend on how critical the services provided by the data center are.

Conclusion

Redundancy is not a luxury but a necessity in modern data centers, with benefits for reliability and availability crucial for business-critical operations. Some go even further then redundancy of critical installations in one data center, opting for geo-redundancy. This means that data center components are duplicated in different areas or even countries, to make sure that a climate event in one country or continent won’t halt their operations. Better to be safe than sorry.

But as mentioned above, even redundancy of critical components like power, cooling, and connectivity can be a big aid in preventing service interruptions. Increased investment in redundancy, as reported by the Uptime Institute, reflects its value in mitigating the costly impacts of downtime. Considering the different levels of redundancy, from N+1 to 2N+1, there is a formula that works for every data center and their need for continuous operations.