Skip to content

In the first article in our series on interconnections, we introduced the concept of interconnection in colocation data centers. We described the important role they play, not only in helping companies conduct vital “business as usual” operations each day, but also in making them more agile, responsive, and competitive.

Yet, we realize the term interconnection is used by vendors and other parties to describe many different approaches or technologies related to connectivity in the data center.

Therefore, this article will define interconnection, but also take a closer look at five different interconnect approaches in use today. Hyperscale data centers increasingly rely on diverse interconnection types to support growing data traffic and reduce latency. We’ll define each one, describe how it works, and even provide some real-world examples to help bring them to life. Hopefully, we’ll establish a level of baseline clarity that will help you pick the right interconnect strategy for your business.

What is Interconnection?

To start, interconnection is an overarching term that refers to many different physical and virtual connections companies can select to exchange data, provide business continuity and customer services, and address specific business objectives.

As a business offering itself, interconnection has come a long way since the first telecommunication providers connected networks to improve the way they exchanged voice traffic. Today, virtually every business needs to connect with others, in some way or another, to exchange data to support vital business processes.

While there are many different mechanisms for interconnection, each complete with additional variations, there are several types of interconnection services available in most data centers today. Let’s take a closer look at a few examples.

Cross-Connects

Cross-connects represent the most basic type of interconnection and generally refer to the direct, physical, and dedicated connection between two networks. Think of the familiar example of running fiber between two endpoints in a colocation data center, and you can picture how cross-connects work.

Cross-connects provide dedicated, point-to-point connectivity as well as the most reliable, efficient, and secure way to connect networks and infrastructure. They also deliver excellent reliability and low latency, great benefits for virtually any data center customer.

Internet Exchanges

An internet exchange, also known as an internet exchange point (IXP), is a switch. Companies can connect their network to an IXP using a physical cross-connect, and once they’ve established that connection, they can connect to other members of the internet exchange, without the need to run separate cables.

Companies use internet exchanges to establish peering with other networks connected to the IXP, leveraging the BGP protocol to establish peering sessions over a single physical connection, and again, without the need for new cabling. Peering is a valuable advantage for interconnected companies such as internet service providers, content delivery networks, and other service providers, as well as the enterprise, and enables them to reduce transit costs, increase capacity, and improve network performance.

Private peering is a variation that takes place in a colocation facility where two parties maintain separate network routers but connect them with a direct cable instead of connecting to the IXP. This is a beneficial use case when networks are exchanging a large volume of traffic, which won’t fit on a shared connection to an exchange point.

Data Center Interconnects (DCI)

A Data Center Interconnect (DCI) is similar in theory to a cross-connect, but uses electronics, typically DWDM, to establish a point-to-point connection between two data centers so they can share resources or improve other operations such as load balancing. For example, a company could choose to connect two different networks in the same metro or in two different metros.

Data Center Interconnection (DCI) can connect any data center, whether it’s in proximity or located a great distance apart, depending on the technology used to deliver the connectivity: Optical Networking or Ethernet.

Internet Connectivity

As the name implies, internet connectivity lets data center customers access and use the internet. Yet, this is more than just a basic internet connection. There are multiple ways of delivering internet connectivity: Dedicated Internet Access (DIA) or IP Transit. While DIA provides basic connectivity, IP Transit is more advanced and leverages the BGP protocol. This enables the company to advertise its own IP Prefixes and control how routing information is used.

Cloud Connectivity

Cloud connectivity refers to the ability of any company to connect to its virtual computing environment hosted by a public cloud provider to access its data and workloads. While many companies may have assets such as compute, data storage, services, and more in the data center, their app may be in the cloud. They need a private connection between all of these to aid with issues such as bandwidth, reliability, and security.

There are several ways to establish these types of cloud connections:

• Cloud on-ramps: These connections are powered by the network equipment the cloud provider deploys. Yet, they might not be available in all data centers because the high number of data centers in a particular region or metro quickly makes this option cost-prohibitive. For companies in a data center with a cloud on-ramp, they can easily access it using a cross-connect.

• Network as a Service (NaaS): For those companies whose data centers don’t have cloud on-ramps, they can use NaaS platforms to accomplish the same goals. NaaS platforms are similar to IXPs: a switch companies can use to connect to other cloud on-ramps.
– VPN: Companies can also connect virtual private clouds to remote networks using many different VPN connectivity options, including site-to-site VPNs, provider-specific VPNs or third-party VPN software.

Any of these options helps companies access public cloud environments in an efficient, reliable, and secure way.

Clarity is Key

We hope these definitions and examples help you understand the various options available as you evaluate interconnection possibilities in a colocation facility. Future interconnection fabrics will support mesh overlays, including private peering, latency-aware SDN, and edge exchanges, to support distributed AI/edge service delivery in metro regions by 2026. Stay tuned for the next article in the Interconnection blog series.

Related Resources

Northern Virginia Data Centers
DataBank Completing $4 Million Minneapolis Data Center Upgrade
What Is the Meaning of Interconnection in IT?
Interconnection 101-Getting Back to Connectivity Basics

Frequently Asked Questions

By Mark Houpt, Chief Information Security Officer, DataBank

As seen in Data Center Frontier Voices of the Industry: Mark Houpt, Chief Information Security Officer at DataBank, discusses cybersecurity in the context of the war in Eastern Europe. He highlights changing dynamics that could potentially increase risk to U.S.-based companies while also offering assurances in the soundness of data security frameworks in general. He also recommends a number of best practices any data center operator should consider to improve its cybersecurity posture.

Due to the constantly changing dynamics, this article reflects conditions in Eastern Europe as of the date of publication. These events could abruptly change and lead to new cybersecurity implications.

I was recently interviewed by Forbes as part of an article on Crystal Ball Predictions About Cyberattacks in 2022. I predicted that we’d have to be more vigilant in defending against possible nation-state attacks, particularly as several countries and independent groups (“nonaligned entities” such as hacker groups) now have significant cyber capabilities. As we’ve seen in the past, these capabilities can be used as ransomware, Distributed Denial-of-Service (DDoS), or other cyberattacks against commercial systems or critical infrastructure.

Unfortunately, we’re seeing this play out now with the events unfolding in Eastern Europe. Tension has been building in this region for quite some time, so the conflict is not a complete surprise. Yet, a dynamic fast-moving scenario like this leads to real questions related to cybersecurity:

They’re all valid concerns. To address them, it may help to first take a step back to understand how we arrived here, and then, revisit cybersecurity best practices to improve your defenses for 2022—and beyond.

Social Media’s Impact

Technology constantly shapes the way we monitor and perceive wars and conflicts such as what we’re now seeing. For example, more than 30 years ago, Operation Desert Storm was regarded as the first war fought on live TV, with satellite communications providing accurate images, footage, and updates on a daily basis.

Similarly, the current Eastern European conflict could be considered the first war to be fought on social media. People are using social media platforms to share videos, distribute information, generate sympathy and support, and influence results. In many ways it’s succeeding, but it also may have unintentional cybersecurity results on a global level.

In this case, the public outcry—as voiced in millions of posts, comments, likes, and shares—has been heard by nonaligned entities and conglomerates of hackers sympathetic to Ukraine. In response, many are launching cyberattacks against the aggressor, which, in turn, has led to a temporary decrease in attacks against American companies and infrastructure.

For CISOs and cybersecurity teams, this may seem to be good news—but only at first. The fact remains that these events are truly dynamic, especially in the case of one or more nonaligned entities targeting a powerful nation-state. These nations are accustomed to responding to attacks from other nations, not hard-to-identify hacker groups. This conflict is changing from moment to moment, and it’s conceivable it could affect the U.S. down the road.

How Can Data Centers Improve Their Cybersecurity?

There are a few steps any data center operator can take to improve its overall cybersecurity defenses and posture.

Expand the Use of Intelligence Sources

One of the most valuable resources any cybersecurity professional should use is the right intelligence sources. Many companies tend to shy away from operational security intelligence and open-source intelligence (OSINT), perhaps because they consider it a government function, not business responsibility. Today’s climate calls for a change: re-evaluating this mindset and investing in effective OSINT tools can give you a valuable advantage.

Take Advantage of Government Resources at Your Disposal

Companies today should do all they can to make use of available government resources. In the U.S., it can be one of the best resources that we have that is not actual law enforcement. For example, the Cybersecurity and Infrastructure Agency (CISA) is an incredibly valuable resource and employs teams whose sole responsibility is to work with businesses in an intelligence capacity as well as an advisory role.

The Department of Homeland Security also has important resources to help U.S. businesses bolster their cybersecurity efforts. This has become more important when you consider the recent SolarWinds, Colonial Pipeline, and other successful cyberattacks.

Twitter Mining

There are companies and solutions that will mine Twitter and other social media platforms to consolidate data and use it to alert about possible threats. Users can even manage multiple Twitter feeds running at the same time to collect hashtags and monitor other trends and possible groundswells of threat activity.

This type of functionality could be used during a crowd event or riot. Cybersecurity teams can track crowd locations, and if they get too close to a facility or data center, they can notify staff and take preventative measures to assure the facilities stay safe.

Shields Up: Adhere to Security Best Practices

Now is not the time to relax your standards. If anything, it’s time for “shields up,” and this means increased scrutiny and discipline related to known cybersecurity best practices.

For example, every company should be up to date when it comes to patching, data hygiene, and physical elements of security. This can include everything from making sure fuel contracts are current and backup generators are filled, to visitors wearing badges at all times.

This is also a great time to revisit various policies and escalation paths, including running business continuity drills, disaster recovery drills, and tabletop exercises. Cybersecurity professionals simply can’t afford to take their eye off the ball.

Be Confident While Remaining Vigilant

As we examine the overall situation, there are many reasons for data centers to be confident in the security strength of the U.S.-based infrastructure, especially as they continue to be vigilant. As I write this, we are nearly a month into the conflict in Eastern Europe and U.S.-based infrastructure is still intact. Generally speaking, this seems to show that the majority of cyberattacks have been contained to that region. However, the situation will be constantly changing, with new dynamics occurring each day that could lead to cybersecurity concerns directly in the U.S.

Knowing this is half the battle, data center providers should use this time to take a closer look at their overall cybersecurity programs and take all the steps they can take to be even more vigilant now to enhance their cybersecurity preparations and posture. Whether investing in new resources, partnering with new cybersecurity partners and service providers, adhering to known best practices, (or all of the above), data center operators can stay a step ahead of potential cyberattacks no matter how the geopolitical situation develops.

About the Author

Mark Houpt, Chief Information Security Officer at DataBank, brings over 30 years of extensive information security and information technology experience in a wide range of industries and institutions. Mark holds an MS-ISA (Masters Information Security and Assurance), numerous security and technical certifications (CISSP, CEH, CHFI, Security +, Network+), and is qualified for DoD IAT Level III, IAM Level III, IASAE Level II, CND Analyst, CND Infrastructure Support, CND Incident Responder, and CND Auditor positions and responsibilities. Mark is an expert in understanding and interpreting FedRAMP, HIPAA, and PCI-DSS compliance requirements. He is also an active member of ISC2, ASIS International, COMPTIA, IAPP, and ISACA, among other leading national and international security organizations.

The tech industry is on the rise in the Los Angeles-Irvine metro as technology employees in the area earn among the nation’s highest average salaries in the industry. Supporting this growth is DataBank’s California presence, which extends from Silicon Valley to San Diego and features in between three colocation data centers within 45 minutes of each other—one in Los Angeles and two in Irvine.

Some of the most recognizable companies have U.S. headquarters in Los Angeles, including Snapchat, TikTok, Walt Disney, Live Nation, Skechers, and Mattel. As home to the global movie industry, numerous universities, and a fast-growing ecosystem of media and digital gaming companies, Los Angeles is rapidly becoming a major edge market for cloud, connectivity, and colocation.

Just south of Los Angeles, Irvine is also headquarters for numerous digital gaming companies that require robust data center compute resources. With a mix of research and entertainment firms, the area adds to the already high demand for colocation options. At the same time, technology in Irvine is advancing at an accelerated pace—governed by the city’s Strategic Technology Plan. The five-year technical and financial guide forecasts IT investments, defines strategic priorities, and promotes innovation and investments in cloud computing, cybersecurity, and disaster recovery.

Preeminent Data Center Locations

In Los Angeles, DataBank clients can access a preeminent data center location for IT infrastructures and one of the top telecommunications centers in the world. Our facility at One Wilshire Blvd, also known as the “Carrier Hotel of the West,” is one of the most densely connected buildings globally with access to 200+ carriers. One Wilshire also offers many features that attract tenants—from multiple fiber entry points to unrivaled carrier access to 24x7x365 staffed security.

Within Irvine, the DataBank data centers also feature impressive attributes. These Orange County colocation options are conveniently situated downtown near UC Irvine and the San Diego Freeway. Together, they offer more than 64,000 sq. ft. of data center space and 16 Megawatts of power. These facilities also provide access to a broad range of fiber, Internet, and connectivity options along with the very best facility logistics amenities.

Data Center Options for Established Enterprises and Start-Ups

With an estimated population of more than 13 million people, Los Angeles-Irvine is the second-largest metropolitan area in the U.S. and the center of the Southern California colocation universe. Known for a Mediterranean climate and dominating presence in the entertainment industry, the area is attracting large enterprises and increasing numbers of technology startups that need data center options like those offered by DataBank. To learn more, take a closer look at our Irvine and Los Angeles data centers or request a no-obligation quote today.

The DataBank Los Angeles-Irvine Metro by the Numbers

3 Data Centers

18

Total Megawatts

193+

Total Carriers

84,000

Total Square Feet

DataBank Los Angeles-Irvine Metro Data Centers

LAX1: Los Angeles

624 South Grand Avenue, Suite 2900

20,000 square feet, 1.78 MW of on-site power

Explore this data center

SNA1: Irvine

17222 Von Karman Avenue

30,938 square feet, 2.7 MW of on-site power

Explore this data center

SNA2: Irvine

17400 Von Karman Avenue

33,700 square feet, 4 MW of on-site power (expandable to 8MW)

Explore this data center

As announced earlier this year, DataBank is reinforcing our commitment to Northern Virginia by building a third colocation facility in the market. Construction of the IAD3 Ashburn data center, is progressing well, and the facility is slated to go online in Q4 2022, joining the adjacent IAD1 data center to form the new DataBank Ashburn Campus.

See our progress. Watch this time-lapsed video of IAD3’s development.

At nearly 287,000 square feet, IAD3 more than doubles our footprint in Loudoun County, providing a perfect solution for colocation, cloud, and technology services.

IAD3 features an 11-acre site with continuous perimeter fencing and security access gates as well as large and small conference rooms, breakrooms, and restrooms with showers. The facility spans 10 data halls and 11,000 square feet of build-to-suit offices and storage areas and features a power capacity of 40 MW—with backup power coming from 3MW CAT Generators that have 24-hour reserve fuel tanks. The facility is also cooled by a Vertiv DSE Pump-Refrigerant technology cooling system with roof mounted condensers.

Combining Interconnection Advantages with Taxation Benefits

In addition to joining IAD1 on the Ashburn campus, IAD3 is less than 30 minutes from another of our Northern Virginia data centers—IAD2 in McLean. The overall data center market in this area of the country is home to more than 20% of all global hyperscale data centers and handles approximately 70% of the world’s Internet traffic.

Customers who colocate in DataBank’s IAD1 or IAD3 facilities benefit from the State of Virginia Retail Sales and Use Tax Exemption (applicable to computers and related data center equipment) as well as the market’s valuable ecosystem built on the world’s densest fiber network. With unmatched technology infrastructure and reasonable energy costs to go along with the significant tax incentives, Northern Virginia is the preferred location in the U.S. for data center operations.

At the DataBank data centers—located in “Data Center Alley” and just a few miles from dozens of other data centers—customers can choose from various build-to-suit options for new deployments. The colocation facilities also deliver maximum uptime assurance—making them ideal for enterprise, web-scale SaaS, and hyperscale cloud workloads that need room to expand and interconnect.

An Ideal Location

IAD3 is also adjacent to Ashburn Technology Park, Loudon County Parkway, Dulles Toll Road, and Dulles International Airport. Along with IAD1 on the Ashburn Campus, the facility provides cross-connect and interconnection options and is served by multiple feeds from an off-site, utility-owned substation.

To get a sense of what this impressive facility offers, you can take a virtual tour, and for information about colocating in any of the DataBank Northern Virginia data centers, call 800.840.7533 or request a no-obligation quote.

The DataBank IAD3 Ashburn Data Center by the Numbers

40MW

Total Megawatts

15 via Cross Connect to IAD1

Total Carriers

286,800

Total Square Feet (2 stories + 85,00 square foot equipment yard)

In this first article in an ongoing series, we introduce the DataBank Customer Portal and describe how it helps our customers gain self-service control and complete visibility into their entire infrastructure. This article highlights the Portal’s extensive capabilities—and how they help customers improve day-to-day management. Stay tuned for additional articles, or learn more about the DataBank Customer Portal now.

Whether you rely on DataBank for colocation, cloud, security, or managed services, the DataBank Customer Portal is a valuable resource that provides increased visibility, convenience, and control over all aspects of your DataBank infrastructure.

We’re proud of the Customer Portal because it is so different from other customer portals or offerings in the market. (After their first look at the portal, our customers consistently tell us they haven’t seen anything like this anywhere else.) We started the process by collecting real-world feedback from our customers and custom-built the portal to make sure it continues to deliver all of the capabilities any company requires.

We chose not to use off-the-shelf software that couldn’t meet our high expectations. Instead, we built the portal from the ground up, complete with an official product roadmap, ongoing iterations based on new requests, and an agile software development methodology to make sure we deliver real business value for our customers.

Today, the Customer Portal gives you everything you need to see your entire environment and manage virtually every part of your infrastructure. This includes areas such as physical access, power use, network performance, resource management, security details, compliance, and reporting.

Customer portals increase service transparency, with 70% of users reporting faster issue resolution and better resource management. Customer portals are being enhanced into insight hubs with real-time analytics on usage, predictive consumption alerts, and AI-based optimization recommendations for tenants and operators.

To learn more, we created this tutorial series, where each article will highlight a different portion of the Customer Portal and describe the many benefits it provides. First up: support

Please accept statistics, marketing cookies to watch this video.

Support Capabilities: Self-Service Access and Control

The support section of the portal is the area that DataBank customers visit the most. They can open tickets, review the status of open tickets, and search all of their ticket history, book conference rooms, manage on-site deliveries, and even request help for remote hands, which are available at all DataBank data centers.

Customers can look at the past history associated with any ticket or see various details (e.g., troubleshooting steps, resolution process, etc.). They can also subscribe themselves or other authorized users to any given ticket. However, if they want to communicate important details to non-authorized users, for example, to notify staff about a particular delivery, they can add them to the ticket email notifications. Those users will receive the ticket updates by email and can respond to those emails, which will add their comments to the ticket history, but they won’t be able to access sensitive data such as access credentials or network IPs.

While we will still perform these same functions for any DataBank customer, the visibility and self-service access give them even more control over their DataBank environment.

To learn more, stay tuned for future articles in this series or download the DataBank Customer Portal Overview today.

Frequently Asked Questions

The Windy City of Chicago is the third-most populous in the U.S. and the most important Illinois colocation spot. The state is home to many Fortune 500 companies—including Walgreens, Boeing, Caterpillar, and McDonald’s. The Chicago area is also a place where technology and tech expos abound—from conferences, trade shows, summits, and seminars.

Formed in the 1960s, the Illinois Technology and Research Corridor is home to the headquarters or regional centers for many Fortune 1000 companies, including many specializing in research, development, and logistics. Chicago has also become a world-class hub for tech talent and a top startup ecosystem in the U.S., driven by economic diversity and access to technology pros.

World Business Chicago states Chicago now plays in the top-tier tech league of San Francisco, New York, Boston and Los Angeles. Also, as a key launchpad for connectivity and cloud services, hyperscaler cloud providers and social media giants recognize the value of expanding operations in Chicago to provision applications benefitting from the low latency of edge computing based near large end-user bases.

Ideal for Edge Computing and Business Continuity

Chicago’s population base and its location in the Central Time Zone make the four DataBank colocation data centers ideal for delivering edge computing services to the heartland of the U.S. In addition, companies with primary data centers on the east and west coast—as well as those in Minnesota, Kansas and other Midwest states—can utilize the data centers for disaster recovery. Taking this approach ensures business continuity by relying on a remote geographic zone for failover operations.

Our colocation data centers play a role in the mission of the City of Chicago to leverage technology to improve and expand city programs and services. In addition, Chicago aims to develop public access to technology across the metro area and is pursuing other digital excellence initiatives that encourage residents, businesses, and communities to participate fully in 21st century online economic and social spheres.

Downtown and Suburb Combination Delivers Range of Benefits

The four DataBank Chicago data center colocation facilities are conveniently located in both the downtown area and in the suburbs. Together, they offer more than 132,000 sq. ft. of data center space and 14 megawatts of power. These facilities also provide access to a broad range of fiber, Internet, and connectivity options. Each facility offers amenities that include loading docks, package service, parking, conference rooms, office space, break rooms, workspace, and Wi-Fi.

Interested in learning more? Take a closer look at our Chicago data centers, or request a no-obligation quote today.

DataBank’s Chicago Metro by the Numbers

4

Data Centers

13

Total Megawatts

43+

Total Carriers

132,000

Total Square Feet

DataBank’s Chicago Metro Data Centers

ORD1: Chicago Loop

Financial District

600 South Federal Street

8,000 square feet, 1 MW of critical IT load

Explore this data center

ORD2: Downtown Chicago

Near Little Italy

840 S. Canal Street

10,000 square feet, 2 MW of critical IT load

Explore this data center

ORD3: Mount Prospect, IL

25 minutes from O’Hare Airport

800 E. Business Center Drive

28,000 square feet, 2.1 MW of critical IT load

Explore this data center

ORD4: Tri-State Data Center-Oak Brook, IL

30 minutes from downtown Chicago

1808 Swift Drive – Oak Brook, IL

86,000 square feet, 8.8 MW of critical IT load

Explore this data center

*World Business Chicago

Data growth rates are continuing to explode, especially as companies look to capitalize on data-related trends such as IoT, machine learning, AI, and advanced analytics. While all of this has contributed to extreme spikes in all types of data, it has dramatically increased the volume of unstructured data in particular.

Unstructured data is now the most common type of data because it really could be any type of information such as text data, sensor data, video, analytics, and more. As the name suggests, unstructured data is not stored in a typical database format, such as a relational database management system (RDBMS).

Unfortunately, traditional data storage techniques simply weren’t designed to be able to scale to keep pace with such aggressive growth rates. Any company would be hard pressed to add the servers, file systems, and other required components to attempt to scale unstructured datasets using traditional methods. This makes internal processes difficult to manage, and inevitably impossible, and will certainly lead to performance degradation in the future.

Yet turning to public cloud vendors may not always be the best option either. On one hand, hyperscalers can definitely provide the storage just about any company needs for its unstructured data, but most contracts charge fees related to managing data, most notably when it comes to API calls and data egress. While these fees are generally estimated at mere fractions of a penny, they may seem innocent in the beginning. But depending on a company’s strategies and use of data, these charges can quickly add up and lead to high costs that catch everyone off guard.

It’s a real challenge. As companies attempt to collect and store high, and constantly growing, volumes of data, many struggle to find the best approach, one that balances cost, data availability/management, and support for specific business strategies such as geographic diversity, latency, and more.

The DataBank Object Storage Solution

All of these trends, and related challenges, led to the natural evolution and introduction of object storage. For readers new to the category, our explainer on what is object storage provides context for DataBank’s offering. Object storage is a more effective way to deliver simplicity and scalability related to unstructured data, and now DataBank is offering our own Object Storage solution for companies looking for this same simplicity and scalability, all in a much more cost-effective pricing model.

The DataBank Object Storage solution was designed with all of these considerations in mind. DataBank’s object storage solution delivers enterprise-grade cloud storage scalability without the operational overhead of managing hardware. We bundle everything our customers need with one, easy-to-understand price based on each terabyte of storage. We don’t charge for data egress or API calls, an important step in making IT expenses much more affordable and predictable, and eliminating fee surprises later.

Our object storage model is also designed to further reduce complexity by using the industry-standard Amazon S3 API protocol. DataBank customers can move their data to our Object Storage sites from the cloud, their existing data center, or wherever it resides now and enables effective storage and easy retrieval of any amount of data from anywhere.

With the DataBank Object Storage solution, companies can have their cake and eat it, too. In this case, it means they can store their data wherever they like, enjoy scalability and full control, and even eliminate the potential for surprisingly high data egress fees. To learn more, please visit www.databank.com today.

Did you know that DataBank’s Salt Lake City Granite Point campus has its own private 66MW N+1 electrical substation? DataBank’s Salt Lake City substation enhances regional power reliability and supports sustainable data center operations with advanced infrastructure.

This is a key advantage for our customers. Owning our own substation gives us much more control over this vital infrastructure, especially in terms of the location of the substation (much closer in proximity than if it were owned by a utility). We can also be much more proactive in maintaining the substation to make sure it is running at peak efficiency.

All of this adds up to a number of important benefits for DataBank customers. For example, we can deliver more consistent power to the data center, which leads to more reliable uptime and even an improved ability for customers to meet critical SLAs for their customers and prospects. Additionally, such a purpose-built, state-of-the art electrical substation in the SLC campus helps lower costs and increases scalability. For example, the Granite Point campus was designed to accommodate six data centers in size to meet customer demand.

Why are Substations So Important?

An electrical substation is a vital component to any data center location. They are needed to provide reliable electricity for customers in order to maximize uptime, build redundancy, and continue to provide exceptional products and service experiences for their customers.

Substations consist of a wide array of high voltage electrical equipment such as transformers, switchgear, circuit breakers, and other related devices and infrastructure. In the case of the Granite Point substation, transformers will play a key role in “stepping down” the high voltage coming in from an outside transmission line (a 138,000 volt feed) and converting it to 12,740 volts for use in our existing data centers – with the fifth building current under construction and scheduled to open in the spring of 2022.

More Reasons to Consider Salt Lake City and the Granite Point Campus

The combination of power, network, facilities, and the campus setting all ensure that Granite Point is the ideal setting for the high-performance computing, content providers, cloud giants, hyperscale providers, and large enterprises considering colocation options in Utah.

In addition, Salt Lake City is at the nexus of growth for start-ups and venture capital in the tech industry. The Salt Lake City region provides a business-friendly environment and low cost of living that can help any enterprise grow. That, combined with low power costs and ample network connectivity, have led to an explosion of large technology companies putting down roots in the state. With its own electrical substation in the Granite Point campus, DataBank is better able to provide the services and experience these companies require.

Investing in a substation of this magnitude reflects our view of how important the Salt Lake City market is, and the fact that we’re committed to doing all we can to provide the best data services possible for DataBank customers.

Interested in learning more about our Salt Lake City data centers or data center options in any region? Please visit https://www.databank.com/data-centers/salt-lake-city/ today.

Please accept statistics, marketing cookies to watch this video.

Frequently Asked Questions

Making the World Go Round

By connecting data, digital workflows, and ultimately…people, interconnection technologies virtually make the world go ‘round. They’re a core service of most data center colocation providers that supports many-to-many connections among networks for rapid data exchanges as well as an on-ramp to cloud services.

In this blog, we kick off a year-long series about interconnection and data center connectivity, discussing their importance and their history. Throughout 2022, we will provide you with an understanding of the basic interconnection types, the business use-cases to which you can apply each interconnection option, and our solutions that help solve connectivity challenges. Understanding interconnection solutions is the first step toward building a resilient, high-performance network. New to the topic? Learn what are interconnection solutions and why they underpin modern enterprise networks.

Let’s begin with a brief review of why interconnection is so important today, as well as some historical context.

The Importance of the Interconnection Conversation

With digital transformation accelerating market dynamics across nearly every industry, interconnection now plays a major role in helping businesses become more agile and responsive. The new breed of interconnection services from colocation providers enables unprecedented flexibility to distribute computing resources and move intelligence closer to the point at which decisions are made. Businesses can also go to market with new services more quickly and improve services in real-time.

Interconnection is also the fastest-growing segment of the colocation industry. That makes it an important conversation to have with your IT team as you plan the next generation of your IT infrastructure and how to deliver a modern experience to end-users, business partners, and customers.

To achieve this objective, you need to align your interconnection strategy to advanced cloud and digital workflow technologies such as Software-as-a-Service applications and edge computing, as well as 5G and Wi-Fi 6 networks. As an example, to improve the performance of a video service, you may need to join an Internet exchange to peer with broadband network providers. Alternatively, you might want to buy IP transit to connect with mobile network operators to ensure your application runs smoothly on wireless networks.

On the flip side, consider the risk of not utilizing all your interconnection options. You may lock yourself into a data center environment that’s too costly, can’t scale easily, or won’t deliver the performance your applications require. You might also lack the agility to migrate workloads among your various environments. Either scenario can force you to invest too heavily in your legacy systems, trying to get them to deliver the performance they’re simply not capable of.

Evolving from Distributed Networks to Secure and Cost-Effective Connectivity

The history of interconnection goes back to when data networks began to grow rapidly as the mass-market adoption of PCs transformed stand-alone boxes to connected systems sharing information through file servers and local area networks. Ensuing networking innovations in wide area networks along with standards such as Ethernet and TCP/IP led to the distributed computing model.

Then, as technology vendors enhanced switching and routing technologies, telecommunications companies deployed networks that circled the globe. This established the foundation for an even bigger transformation as the Internet linked millions of networks. While Internet service providers could easily connect to each other, they were not equipped to scale. This is when vendor-neutral data center environments emerged, where providers could peer with each other to exchange information.

Along with peering, direct cross-connects and Internet exchanges enabled private, high-speed connections that bypassed the public Internet. This provided more secure and cost-effective connectivity services over greater distances. Today, interconnection networks deliver anytime-anywhere connectivity, made possible by mobile, cloud, and social media technologies.

Up Next: Understanding Interconnection Types

Interconnection represents the umbrella under which many technologies operate to connect networks to networks. It’s important to know the difference between each type to select the right tool for the right job as you establish connectivity among your various data centers and networks. That’s what we will cover in the future blogs of this series.

To learn more about the carrier-neutral connectivity and exchange network ecosystem offered by DataBank and the best way to apply interconnection concepts to your data center environments, visit our website.

Related Resources

Northern Virginia Data Centers
DataBank Completing $4 Million Minneapolis Data Center Upgrade
Interconnection Types and Definitions
What Is the Meaning of Interconnection in IT?

Frequently Asked Questions

Fault Tolerance Requires Avoiding Single Points of Failure

A December public cloud outage was a rare but real occurrence of data disruption. It underscores how IT managers and directors must remind their teams about the need to get back to basics. When managing infrastructures, key tenets include avoiding single points of failure as well as building tolerance into the environment. Recent public cloud outages highlight why resilient cloud computing architectures must include redundancy and failover planning.

Outages that occur to data centers managed by the major public cloud providers are highly visible because many businesses use these platforms. Even for customers who don’t deploy applications in the cloud directly, they, likely, rely on third-party SaaS providers who use these large public clouds behind the scenes for VoIP, email, chat, help desk, call center, website hosting, and other enterprise application services. In fact, avoiding a single point of failure is sound infrastructure design, whether using public cloud or private cloud platforms.

If any of your third-party services happen to run in the cloud, you may not have sufficient redundancy. It is critically important you ask your third-party providers a) who their cloud provider is and b) what their back-up plan is if their cloud provider suffers an outage.

Many small business owners as well as IT pros at the enterprise level might be under the impression that they have distributed their workflows sufficiently because they are working with multiple IT infrastructure partners. However, if your partners are using the same underlying cloud provider, you still have a single point of failure. Also, keep in mind that your public cloud options are not limited to the major public cloud providers with wide name recognition. Other organizations, including Multi-Tenant Data Centers, like DataBank, can provide you with public cloud access as well.

Real Redundancy Requires More Than One Environment

Implementing a failover site that can host your infrastructure should a disaster strike may seem obvious, but this is sometimes forgotten when new infrastructures are deployed or when an existing infrastructure is migrated to a new environment. In fact, the major public cloud providers also emphasize the need for their customers to set up failover infrastructures at secondary data centers. It’s not enough to just deploy a backup site; you also need to test your failover capabilities regularly.

Before the cloud existed, when companies hosted their infrastructure on-premises, they focused on redundancy for all layers of their stack, ranging from the top, the application itself, down to lower levels, including power, cooling, servers, and network devices. As enterprises began to migrate to the public cloud, they stopped worrying about the parts that are outsourced to their cloud provider. They most likely assumed their cloud providers managed all of this. However, for real redundancy, you need more than a single environment.

Make Sure Tolerance Is Part of the Design Conversation

As you design your infrastructures, make sure fault tolerance is part of the conversation. Your system engineers should consider what will happen if, at random, services are shut off coming from a public cloud provider. Hypothetical outages could range from single VMs to entire datacenters, as well as any SaaS platform. Create a failover plan and then test it to see if the business can tolerate the shut-down.

Warning: If your system engineers are uncomfortable with this exercise, that’s a sign the current state of your fault-tolerance capabilities may not be up to your business requirements.

Testing what will happen if public cloud services suddenly become unavailable is critically important. As an alternative, you can build a private cloud or use a colocation data center to get more control over resiliency decisions. You will want to work with a cloud provider who makes decisions based on your best interests, not their own.

For example, you can make sure your data center is not too close to the blast radius of a strategic city. It’s also a good idea to deploy ample levels of back-up generator capacity along with multiple IP transit providers, diverse fiber optic pathways, and a true A-B server and network infrastructure.

Failover Site Considerations

Before deploying a failover site for an existing IT infrastructure or one you’re about to deploy, evaluate the mission-criticality level of the applications supported by the infrastructure. How long can your business afford for that infrastructure and the applications it supports to be unavailable to end-users? They may be internal users managing operations or external users, such as customers and vendors, trying to transact orders.

From there, determine the IT resources and processes to meet the recovery time and recovery point objectives. Another key consideration is just how much control you want to maintain over the primary and failover infrastructures. Public cloud platforms give you the least control, while on-premises data centers give you the most. In between those two extremes are private cloud and colocation data centers.

You may, for example, deploy your primary infrastructure in a colocation data center where you have more control. You can then set up the failover environment in the public cloud, where there’s less control, but where you can run the infrastructure for as long as it takes to restore the colocation data center should that infrastructure go down.

There’s also an added benefit to this approach. You can use the public cloud environment for extra capacity if a flash event occurs and the workload on your colocation data center spikes. In this case, you would address scalability and failover requirements with a single environment.

Portability Facilitates Fault Tolerance

Where you deploy the primary and failover infrastructures will vary according to your business requirements. Given all the variables, it’s best to consult with an IT partner who has data center and hybrid environment expertise. It’s also important to realize that as your applications mature, it may make sense to move your infrastructure to a different type of environment. This means you will need to evaluate your failover plan regularly, perhaps, as often as you test the plan.

The need to migrate infrastructures is where environment portability comes in handy. If you partner with data center providers that give you flexibility as to where you deploy your infrastructures, you have the freedom to migrate either your primary or failover infrastructures when the business or technical requirements warrant. Your choices can include colocation and on-premises data centers as well as public and private clouds.

The key is never to forget about the basics. Mission-critical applications always need a failover plan that’s tested and evaluated regularly. Your business can’t afford the revenue loss in the scenario that customers can’t place orders and if internal teams can’t fulfill those orders. You also risk tarnishing your brand reputation if customers stop trusting your ability to deliver products and services reliably.

Summary:

For more information on how to set up failover environments and build resilience for your mission-critical applications, contact DataBank today.

This article was written by Phil Rosenthal, Vice President of Product and Engineering, DataBank.