What are Edge Servers and How are Edge Servers Used?

By ·Categories: Tech Explained·Published On: May 10th, 2023·7.7 min read·

What are edge servers?

Edge servers are powerful computers placed at the network edge where data computation needs to happen. The physical location of an edge server is often close to the systems or applications that are creating the data that is being stored on, or used by, the edge server. This is in contrast to a more traditional server architecture which commonly stores information in a data center or the cloud.

In the video below, we answer the question: what is an edge server? It delivers an in-depth explanation of edge servers and the technologies they power. Watch the video and keep reading to learn more.

The growth of edge computing 

Before we dive into edge servers, let’s lay the foundation. The move to cloud computing has changed the way businesses operate. With the cloud, it’s easier to store data and access it from anywhere. But in recent years, especially with the growth of IoT and IoT devices, the amount of data being created and stored has grown tremendously. 

According to Cybersecurity Ventures, the amount of data stored in the cloud by 2025 will be 200 zettabytes. For a better representation of scale for that number, that’s 200,000,000,000,000,000,000,000 bytes or 200×1021. And that number is only going to grow. According to Finances Online, the total number of IoT devices is expected to nearly double within the decade, from about 13 billion in 2023 to 25 billion by 2030.

What to do with all that data

With all that data, many organizations realized that relying exclusively on cloud-based data storage and processing can result in massive bills from their internet and cloud service providers. This is because there is a cost associated with both storing the data and transmitting it. 

Another issue, the inherent latency with cloud computing can be potentially costly, or even dangerous as is the case of applications like autonomous vehicles, when making data-based decisions.

What is low-latency computing?

Low-latency is the ability to provide responses to data inputs with minimal delay. A traditional cloud computing architecture has limited capacity to offer low-latency. That is because the data is sent from the edge device to the cloud, processed and returned. This round trip of data to the cloud and back adds precious time which inhibits the ability for that device to act in near real-time in response to the data. 

Edge servers live on the “edge”

When people hear the word server, most think of a climate controlled space in a data center full of endless rows of blinking boxes. Edge servers are the next step in the evolution of server technology. Edge servers are driving advancements in artificial intelligence, machine vision, and deep learning. An edge server is able to bring server capabilities and computation to the edge so that analytics can happen closer to where the data is created and further from the traditional data center environment. 

Edge servers offer low latency performance

To deliver low latency performance, edge servers offer the processing power needed and are located near where the data is produced. They offer the ability to aggregate and process a high volume of data locally with minimal delay. As a result, they reduce the amount of data sent to the cloud and the server can deliver the near real-time responses needed for automation.

Low latency for cobotic solutions

For example, let’s say you have a robotic arm on a manufacturing line. Imagine if a person got too close to the arm. For safety reasons, you would want to stop the robot’s activity or sound an alarm. The system doesn’t have the time to send data to a large analytic center to make that decision. It needs to happen immediately. 

This is an example of how OnLogic edge servers can be used by companies developing cobotic (collaborative robotic) solutions. The low latency can help ensure the safety of team members who work in close proximity to these robots. 

Explore OnLogic’s Line of Edge Servers

Edge servers for cloud repatriation

To save money and reduce latency, there is an increasing trend toward using edge servers for cloud repatriation. This is the process whereby businesses move more of their data handling operations to localized resources. 

The right mix of on-premise and cloud tools depend on your business needs. Edge servers allow organizations to take on complex workloads, process locally, and only send the key data back to cloud applications or to enterprise on-premise data centers. 

Benefits of an edge server for cloud repatriation include:

  1. Reduced operational expenditure on cloud services and data transfers
  2. Reduced latency for critical applications
  3. Increased resiliency by distributing key compute resources physically and logically across the organization
  4. Improved data security by limiting data transfers off-site to essential information

An edge server is specialized hardware designed to aggregate the data locally, reduce bandwidth and enable real-time decision making. They help businesses optimize where and how their data is processed, increase efficiency and help turn information into real business value. 

Using edge servers to offset cloud computing costs

An edge server can make computational decisions ahead of time before sending data to the cloud. This can save you money both on transfer fees as well as cloud storage fees.

Edge analytics is basically trimming the fat at the source so that what’s being transmitted is leaner and more efficient. This makes it a more cost-effective way of dealing with your data. 

Moving the data center to the edge

Once we have taken that data center and moved it on-site (often referred to as on-premises or on-prem), that edge server not only needs compute resources, it needs connectivity and some on-site storage. Once all that information gets generated, sorted, and reacted upon, it has to be able to connect up to the cloud, intranet, or other devices.

Those are the problems that edge servers are solving. They’re delivering high connectivity, high compute and flexible storage capacity. 

What does an edge server look like?

An edge server fits the location you need it to, so there is no “typical looking” edge server. Form factors for edge servers include traditional rackmount servers that range in size, to mini servers that can be installed in locations that don’t have room or resources for a server rack.

A photo showing the front and rear view of the OnLogic Axial AC101 edge server

A photo of several edge servers of variying form factors stacked on top of each other

What features make up an edge server?

As mentioned, an edge server delivers high compute power, flexible storage capabilities, and connectivity. In addition, remote management with a Baseboard Management Controller (BMC) or IPMI is a highly desirable feature.

Our rackmount servers come in a variety of form factors including 4U, 2U, 1.5U, and 1U options. Powered by advanced processors including Intel® 13th generation (formerly known as Raptor Lake), Xeon® and AMD EPYC™, our rackmount servers provide powerful data processing capabilities for near real-time control over your operations.

For example, our Axial AC101 rackmount edge server offers high-performance computing with 13th generation Intel Core processors with Hybrid-Core architecture. Designed with the edge in mind, the AC101 offers configuration flexibility and a full length PCIe slot for the addition of accelerators such as Graphics Processing Units (GPU) or expanded networking cards.

Mini server options include our small but mighty systems – the MC850 available with a scalable Xeon processor up to 24 cores and the rugged Karbon 700-X2-2 also with scalable Xeon processing. Both offer abundant PCIe lanes and option to add a GPU to support AI applications. All that power is available in a small form factor that can fit on a desk, in a NEMA enclosure, or just about anywhere you need.

Karbon 700 Fanless Hybrid rugged computer by OnLogic

Examples of edge server applications

OnLogic offers scalable solutions to enable innovators to handle real-time decision making, analytics, and processing onsite or remotely through a variety of deployment methods. Some examples include: 

  • Industrial Automation: In automation, edge servers are used for real-time monitoring, control, and analysis of data generated by sensors and machines. The resulting data can inform predictive maintenance, process optimization, and immediate response to events.
  • Healthcare: Real-time monitoring using edge servers plays a key role in modern healthcare solutions by monitoring and analyzing vital signs. When paired with vision systems, they can be used to detect deviations from standard patient behavior or falls.
  • Smart Cities: Edge servers are being deployed by municipalities to process data and inform both decisions and actions for traffic management, public safety, and environmental monitoring like air or water quality.

You can think of an edge server as an extension of edge computing. Except, instead of using lightweight, smaller systems, you’re using more powerful, more capable systems. In fact, many are replacing multiple smaller systems with a single more powerful edge server. 

Conclusion

Edge servers are not a one size fits all solution. There are different ways to solve problems using different technologies, connectivity, processing, and form factors. We have edge servers designed to solve even the most complex technology challenges. 

For additional information on edge servers, or for help choosing and configuring the right solution for you, contact us today.

Note: This blog was originally published on December 11, 2019. We updated it for content on May 10th, 2023.

Get the Latest Tech Updates

Subscribe to our newsletters to get updates from OnLogic delivered straight to your inbox. News and insights from our team of experts are just a click away. Hit the button to head to our subscription page.

Share

About the Author: Darek Fanton

Darek is the Communications Manager at OnLogic. His passion for both journalism and technology has led him from the newsrooms of local papers to the manufacturing floor of IBM. His background in news gathering has him always on the lookout for the latest in emerging tech and the best ways to share that information with readers. In addition to his affinity for words, Darek is a music lover, juggler and huge fan of terrible jokes.