What Is Edge Computing and Why Is It Important?

Source: Yuanwang Think Tank Open Source Intelligence Center

Author: Yizhu

With the deployment of IoT devices and the rapid arrival of 5G wireless technology, placing computing, storage, and analysis close to where data is created has created conditions for edge computing.

Edge computing is changing the way billions of IoT and other devices generate, store, process, analyze, and transmit data. The early goal of edge computing was to reduce the bandwidth costs associated with moving raw data from its creation point to enterprise data centers or the cloud. Recently, the rise of real-time applications that require minimal latency, such as autonomous vehicles and multi-camera video analysis, has driven the development of this technology.

The ongoing global deployment of 5G wireless standards is closely related to edge computing, as 5G can process these cutting-edge low-latency use cases and applications faster.

1. What Is Edge Computing?

What Is Edge Computing and Why Is It Important?

Gartner defines edge computing as “a part of a distributed computing topology where information processing is located closer to the edge, that is, where things and people produce or consume information.”

At its most basic level, edge computing brings computing and data storage closer to the devices that collect them, rather than relying on a central location that may be thousands of miles away. This is done to ensure that data (especially real-time data) does not suffer from latency issues that can affect application performance. Additionally, companies can save money by processing locally, reducing the amount of data that needs to be sent to a central or cloud-based location.

Imagine monitoring equipment in a factory or a networked camera sending real-time video from a remote office. While a single device generating data can easily transmit data over the network, problems arise when the number of devices transmitting data simultaneously increases. Instead of transmitting a live shot with one camera, imagine doing it with hundreds or thousands of devices. Not only will quality suffer due to latency, but bandwidth costs can also be astronomical.

Edge computing hardware and services help solve this problem by providing local processing and storage resources for these systems. For example, an edge gateway can process data from edge devices and then only send relevant data back through the cloud. Or, in cases where real-time applications are required, it can send data back to edge devices.

2. What Is the Relationship Between 5G and Edge Computing?

What Is Edge Computing and Why Is It Important?

While edge computing can be deployed on networks beyond 5G (such as 4G LTE), the reverse is not necessarily true. In other words, unless companies have edge computing infrastructure, they cannot truly benefit from 5G.

Dave McCarthy, IDC’s Edge Strategy Research Director, stated: “5G itself reduces network latency between endpoints and mobile towers, but it does not address the distance to data centers, which can be an issue for latency-sensitive applications.”

Carnegie Mellon University Computer Science Professor Mahadev Satyanarayanan agrees, having co-authored a paper in 2009 that laid the groundwork for edge computing. “If you have to go all the way back to a data center on the other side of the country or the world, what difference does it make if the last hop is zero milliseconds?”

As more 5G networks are deployed, the relationship between edge computing and 5G wireless will continue to be intertwined, but companies can still deploy edge computing infrastructure through different network models, including wired and even Wi-Fi, if needed. However, as 5G offers higher speeds, especially in rural areas without wired network service, edge infrastructure is more likely to use 5G networks.

3. How Does Edge Computing Work?

What Is Edge Computing and Why Is It Important?

The physical architecture of the edge can be complex, but the basic idea is that client devices connect to nearby edge modules for faster processing and smoother operation.Edge devices can include IoT sensors, employees’ laptops, their latest smartphones, security cameras, and even a networked microwave in the office or break room.

In industrial environments, edge devices can be autonomous mobile robots or robotic arms in automotive factories. In healthcare, it can be a high-end surgical system that allows doctors to perform surgical operations from remote locations. Edge gateways themselves are considered edge devices within edge computing infrastructure. The terminology varies, so modules referred to as edge servers or edge gateways may be heard.

While many edge gateways or servers will be deployed by service providers looking to support edge networks (e.g., Verizon’s 5G network), companies looking to adopt private edge networks will also need to consider this hardware.

4. How to Purchase and Deploy Edge Computing Systems

What Is Edge Computing and Why Is It Important?

The methods for purchasing and deploying edge systems can vary widely. On one hand, companies may want to process most of the workflow on their end. This would involve selecting edge devices (potentially from hardware vendors like Dell, HP, or IBM), building a network sufficient to meet use case demands, and purchasing management and analytics software.

This requires a significant amount of work and a lot of internal IT expertise, but it remains an attractive option for large organizations that require fully customized edge deployments.

On the other hand, vendors in specific vertical industries are increasingly marketing edge services that they will manage for you. Organizations wanting to go this route can simply ask vendors to install their own hardware, software, and networks, and pay regular fees for usage and maintenance. Products from companies like General Electric and Siemens in the IIoT (Industrial Internet of Things) space fall into this category.

The advantage of this approach is simplicity and relative ease of deployment, but such highly managed services may not be suitable for every use case.

5. What Are Some Examples of Edge Computing?

What Is Edge Computing and Why Is It Important?

As the number of internet-connected devices continues to rise, the use cases for edge computing that can save companies money or leverage ultra-low latency are also increasing.

For example, Verizon Business describes several edge scenarios, including the scrapping quality control process of manufacturing equipment; creating pop-up network ecosystems with sub-second latency using 5G edge networks to change the way live content is transmitted on-site; using edge sensors to provide detailed images of crowds in public places to improve health and safety; automating manufacturing safety with near real-time monitoring that sends alerts about changing conditions to prevent accidents; and manufacturing logistics aimed at improving efficiency from production to shipping of finished products by creating accurate product quality models using digital twin technology to gain insights from the manufacturing process.

The hardware required for different types of deployments can vary greatly. For industrial users, reliability and low latency are crucial, requiring rugged edge nodes that can operate in harsh conditions on factory floors, as well as dedicated communication links (dedicated 5G, dedicated Wi-Fi networks, or even wired connections) to achieve their goals.

In contrast, connected agricultural users still need rugged edge devices for outdoor deployments, but the connectivity aspects may vary greatly—while low latency may still be a requirement for coordinating heavy equipment movement, environmental sensors may have a greater range and lower data requirements. LP-WAN connections, Sigfox, etc., may be the best choices.

Other use cases present entirely different challenges. Retailers can use edge nodes as in-store information exchange hubs to achieve various functions, linking point-of-sale data with targeted promotions, tracking foot traffic, and providing more capabilities for unified store management applications.

The connectivity aspects here can be simple, with each device having internal Wi-Fi, or more complex, with Bluetooth or other low-power connections serving traffic tracking and promotional services, while Wi-Fi is dedicated to point of sale and self-checkout.

6. What Are the Benefits of Edge Computing?

What Is Edge Computing and Why Is It Important?

For many companies, cost savings are the driving force behind deploying edge computing.Companies that initially adopted the cloud for many applications may have found bandwidth costs higher than expected and are looking for cheaper alternatives.Edge computing may be a suitable choice.

However, the greatest advantage of edge computing is the ability to process and store data faster, enabling more efficient real-time applications that are critical to companies. Before edge computing, facial recognition algorithms for smartphones scanning faces had to run through cloud services, which would take a considerable amount of time to process. With the edge computing model, algorithms can run locally on edge servers or gateways, or even on smartphones.

Applications such as virtual and augmented reality (VR/AR), autonomous vehicles, smart cities, and even building automation systems require this level of rapid processing and response.

7. Edge Computing and Artificial Intelligence

What Is Edge Computing and Why Is It Important?

Companies like NVIDIA continue to develop hardware capable of recognizing the increased demands of edge processing, including modules with built-in artificial intelligence (AI) capabilities.The company’s latest product in this field is the Jetson AGX Orin developer kit, a compact, energy-efficient AI supercomputer aimed at developers of robotics, autonomous machines, and next-generation embedded and edge computing systems.

Orin delivers 275 trillion operations per second (TOPS), which is 8 times more than the company’s previous system, Jetson AGX Xavier. It also includes updates in deep learning, vision acceleration, memory bandwidth, and multi-mode sensor support.

While AI algorithms require substantial processing power to run on cloud-based services, the growth of AI chipsets that can perform work at the edge will see more systems created to handle these tasks.

8. Privacy and Security Issues

What Is Edge Computing and Why Is It Important?

From a security perspective, edge data can present challenges, especially when it is processed by different devices that may not be as secure as centralized or cloud-based systems. As the number of IoT devices grows, IT departments must understand potential security issues and ensure these systems can be protected.This includes encrypting data, adopting access control methods, and possibly using VPN tunnels.

Moreover, the different requirements for processing power, electricity, and network connectivity among devices can affect the reliability of edge devices. This makes redundancy and failover management critical for devices processing data at the edge to ensure that data can be correctly transmitted and processed when a single node fails.