AI • May 18, 2023

Demystifying 5G and Edge AI

As boundaries blur between the digital and physical world, our work, ways of living, and communication transform. WiFi and broadband have become indispensable today. Imagine your day with a slow internet connection (no internet is not even an option!) Video calls have become ubiquitous. We are connected like never before - people with people, people with devices, and devices with each other.

The amount of data is growing exponentially, and so is the need for better connectivity.

Edge computing is at the core of this innovation. It will empower companies to deliver ultra-low latency and high-quality solutions to their end-users. And with the advent of 5G, we will witness the next wave of wireless connectivity. It will give the ability to support a large number of connections simultaneously while improving the speed, reliability, and latency of consumption devices and IoT touchpoints.

This blog aims at demystifying Edge computing, it's coming together with 5G and some of the most relevant opportunities and challenges that await us.

What Is Edge Computing?

Edge Computing is the practice of placing the compute and storage resources locally, closer to the end-user. Gartner defines edge computing as solutions that facilitate data processing at or near the source of data generation.

For example, in the Internet of Things (IoT), data generation sources are sensors or other embedded devices. Edge computing serves as the decentralized extension of the campus networks, cellular networks, data center networks, or the cloud. The edge could be on the customer's premises or the base of cell towers. Additionally, edge computing can occur on smaller pieces of hardware like routers or WiFi hotspots where it makes the most sense. Not sending data to a distant central data center for computing power implies faster network speeds, lower latencies, and more reliable network connections.

Multi-access edge computing architecture
Fig 1. Multi-access edge computing architecture
Image Credits Source

While Edge computing is a concept, Multi-access Edge Computing (MEC) is a standard architecture concept. MEC, formerly known as mobile edge computing, is an ETSI initiative that initially focused on placing edge nodes on the mobile network. But with the evolution of research, the term was expanded to include additional access points that may also make up the edge of the network. These include IoT-enabled sensors, edge data centers, connected sonography machines. For the purpose of this blog, we will use edge computing and MEC interchangeably.

How does 5G fit in with Edge Computing

Let's think of them as 'Mac and cheese' - two things that are better together than individually!

5G and MEC are two independent technologies that are closely related to each other for success and viability. Many leading applications and business use cases utilize the 5G technology for higher bandwidth, lower latency, and a dense layout of cell sites to make the last mile stronger.

This is where MEC makes its grand entry to take it up a notch. The critical role of MEC is to reduce congestion in the network. By moving functions, content and processing closer to the subscriber, the performance of the applications is vastly enhanced, thus improving the utilization of network resources.

While 5G isn't a must-have for device connectivity and edge computing, quality of service (QoS) improvements justify the switch. The unique 5G network design advantages are a lower data plane latency and a significant decrease in the control plane latency.

At the risk of making this sound like a food blog, think of it as your favorite pizza place. It has a fast order-taking and servicing mechanism (the promise of 5G) and has many franchises spread across town (the edge leverage) for even quicker delivery.

Additionally, by leveraging the 5G technology, the enterprises would be free from network requirements for connecting with the cloud. Instead, they focus on developing applications. The 5G service provider takes care of the rest, including edge hosting, infrastructure, and networking. It is a win-win for the CSPs and the enterprises as it opens new arrays of business opportunities.

What does the 5G Ecosystem entail

As Edge computing evolves, new business possibilities will arise, which again will fuel this ecosystem. The stakeholders include the communication services providers (MNOs, fixed telcos, cable companies), big cloud providers, data center providers, CDN players, tower companies, real-estate companies, and industries (Retail, Manufacturing, Media and Entertainment, and Healthcare).

Indicative list of 5G Edge ecosystem players
Fig 2. Indicative list of 5G Edge ecosystem players

Industry Applications and Use Cases:

Autonomous/connected vehicles - The key requirement for autonomous/connected vehicles is real-time information sharing and processing of a multitude of data points. To name a few, the road infrastructure, the position and movement of pedestrians and other cars on the road, and weather conditions. The low latency that is critical for autonomous vehicles to operate safely, will be achieved by leveraging the MEC technology. Vehicles can rely on the edge rather than wait for information to be processed on the cloud.

AR/VR and mixed reality applications - Apart from providing new immersive experiences, leveraging AR for supporting field service teams in carrying out maintenance are sought-after applications. Edge computing offers real-time information on mobile devices. It supports applications that are too heavy to render on the end device and have low latency needs. Multi-user collaboration is another example where AI-enabled insights could be shared without any lag.

Cloud and multiplayer gaming - The low latency needs of cloud gaming calls for a highly optimized network. The massive multiplayer games and the live streaming of gaming tournaments are on an unprecedented rise, resulting in higher volumes of data to be processed in real-time. 5G implementations with advantages of virtualization and MEC will be vital in delivering a quality experience to gamers. This is a promising area for leveraging 5G and edge, the proof being in the partnerships. Many telecoms, cloud gaming companies, and cloud providers have come together to advance in this arena. For example, Microsoft's partnership with SK Telecom, Vodafone, and T-Mobile to test its Project xCloud cloud-gaming service on live networks.

Real-time drone detection - In December 2018, hundreds of flights were canceled at Gatwick airport near London, England, following reports of drone sightings close to the runway. With 140,000 passengers and 1,000 flights affected, it was the most significant disruption at Gatwick in years. Incidents like these increase the need for solutions to detect any unauthorized drone entering a secure area. Real-time detection and path tracking using MEC will reduce time to react in a situation of breach or threat. Airports, prisons, and hospitals are some of the places that will immensely benefit from such a solution.

Healthcare - With 5G and Edge computing impacting multiple industries, applications in healthcare are the need of the hour. Telehealth and round-the-clock patient monitoring become more manageable and effective through IoMT coupled with 5G and edge computing. Given the times we live in now, contact tracing and infection control have become significant concerns. Use cases such as PPE and mask detection in crowds have more relevance now than ever. The promise of low latency and faster data processing capabilities will enable more accurate and timely diagnosis in life-critical situations.

Video Analytics / Computer vision - One of the most compelling use cases of Video analytics is enhancing the real-life experience of event audiences such as sports, concerts, and other shows. Verizon collaborated with the NFL and AWS to debut the first 5G MEC mobile game for fans in-stadium at Super Bowl LV, called NFL Ultra Toss. Other examples of video analytics at the edge include surveillance and security use cases such as intrusion detection in high-security areas such as data centers, real-time person tracking, ensuring and measuring COVID compliance.

What lies Ahead for Edge Computing

With any innovation comes a set of unprecedented challenges, and edge computing with 5G is no different. DDoS attacks that were easier to tackle in a centralized landscape will now raise more concerns with the possibility of targeting individual MEC nodes. The 5G MEC ecosystem is still evolving with many collaborations and a promise of new revenue streams for all the entities involved.

As a result, its global adoption alongside 5G will experience significant growth in the next few years.

Getting a little 'edgy' yet? It's about time we do!

Get in touch with our experts to explore our MEC capabilities.

Read more on "Quantiphi's Partnership with Google Cloud to deploy intelligent video analytics and low-latency Edge AI solutions."

Written by

Misheka Goswamy

Thank you for reaching out to us!

Our experts will be in touch with you shortly.

In the meantime, explore our insightful blogs and case studies.

Something went wrong!

Please try it again.