3 Ways 5G is Driving Edge Intelligence

5G is closely tied to edge computing. With a whole new “fog” layer created through 5G network infrastructure, 5G will allow companies to feel more secure in their own private networks. This article takes a deep dive into how 5G will drive the transformation of edge intelligence.

In the world of the Internet of Things (IoT), two of the most popular search terms today are “edge computing” and “5G.” However, many miss how the two are interrelated, and that 5G deployments will bring IoT adopters the opportunity to make their business processes more flexible, adaptable, efficient, and smarter.

5G's higher network reliability and durability will drive wider deployment of closed-loop applications. 5G will make companies feel more secure in their own private networks, creating a whole new "fog" layer through 5G network infrastructure. In the same way that cloud virtualization has changed existing business systems over the past decade, the combination of network performance and edge computing capabilities will produce "edge virtualization," which will change the way the Internet of Things operates.

5G and edge computing are closely linked

The technology and expectations of 5G networks are common technical themes. But amid all the 5G hype, three key attributes of these new networks will drive the transformation of edge intelligence:

• Ultra-dense network node deployment
• Increased bandwidth due to higher spectrum
• Dedicated instances enable interoperability and choice between public and private networks

The first two attributes combine to connect 5G to edge computing. Edge computing is a system capability that performs digital computations in devices that exist at the edge of the IoT stack. It adds digital capabilities in the same way that personal computing added new computing power to the enterprise in the 1980s and 1990s. Because 5G networks must deploy many network nodes, up to one per 50 square meters, a large amount of new edge computing will emerge near the edge of the IoT. The physical environment of the edge (i.e., the processing power in the devices) and the virtual capacity (i.e., the processing power in the dedicated edge hardware such as routers, device servers, terminal servers, and gateways) will continue to evolve due to the increase in data collected.

Additionally, the speed of 5G networks will require more and faster computing to manage data flows. Centralized management of the infrastructure will enable cloud-like virtualization and access to new layers of computing. With the addition of private deployments, this new edge computing capability will allow enterprises to implement and manage 5G as a private instance. As with cloud computing infrastructure, security- and privacy-sensitive enterprises will be able to take advantage of 5G in their firewalls and policy guidelines.

The combination of these three attributes will change the way cellular networks and enterprises operate at the edge.

Driving edge intelligence

Edge intelligence is the ability of the edge to adapt, deploy and execute business processes to deliver the desired results. 5G will change the way businesses operate by deploying new business intelligence at the edge and deliver new and better results.

This 5G-driven IoT transformation will bring three key types of edge intelligence:

1. Improving network reliability and durability will drive closed-loop applications

Dense network node deployment will create a more redundant, reliable and deterministic network, as shorter transmission distances and higher bandwidth can reduce latency. In addition to the IoT stack computing layers (cloud, aggregated edge and physical edge), 5G will also deploy a new edge computing layer, the multi-access edge computing (MEC) layer, which will reduce the transmission time required to obtain the cloud computing capabilities required for more complex, big data-driven applications.

5G will enable low latency by providing shorter time slots at the physical radio layer, higher frequencies (such as mmWave), and moving intelligence from the centralized network core to a decentralized network core closer to the edge. The combination of lower latency and more reliable networks will help close the loop for business and mission-critical applications.

Additionally, 5G will provide networking and computing performance that was previously only available in private or proprietary wired systems, such as those used in factory automation. 5G edge automation will be one of the first ways 5G will drive intelligence at the edge.

2. Your own private fog! Security-enabled edge deployment

Many enterprises, especially those in the industrial control and mission-critical market segments, have been slow to adopt public cloud computing and public networks due to a lack of confidence in reliability and security. 5G will address these issues anticipated in 3GPP Release 16 by extending the private LTE network opportunities introduced in 3GPP Release 15.

Private networks based on shared spectrum enable customers to be independent of mobile network operators. Ongoing operations and automation will no longer be constrained by data plan costs and overruns, sensitive data will not have to traverse public infrastructure, and the network will be private rather than shared with other tenants. Combine this network performance with the MEC layer that comes with 5G installations, and industrial operations leaders will find themselves regaining the comforts of in-house wired networks and server rooms, but without the wires and servers.

3. Edge virtualization will support large-scale transformation of installed infrastructure

5G’s functional capabilities will enable closed loops for mission-critical applications and provide enterprise operations leaders with confidence that they can trust the new network and its computing capabilities. However, the more disruptive impact of these 5G attributes will be the virtualization of the network and edge computing, which will help transform the installed base of devices and infrastructure with edge intelligence.

Both the networking and edge computing required to build smart processes will be available and software-configurable—virtualized, deployed, and delivered just like the cloud used by enterprises today. Service providers and manufacturers alike will find that they will have new options for purchasing solutions and tools such as sensors, the networks connecting those sensors, computing and analytics, and closed-loop control/algorithms to improve edge intelligence across their installed base. In addition, proprietary, dedicated connections for all types of applications, including industrial production, traffic control, water, and energy management, can be replaced or enhanced with new capabilities on 5G infrastructure.

5G is very popular in technology trend and prediction discussions, but many overlook the impact 5G will have on business operations in the form of deploying edge intelligence.