Edge computing: 4 use cases for the industrial sector

Given the relationship between edge computing and IoT, it’s no surprise that the industrial sector – which has spawned its own IoT subcategory, aka Industrial IoT (IIoT) – is rife with use cases of edge computing.

The industrial sector – which we use here as a general term for businesses such as manufacturing and energy (think heavy machinery manufacturing and power plants, for example) – was actually one step ahead of the state-of-the-art concept: industrial SCADA systems. In short, they are local, isolated control systems responsible for all kinds of critical industrial and other on-site processes. You could think of them as precursors to modern high-tech architecture.

“Industrial SCADA is a cutting-edge form and has been around for over 30 years in some way,” says Andrew Nelson, Principal Architect at Insight. “Most facilities will have an isolated control system in place today.” In fact, they often have multiple such systems and processes, and edge IT deployments are increasingly likely to augment or even replace them.

Industrial environments themselves are fundamentally edge locations—meaning they’re typically away from a centralized data center or cloud—and so they’re perfectly suited for the growing adoption of the edge. An oil and gas platform in the middle of the ocean? This seems to meet anyone’s definition of “the edge”.

On that note, the industrial sector deals with inherently challenging sites: Nelson points out that edge computing use cases overlap with other contexts such as warehousing or logistics, but often involve more hostile environments.

All of this makes the industrial sector a good sector to consider in terms of edge use cases. How do industrial CIOs and other IT and business leaders actually envision and implement state-of-the-art infrastructure and applications?

[ Building an edge strategy? Also read Beat these common edge computing challenges. ]

First, an overview of the background, courtesy of Red Hat technology evangelist Gordon Haff: There are basically two main streams with industrial edge computing.

“On the one hand, sensor data – often filtered and aggregated – flows from the operational/workshop level to the core,” says Haff. “On the other hand, code, configurations, master data, and machine learning models flow from the core – where development and testing takes place – to the factory.”

This has a lot of bearing on cutting-edge strategy in various sectors. The edge-to-core flow is where IT managers have to decide what really needs to live at the edge and what can or should be kept in a centralized cloud or data center.

“The idea is that you often want to centralize if possible, but stay decentralized if necessary,” says Haff. “For example, sensitive production data may not be allowed to leave the premises, or you need to protect your running industrial processes from failure due to network issues outside the factory.” (The latter is a big part of the SCADA connection – in many industrial environments unexpected downtime is not an option.)

The flow from the core to the periphery is largely about mental health and operational efficiency. As with edge architecture in general, you can’t expect to send a human IT professional every time you need to update a configuration or patch a system at an edge location. In the industrial sector, says Haff, there could be hundreds of factories with thousands of processes running: “Automation and consistency are key,” says Haff.

Ishu Verma, Technical Evangelist at Red Hat, adds that core-to-edge flow is how organizations can extend the same practices and technologies they apply in the cloud or on-premises to their edge nodes, even under harsh conditions. most difficult industries. settings.

“This approach allows enterprises to extend emerging technology best practices to the edge – microservices, GitOps, security, etc.,” says Verma. “This enables the management and operations of edge systems using the same processes, tools, and resources as with centralized sites or the cloud.”

Edge computing in manufacturing and energy

Within these two-way flows, here are four examples of how industrial organizations are using edge computing.

1. Streamline real-time operations

These traditional SCADA and other control systems are like monolithic or legacy applications in many other industries: important, but not particularly easy or flexible to use in the modern environment.

“Traditional SCADA and control system infrastructure tends to be closed and vendor specific,” says Nelson. “An IoT/edge deployment can facilitate real-time operations in a single window rather than hopping between systems.”

“Many industrial facilities will have multiple control systems that may or may not integrate. The IoT/edge use case can pull data between systems, correlate events, and predict outages.”

Monitoring and predictive maintenance are good examples in this category: a plant’s sensors and instrumentation can be used for real-time operations and help industrial operators better plan when critical maintenance and further work will be required. It was more difficult in the past due to data silos – a familiar challenge for CIOs in many companies.

“Many industrial facilities will have multiple control systems that may or may not integrate,” Nelson says. “The IoT/edge use case can extract data between systems, correlate events, and predict failures.”

2. Running AI/ML Workloads at Industrial Sites

Latency, i.e. reducing or eliminating it, is one of the main drivers of edge computing strategy. This is especially true for AI and machine learning applications, as well as other forms of automation that require data – and lots of data – to be effective.

There is huge potential for AI/ML and automation in Industrial IoT, but also huge data and latency implications.

“Getting smart machines to work seamlessly at the edge is data-intensive,” says Brian Sathianathan, CTO at Iterate.ai. “Good AI requires data. A great AI requires a plot of data, and he demands it immediately.

This can become problematic in the context of that first Red Hat Haff stream described above: sensor data flowing from the edge to the core.

“I’ve seen situations in manufacturing plants where there was ‘too much’ data to go from a robot on the floor, through the LAN, then to the cloud and back,” Sathianathan says. “That’s not good because, as manufacturing CIOs know, decisions have to be made instantaneously to be effective.”

If latency is an issue, then real downtime is a complete killer – especially in industrial environments (where a data outage or network glitch could, for example, shut down a gas pipeline) and related segments like the making.

While some downtime is generally acceptable in standard IT environments, this is simply not the case in manufacturing. Costs of production line downtime due to failing edge applications can run into the hundreds of thousands of dollars per minute. There is simply no room for error.

Keeping necessary data at the edge will be an enabler that marries edge computing with AI/ML use cases and minimizes the “too much data” scenario described by Sathianathan.

Having state-of-the-art applications that can automatically monitor and optimize energy consumption at industrial sites isn’t just good corporate citizenship, it’s potentially a huge boon to the bottom line.

3. Improve energy management

Having state-of-the-art applications that can automatically monitor and optimize energy consumption at industrial sites isn’t just good corporate citizenship, it’s potentially a huge boon to the bottom line.

There is great pressure to monitor power consumption and control load in manufacturing and industrial applications,” says Nelson of Insight. “In the industrial space, there are massive savings just by turning off or metering the electrical load during peak hours.”

In fact, rising energy consumption and costs in industrial organizations is a big enough issue that it was the subject of a presentation and a conference paper in 2021: A System of energy management with Edge Computing for industrial installations.

It’s not exactly a range reading, but CIOs and other IT managers can certainly appreciate its starting point: designing a cutting-edge application that can automatically adapt and optimize power consumption based on the fluctuation pricing could be a use case that really moves the needle.

[ Related read ESG strategy: 3 ways CIOs can play a pivotal role ]

“Reducing the cost of electricity has become an urgent problem to be solved”, write the authors of the report. “Meanwhile, remote monitoring of connected devices and pushing intelligence to the edges of monitoring devices are becoming critical in the industrial IoT.”

4. Improve employee safety and site security

You’ll see a pattern here: industrial edge/IoT use cases feed off of the massive number of sensors and other machines in these environments. But it’s not just about machines, it’s also about people. Nelson says the industrial edge also offers significant opportunities for employee safety and site security.

“Tracking employees and contractors and alerting them when they’re not where they’re supposed to be working is a big deal” for security, Nelson says.

Like many cutting-edge applications, this is a category that typically involves or integrates with other technologies (like AI/ML). It’s also where seemingly lo-tech devices — the ubiquitous employee ID badge, for example — can get a makeover.

“Computer vision, RFID, and BLE can all be leveraged in this use case,” Nelson says. “Linking building security badge readers and security cameras is a useful integration.”

Or try another security item universally recognized for its size, which predates the edge, the cloud and, well, digital computing as we know it: the hard hat.

“They make headsets with built-in sensors that can be tracked through WiFi hotspots for this use case,” Nelson explains.

[ Discover how priorities are changing. Get the Harvard Business Review Analytic Services report: Maintaining momentum on digital transformation. ]

Sherry J. Basler