Control Engineering research: Edge computing, AI
Control processes, SCADA and HMI are leading applications for edge computing; enhancing control capabilities is a common use of artificial intelligence.
- Understand Control Engineering research on use of edge controllers, artificial intelligence and machine learning for automation, controls and instrumentation.
- Review key findings from the research.
Controller research insights
- Control Engineering research on edge computing and artificial intelligence (AI) provides insights about how those in automation are using each.
Control Engineering subscriber research on “Edge computing and artificial intelligence technology” was conducted in February and March 2023 to learn how those technologies are being used for automation, controls and instrumentation. About half of respondents agree edge computing is a better target for artificial intelligence (AI) software/algorithms than programmable logic controllers. Computing power, networking capabilities and reliability are the leading reasons respondents are using AI with edge computing. The top reasons respondents use AI/machine learning (ML) include access to capabilities previously unavailable in other software (61%) and to enhance traditional control methods (58%). Summary results follow.
Click here to download the research.
Edge computing for automation, controls, instrumentation
Among survey respondents, 98% are using edge computing in some way. Edge computing is most commonly used in control processes (51%) and supervisory control and data acquisition (SCADA) software (50%) for automation, controls and instrumentation applications and with human-machine interface software (46): This is a three-way tie, considering margin of error.
Controls, automation or instrumentation technical support is used, or expected to be in use, for edge computing by 28% of respondents. Another 21% cited operational technology (OT) or engineering department support.
Half of respondents said edge computing is used because it enables a more agile and responsive monitoring and control system over other compute or logic devices, as well as providing next-generation control solutions like AI/ML. About the same number said it supports better decision making by faster processing of real-time data.
Among respondents, 88% use cloud resources with edge computing; analytics (55%) and memory/storage (50%) are the top cloud resources.
Artificial intelligence, machine learning
AI/ML was acquired by 53% of respondents through an application that an automation, controls or instrumentation vendor or distributor provided to them.
Among respondents, 73% are using AI/ML for controls, automation or instrumentation technical support; 47% for OT or engineering department support.
The top reasons respondents are using AI/ML include access to capabilities previously unavailable in other software (61%) and to enhance traditional control methods (58%).
After initial startup and regular operation, 22% of respondents cite they update the data model that helps guide the AI/ML application in real time; 16% weekly; 12% twice a year and 11% daily.
Edge computing, AI and ML
About half (51%) of respondents agree edge computing is a better target for AI software/algorithms than programmable logic controllers (PLCs).
Computing power (38%), networking capabilities (37%) and reliability (32%) are the top three reasons why respondents are using AI with edge computing.
The automation, controls or instrumentation person, team or department within respondents’ companies are most involved in the specification and/or purchase of edge computing technologies, while the information technology person, team or department is most involved when acquiring AI/ML applications.
Methods for the 2023 Control Engineering edge computing, AI research
To do the research, subscribers were sent an email from Control Engineering asking them to participate in this study. The email included a URL linked to the questionnaire. Information was collected from Feb. 8 through March 23, 2023. With 121 respondents, the margin of error for the results was +/-8.9% at a 95% confidence level.
Think again about edge computing and AI can be applied to automation, controls and instrumentation applications.
Mark T. Hoske is Control Engineering content manager, firstname.lastname@example.org. Amanda Pelliccione, director of research and awards programs for CFE Media and Technology, conducted the research and assembled the related report, including much of the information above from the executive summary.
KEYWORDS: edge controllers, AI/ML use in automation
Are you applying edge computing and AI/ML?
Do you have experience and expertise with the topics mentioned in this content? You should consider contributing to our CFE Media editorial team and getting the recognition you and your company deserve. Click here to start this process.