Typically, when we think of artificial intelligence (AI) tools, we think of software residing in the cloud. After all, AI models require massive compute power, and as they grow, that power needs to scale rapidly. Such support is a perfect fit for cloud computing.
However, as Sean Saul explores in his recent article in Control Engineering, that cloud connectivity can be a challenge for operational technology (OT) environments. Sean explains,
“OT teams are typically reluctant to connect systems to the cloud. Cloud connectivity can be impacted by network constraints impacting performance, and in some jurisdictions data governance and regulatory requirements could limit adoption. These are critical issues for organizations focused on safety, availability, and competitive advantage.”
And even if OT teams were willing to connect their control systems to the cloud, the latency of using cloud resources would be too high for real-time, mission-critical operations. The solution, Sean explains, is emerging AI software built to operate much closer to underlying processes—delivered via edge hardware platforms and software-defined architectures.
High power, on prem
What OT needs is a way to bring the high performance of cloud-native applications into an on-premises environment for security, stability, and low latency. Modern edge solutions deliver that capability. Technologies like Emerson’s DeltaV™ Edge Environment are designed to securely connect to control system data and provide a local sandbox for high-level execution and experimentation. Sean shares,
“Automation solutions providers are equipping edge platforms with AI accelerators, allowing variants of models like those deployed in the cloud to run on local systems. The goal is to deliver solutions that can run on-premises—delivering the security and latency necessary for OT environments—while still providing reasoning capability and generating natural language responses that are verifiably accurate without fabrications.”
That means OT teams can connect the rich, contextualized data from the DeltaV distributed control system with AI tools running on the powerful hardware provided by the edge environment.
But that’s only the beginning. With the emergence of the Enterprise Operations Platform (EOP), AI models needing extremely low latency will creep ever closer to the underlying process dynamics. Ultimately, as a software-defined, next-generation automation system becomes a reality, such software will run in the same virtual environment as the control system.
“With extremely low cycle times, these software-defined systems will help operators determine the best action in complex scenarios by using AI to capture and embed knowledge, making it available on demand. These systems will also have the capability to automate operator-guided, multi-step workflows, dramatically reducing the time from analysis to problem resolution”
Orchestration is essential
What will be key to making this vision for seamless AI a reality is a flexible foundation. Some AI technologies will still reside in the cloud—planning tools, performance engineering software, enterprise virtual advisors, etc.—as they will not need the real-time, low-latency performance of the control layer.
Other technologies, such as reliability and sustainability tools, are likely to reside in edge environments, where they still gain near-real-time access to data from critical technologies.
Making all these solutions work together across cloud, edge, and core control systems will require an orchestration architecture to drive optimal performance across the automation stack. All software solutions will need continuous access to contextualized data from the intelligent field, through the edge, and into the cloud. That seamless data availability and continuity will be accomplished via the data fabric built into the EOP.
Perhaps what is most exciting is that the emerging EOP and its associated data fabric empowers teams to start moving toward this AI-driven future today. Even as AI technologies continue to evolve, companies can start investing in the existing software that will deliver value for their facilities, knowing that their foundation is built on seamless connectivity. By embracing a foundation for next-generation automation, teams no longer have to sacrifice the tools that drive operational excellence.
