How can edge computing operators better plan for modernization projects and use a proven model for implementation success? To get some answers, Senior Technology Editor Bill Wong talks with John Vicente, CTO at Stratus Technologies, about edge computing—what it is and what it’s not.
What are the most common misconceptions about the edge?
I think one of the misconceptions I hear is that edge computing is mostly hype. That edge computing is what people have been doing for a long time or it’s the same as existing private, on-premise enterprise devices like gateways or proxies or DCS and SCADA systems in plant manufacturing.
Another misconception is that the edge computing is basically the Internet of Things or IoT. That it’s sensors and small devices that collect data.
But it’s much more than that. Edge computing is powering the fourth Industrial Revolution through the advancement of technologies in cloud systems, software, computing, communications, advanced storage, and memory. It’s powering what we will come to see as the age of artificial intelligence.
What are key aspects of the edge and edge computing, regardless of industry?
The key aspects of edge computing include low latency, the ability to perform deterministic real-time computing, support for mission-critical or safety-critical use cases, and the ability to extend computing beyond humans to the extremes of the environment and things.
What’s an example of an industry or business that’s been significantly impacted by edge technology?
It’s really interesting that right now, no one industry has truly been transformed or disrupted by edge computing. And that’s because we’re still in transition, the early days of evaluating and finding the optimal use cases. We haven’t seen anyone truly scaling (large) on edge transformation strategies just yet. Alternatively, we have seen edge computing enabling innovation and ROI across multiple industries as varied as manufacturing, energy, smart cities and buildings, transportation, retail, and law enforcement.
Why is real-time data processing so critical?
There are a couple of reasons. First is time criticality. Some decisions or actions need to be executed within milliseconds or even microseconds. Think about autonomous vehicles recognizing a pedestrian or hazard in the roadway. The vehicle needs to make a deterministic decision about how to avoid injury or hazard, and there isn’t time to send that data to a cloud for processing, and then send it back to act on it. Thus, time-critical processing or computing needs to be done in vehicle.
Second, there are many factory production scenarios where large amounts of machine data or vision need to be processed in real-time (e.g., motion control) to perform human-assisted (e.g., safety-critical) robotic control or in the networked coordination of many robots in assembly or production.
next: will edge system slast?