Edge analytic or edge computation is set on a path of massive growth. However, in the context of a factory or commercial building, edge architecture can pan into the diversified system architecture. Edge computation can happen with sensor electronics, in gateway devices and in a factory cloud, which may be a server inside the factory. And the whole system may or may not be connected to a public cloud (AWS or Azure) depending on what end customers want. On top of that, all the analytics results have to be available to HMI or the display panel of a PLC.
Due to the lack of a unified or standardized architecture of Industry 4.0, it’s extremely important for OEMs (those who want to make smart machines) to be cognizant of the reality that their customers (manufacturing plants) may or may not allow cloud. They may or may not have a factory cloud. They may or may not want the data to be displayed on a PLC. They may want the system to be incubated into any of the major Industrial IoT PaaS platforms like Azure IoT PaaS or MindSphere.
SignaGuard Edge Platform is diversified to interact with of all the variations in edge architecture.
EDGE – PROS AND CONS
MachineSense (www.machinesense.com) runs its SaaS on IaaS IoT analytics fully in edge and it has been deployed in different sites since 2017. For almost two years, all the advanced statistical and machine learning algorithm has been running in edge instead of the cloud for MachineSense.