As drilling rigs become more connected, the volume of captured data that engineers need to manage and analyze increases exponentially. This would not be a problem if data resided on the local network; however, IoT device data is commonly generated outside of the local IT infrastructure—at the edge of the network—in operational environments or remote locations like an oil rig. As a result, organizations often struggle with IoT data growth at remote sites, since they are forced to transmit it to the data center for analysis. Challenges such as data transfer, location, and mobility of the drilling hardware drive the need for local computing. Companies need a practical, cost-effective way to make data-driven decisions in real time at the edge. The answer lies in edge computing. With edge computing, desktop algorithms can now be deployed to drilling rigs for real-time decision making, immediate corrective responses, and minimal production losses.

National Oilwell Varco (NOV) adopted Simulink Real-Time and Speedgoat to prototype their IIoT and edge computing platform for drilling automation. This has enabled them to rapidly and efficiently churn through models to test their performance and stability with streaming data. They chose Simulink Real-Time because of its ability to autogenerate real-time task execution and scheduling without having to perform substantial model restructuring.