Kinetic Edge Alliance member, Latent AI gives their perspective on leading the way on AI data at the edge.
Edge computing and AI must work hand-in-hand to provide a continuum of services from device to cloud, inferencing and extracting value at different layers. The industry calls this multi-stage value extraction and it is, in fact, the only sensible way to analyze vast amounts of data from a very large number of sensors .
Take, for example, 4K drone-mounted cameras capable of collecting hundreds of gigabytes of data per hour. The current method of analyzing data—piping it up to the massive data centers or the cloud—quickly becomes cost-prohibitive and impractical with data sets this large, especially if the data needs to be processed immediately. Is it feasible or scalable for the future to have your favorite cloud vendor send their container truck with petabytes of storage, just to haul it off somewhere?
Let’s consider an example from the oil and gas industry to highlight how a drone-based inspection system could use multi-stage value extraction. Oil and gas pipelines can be thousands of miles long and snake through an immense landscape. Pipe sections are generally fitted with analog gauges to measure things like pressure and flow. By employing an edge AI-enabled surveillance drone to capture these analog gauge images, it’s possible to isolate the gauge images and send only that critical information to the next compute layer. Then only the localized needle data is processed for the exact reading. What results is actionable intelligence sent to the historian or the next process.
According to Cisco, in 2020, we generate about 22 exabytes of data every four hours globally. This pace is not slowing down anytime soon, as the number of devices coming online is exponentially exploding. If data is the new oil, then we need data refineries working alongside the whole continuum, from edge to core. These data refineries will be composed of many different innovative solutions, but we believe the future of data includes intelligently and efficiently applying AI across the entire edge-to-core continuum.
P.S. Don’t become a data hoarder!
