Edge computing adoption secrets for IIoT
|Ramya Ravichandar in IoT Wednesday, June 12, 2019|
How true edge computing solutions with real-time data enrichment benefit industrial and commercial organizations embarking on the path toward digital transformation.
Over the past year, many industry players increased their focus on edge-based solutions, and organizations are now beginning to understand the value edge computing can bring to their Internet of Things (IoT) and Industrial Internet of Things (IIoT) projects. According to a recent Spiceworks survey, 86% of companies with more than 5,000 employees plan to adopt IoT solutions and 65% plan to deploy edge computing technology by 2020.
Defining the edge
Like the introduction of IoT and digital transformation, the market adopted edge terminology without considering its exact characteristics. Some edge solutions claim they can treat data at the edge while relying on the cloud for data processing. Although the cloud is a good place to train machine learning models, it cannot deliver high fidelity real-time streaming data analysis. These “weak” edge solutions lack a crucial step in the edge computing process, real-time data enrichment.
The secret behind “strong” edge computing solutions
Strong edge computing starts with an efficient complex event processor (CEP) that cleanses, normalizes, contextualizes and aligns “dirty” or raw streaming industrial data as it’s produced. By utilizing the complex event processor for data pre- and post-processing, “strong” edge solutions can shrink ML models by about 80%, enabling them to be pushed much closer to the data source on constrained compute for optimal benefits. Also, a “strong” edge solution includes integrated ML and AI capabilities, all embedded into the smallest (and largest) compute footprints. Now, the power of the CEP does not eliminate all cloud involvement; in fact, edge solutions rely on the limitless resources of cloud environments to train existing machine learning models. Organizations will discover edge devices that generate analytics on live streaming data should regularly send insights back to the cloud, specifically data that represents unusual activity warranting a shift in the current models. Then, once the models are fine-tuned, they are pushed back to the edge, resulting in a constant, closed-loop process that generates much higher quality predictive insights to improve asset performance and process improvements.
Strong edge solutions promise numerous benefits, including:
- Massive reduction of data sent to the cloud. When analytics move to the edge, there is a massive decrease in the amount of data pushed across the network. This reduces data storage, data-handling, and bandwidth costs.
- Better real-time insights. By keeping the computing close to the data source, edgified machine learning models can detect emerging patterns in real-time and enable immediate action.
- Predictive maintenance for all. Because an edge-based system can handle all incoming sensor data, it can predict maintenance needs across all equipment in operation, allowing for a comprehensive understanding of all upcoming maintenance needs.
- Improved yield. Manufacturers can increase productivity and reduce downtime by rapidly detecting and addressing suboptimal performance.
Many different factors will contribute to increasing edge adoption, including the vast increase in data, and the need for lower latency requirements, higher fidelity analysis, and substantial cost advantages. In the next few years, 75% of enterprise-generated data will be processed at the edge, up from less than 10% today - which will move many pilots to production with improved business outcomes and unlock the trillions of dollars of value creation for IIoT.
This content is made possible by a guest author, or sponsor; it is not written by and does not necessarily reflect the views of App Developer Magazine's editorial staff.