Five Smart Questions to Ask About Edge Computing

by Brad Johnson, on Jan 11, 2018 11:28:11 AM

You’ve come to the conclusion that your business needs an edge computing strategy. You’re buried under a mountain of sensor data and your existing business systems just can’t keep up. Edge computing will enable you to take advantage of real-time analytics to reduce costs, prevent equipment failure, and improve visibility into business processes, but you’re just not sure how to get started.


5 Smart Questions_No URL

There’s a lot of noise regarding edge computing and the industrial internet of things (IIoT). Asking the right questions can ensure that your edge computing project has a solid foundation for success. Here are five smart questions to ask about edge computing:

1. How can edge computing help visualize my business in real-time?

Edge computing enables industrial data to be processed more efficiently, because data is processed across multiple edge nodes in parallel. Furthermore, because data is being computed at the edge, it is not necessary to incur latency from a round trip across the local network, to the cloud, and back. This makes edge computing ideally suited for real-time applications. Edge computing can help prevent equipment failure by observing and predicting when failures will occur, so that operators can intervene sooner. Real-time KPIs can empower decision makers with full context into the state of their system. Identifying which information is most valuable to receive in real-time can scope edge computing projects to focus on what’s important.
2. How can I leverage Machine Learning at the edge?
Machine learning algorithms can cut down raw sensor data at the edge, removing duplicates and other noise data. Using Machine Learning to identify relevant information and discard the rest can significantly decrease the amount of data that needs to be transported over local networks or stored in the cloud or other database systems. Leveraging machine learning in edge deployments ensures lower operating costs and that downstream applications can operate more efficiently.
3. Where are there opportunities for integration with existing systems?
According to an IDC Research survey, 60 percent of surveyed IT professionals have five or more analytical databases, and 25 percent have more than 10. Edge computing offers the opportunity to integrate these external systems into a unified real-time experience. While integration traditionally posed a major challenge, by using bridges and connectors, edge computing systems can simply treat external systems as additional nodes in the system. Therefore, identifying opportunities for integration early can maximize the value delivered by pursuing an edge computing solution.
4. What costly events can be prevented if I’m notified sooner?
The real-time advantages of edge computing architectures can lead to the prevention of costly downtime or other avoidable consequences. By identifying which events can be most disruptive to your business, you can more effectively prioritize the desired outcomes for your edge computing project. Whether your goals are to reduce downtime, implement an effective predictive maintenance strategy, or ensure that logistical operations are made more efficient, edge computing can help identify the conditions which bring about failure in real-time and enable operators to intervene sooner.
5. How can I make it secure?
Edge deployments are complex, and every node increases surface area for potential vulnerabilities. Therefore planning for security is critical to the success of any edge computing project. Edge computing allows sensitive data to be encrypted at the source, ensuring an end-to-end security solution. Additional security measures can be taken by partitioning edge services from others, ensuring that if a single node is compromised, the rest of the application can continue operating unaffected.

Learn More
Learn how SWIM uses Edge Computing to deliver real-time edge data insights with millisecond latency for industrial and other real-time applications.

Topics:Machine LearningSWIM SoftwareEdge AnalyticsEdge Computing