Note: This is the second in a series of blogs on IoT and the Edge. The previous one is ‘Where is the Edge?
One can make almost any technology work on a small scale in a ‘point solution’ with isolated business benefit. To scale up to an application having a positive effect on wider business performance requires a solid plan for what you expect the technology to do for your business. To be able to build on your initial success, consider the business strategy of your Internet of Things (IoT) project at the start.
Original Equipment Manufacturers (OEM) who offer IoT based after-market condition monitoring services do so to differentiate themselves from competition, to make customers sticky, and potentially to enter brand new markets/create new revenue streams. To effectively deploy IoT within this strategy, planning for robust network infrastructure is critical to be successful. Edge computing provides a means to assure reliability of the service to avoid unplanned downtime with high customer satisfaction. End-users at plants adopting IoT for near real-time predictive maintenance, process optimization and visibility also need a robust architecture with edge computing to assure high data integrity and avoid missed alerts.
Getting beyond a ‘Science Experiment’
Many successes have occurred with IoT pilot projects and production applications for predictive maintenance and related asset performance management (APM). Dozens of case stories have documented the application of IoT and analytics to equipment condition monitoring. When an issue is sensed, the software sends an alert that allows maintenance to be proactive and prevent unplanned downtime. This avoids lost production, millions in missed revenue, and safety issues.
In many cases, these successes are pilot projects that some would call a science project, i.e., it proves the technology while providing some business benefit. Here, ‘small data’ from a specific piece of equipment combined with specific analytics identifies a problem. These pilot projects and science experiments are a good start. Now, the challenge becomes extending this success to ‘big data’ across many devices for a more transformational benefit and competitive advantage.
Building on Success
Extending initial successes requires a robust architecture that can scale-up. Point solutions hit barriers with network delays, disconnects and other perturbations that lead to lost data, missed alerts, and/or false positives. Then, users lose confidence in the program, and go back to the old way of doing things. Don’t get “painted in a corner” with no way to build on initial successes. As Stephen Covey says “Begin with the end in mind.”
A robust approach involves ‘fog computing’ with resources at the edge for data acquisition, buffering and processing. Here, processing small data occurs at the edge in either a gateway for legacy systems, or a modern device containing the needed intelligence. Being close to the device, edge systems reduce network traffic by discarding unimportant data and using data to respond to issues in real-time. Only important data is retained and is transferred to the cloud. With data from many devices in the cloud, big data and analytics address enterprise needs which includes visibility, KPIs and business process automation.
One can easily visualize IoT on a small scale with a few devices feeding data to a cloud platform with analytics. But, what happens with hundreds or thousands of devices? When accumulated across all the devices, consider the near continuous occurrence somewhere of network latency, interruptions and equipment issues somewhere in the fleet. Scale needs a more robust approach.
Robust Architecture with Edge Computing
A robust architecture is inherently more resilient to faults and other perturbations. With edge computing, data storage and computation occurs at the edge for more real-time issue identification and to buffer data during network issues. Then, send to the cloud only the data needed for more sophisticated analytics as, for example, would apply to longer-range predictive maintenance. This pre-processing at the edge also helps reduce network bandwidth and cloud server needs.
Begin with the end in mind and set your strategy for what you want IoT to achieve for your business. Then assure a robust industrial IoT architecture based on the application and situation.
- End-users who purchase condition monitoring services from an OEM need to be confident that when issues arise, they will be alerted. These users should examine their equipment suppliers’ IoT strategy, and make edge computing part of the selection criteria.
- OEMs offering after-market condition monitoring need to consider their brand protection, i.e. the expectation of near zero unplanned downtime. Using edge computing provides the robust architecture needed to assure no missed alerts.
- Plant owner operators who are considering IoT for process optimization and real-time visibility know that spurious network interruptions occur in their plant for a range of reasons. As this impacts data integrity and trust, users lose faith in the application and go back to the old way of doing things. Use gateways with edge computing to assure buffering when temporary network interruptions occur.
About Intel IoT
The Intel® IoT Platform includes end-to-end reference architectures model and family of products from Intel and its ecosystem that works with third-party solutions to provide a foundation for seamlessly and securely connecting devices, delivering trusted data to the cloud, and delivering value through analytics. Harnessing these connected “things” and turning massive amounts of raw data into actionable insights will have a transformative impact on organizations. Intel offers open and scalable products with a thriving ecosystem of OEMs and partners for a comprehensive portfolio of end-to-end hardware and software with built-in security.
The Intel IoT Platform provides a design blueprint that details how partners can securely connect and manage a fleet of “things” from small sensors to huge server farms that make up the cloud. Intel’s products are used by partners at the edge, in the network, and for powering the data center. The range of Intel’s IoT products includes processors (from Intel® Quark™, Intel® Atom™, to Intel® Core™ and Intel® Xeon®), networking devices, real-time operating systems (Wind River), and security software. IoT gateways based on Intel technology act as data routers and filters from sensors to the cloud.