Close to the edge: How to realise the benefits of edge computing for IIoT
You may well have heard of the ‘intelligent edge’, as Microsoft puts it – the future of computing, on multiple devices, the blurring of the physical and virtual worlds, driven by huge amounts of data, as well as artificial intelligence and machine learning. But how can organisations make the most of this opportunity?
A new whitepaper from the Industrial Internet Consortium aims to shed some light on this process and how to architect an edge computing implementation.
It is important to note first of all, the paper outlines, that while technologically the definition of the ‘edge’ can vary, from a business perspective it all depends on the business problem or objectives to be addressed.
Take the example of a ‘dumb’ thermocouple managing temperature on a pump. With edge computing capability, the pump can be defined as having exceeded a defined threshold and then shut down in milliseconds. If there is no need for connectivity to perform the function – it can be used for notification in this instance – then the edge must be defined at the device level as the key objective can be achieved even if connectivity is interrupted.
The benefits of edge computing, as the report puts it, are improved performance, greater compliance, data privacy and data security, as well as reduced operational cost. Performance is simply improved because more data in more locations more quickly can be collected. “The edge is not merely a way to collect data for transmission to the cloud, it also processes, analyses and acts on the collected data at the edge within milliseconds and is therefore essential for optimising industrial data at every aspect of an operation,” as the report puts it.
It’s worth noting as well that part of the reason the edge exists is because moving everything to the cloud, as was the strategy a few years ago, doesn’t quite work. “Due to network latency and the cost to transmit a large amount of data, more logical tasks remained at the edge,” the report notes. “With the improvement of the processing power and capability, the amount of tasks performed on the edge will continue to grow.”
The report also explores various use cases, from fleet tracking to predictive maintenance. The latter, around connected elevators, is the most interesting. Edge computing devices are connected together to diagnose the operational status of the elevator, from noise, vibration, temperature, and more. The project needs two requirements – for the edge devices to have containers and open APIs to allow third parties to develop applications, and supporting 24x7 monitoring.
“Organisations adopting an IIoT strategy need to understand what data is available, how to use it to drive industrial processes, and how to orchestrate, manage and secure data/compute,” said Lalit Canaran, VP at SAP and co-author of the paper. “This paper and subsequent technical report will enable enterprises to unlock the full potential of the edge-cloud continuum and drive the business outcomes enabled by next-generation IoT devices, machine learning and AI.”
You can read the full report here (pdf).
- » Connecting the smart home: The history of wireless protocols – and why they matter
- » Facebook’s latest acquisition shows interest in UK AI industry
- » Microsoft unleashes Windows 10 IoT Core Services
- » Sense and sensor ability: How AI and connectivity will help each other grow
- » BlackBerry CEO believes it will be a decade before self-driving car prevalence