Sponsored Article
An introduction to the edge
Author : Jim ten Broeke, Advantech Business Development Manager IIoT Europe
02 March 2023
I think the first thing to understand is that while we talk about ‘the edge’ as if it is a single point in an architecture, in a real system, there are actually many cascaded levels of edge device lying between the physical world and the enterprise. The exciting thing is that we’re seeing innovation in each of these different levels.
At the enterprise, there’s an increasing trend towards the use of edge servers, where enterprise cloud functionality is transparently and seamlessly brought on-premise, reducing communications overhead, accelerating responsiveness and increasing resilience. This is happening with both content delivery server applications and in the move towards high-level application edge servers, running at area, building or even individual process level.
At the communication edge, besides the well-reported opportunities being presented by the emergence of new wireless communication options such as LoRaWAN, NB-IoT and public/private 5G, we’re seeing much more awareness of the threats posed by cyber-crime.
Whilst there are still a lot of enquiries for traditional edge gateway functionality such as protocol conversion, communications media translation, data aggregation and event detection, the market is now equally concerned with the security features of the edge devices – how they protect against unauthorised access by individuals, or prevent unauthorised or hacked code being installed and run.
At the same time, users are realising that remote management of these devices is critical to enable the fastest possible response to security patch rollouts across an installed base, as well as offering cost-of-ownership benefits by reducing truck rolls.
Perhaps the most exciting area is at the lower edge levels, closest to the physical assets and operations. Here, the big trend is towards artificial intelligence and machine learning embedded within edge devices.
Until relatively recently, AI implementations relied on expensive, very high bandwidth computers, and teams of specialist data scientists to create and refine the data models needed. This meant that only very high-value operations could enjoy the advantages offered by AI.
Recent advances in edge inference have now brought the price of implementation right down, and corresponding advances in machine learning, and the availability of pre-trained models for many common applications mean implementation times are often measured in days or weeks, rather than months or years.
We’re seeing this trend in all sectors, but especially within the factory. AI and ML embedded in the edge use connected cameras to automate optical inspection, providing faster and more accurate detection of non-conformance as well as addressing the problem of an ageing workforce within manufacturing.
In warehousing, edge intelligence optimises the movements of AGVs while AI within the AGVs enables them to operate autonomously. On production lines, AI optimises efficiency across multiple machines, analysing yields across different operating scenarios.
Again, using connected cameras, edge AI provides worker protection through intelligent, 24/7 monitoring of safety zones around moving machinery. Face and number plate recognition are improving access security in factories and offices. The list just keeps growing.
As you can imagine, this explosion in the adoption of edge computing at all levels within a system architecture means that there is an extremely diverse range of both hardware and software solutions required. The perception remains that AI and ML require very large amounts of processing power, but for some applications, we’ve implemented them in something as small as a cellular router.
As in other areas of edge computing, no one size fits all solutions, and even in the same application, the topology of the installation may determine if it’s better to fit several small distributed edge devices, or to bring signals and data into a larger, more centralised unit.
In some sectors, there is still the factor of specific certifications required, and in any event, environmental conditions and therefore edge device characteristics vary between different applications, industries and implementations. Having a wide variety of edge solutions to call upon is therefore a key benefit for suppliers of enabling technology such as Advantech, allowing us to provide an optimum fit for any scenario.
Contact Details and Archive...