Verónica Castro-AllendeAn organization that wants to go this route can just ask a vendor to install its own hardware, software and networking and pay a regular fee for use and maintenance. IoT offerings from companies like GE and Siemens fall into this category.
This approach has the advantage of being easy and fairly headache-free in terms of deployment, but heavily managed services like this might not be available for every use case.
What are some examples of edge computing?
Only as the number of online-connected devices continues to climb, so does the number of use cases where edge computing can either save a company money or take advantage of extremely low overhead.
Verizon Business, for example, describes many edge scenarios including end-of-life quality control processes for manufacturing equipment, using 5G edge networks to create flash network ecosystems that change how life content is streamed with post-next latency, using edge- enabled sensors to provide detailed imaging of crowds in public spaces to improve health and safety, automated manufacturing safety, which leverages near real-time monitoring to send alerts about changing conditions to prevent accidents, manufacturing logistics, which aims to improve efficiency through the process from production to shipment of finished goods, and creating precise models of product quality via digital twin technologies to gain insights from manufacturing processes.
The hardware required for different types of deployment will differ greatly. Industrial users, for example, will put a premium on reliability and reduced- overhead, requiring rugged edge nodes that can operate in the harsh environment of a factory floor, and dedicated communication links (private 5G, dedicated Wi-Fi networks or even wired connections) to achieve their goals.
Connected agriculture users, by contrast, will also require a steep edge device to cope with outside deployment, but the connectivity piece could look very different–low-latency might also be a requirement for coordinating the movement of heavy equipment, but environmental sensors are likely to have both higher range and lower data requirements. An LP – WAN connection, Sigfox or the like could be the best choice that.
Different use cases offer different challenges completely. Retailers can use edge nodes as an in- store clearinghouse for a host of different functionality, tying point- of- sale data along with targeted promotions, tracking foot traffic, and more for a unified store management application.
The connectivity piece these could be simple in-house Wi-Fi for every device or more difficult, with Bluetooth or other low power connectivity servicing traffic tracking and promotional services, and Wi- It reserved for point- of- sale and self- checkout.
What are the benefits of edge computing?
For some companies, cost savings alone can be a driver to deploy edge- computing. Companies that immediately embraced the cloud for some of their applications may have discovered that the costs in bandwidth were higher than expected, and are looking to find a less expensive alternative. Edge computing might be a fit.
Significantly, though, the biggest benefit of edge computing is the ability to process and store data faster, enabling more efficient genuine- time applications that are essential to companies. Prior to edge computing, it would take a long time for the visual recognition algorithm to be processed by the cloud-based service used by smartphones to scan people’s faces in order to recognize their faces. The algorithm could run directly on an edge server, gateway, or even on the smartphone itself if it had a model for edge computing.
This level of quick processing and response is necessary for applications like electronic and augmented reality, self-driving cars, smart cities, and actually building automation systems.
AI and edge computing
Companies like Nvidia keep creating hardware that acknowledges the need for more processing at the edge, including modules with built-in AI functionality. The Jetson AGX Orin developer kit, a small and energy-efficient Artificial supercomputer aimed at creators of robotics, automatic machines, and next-generation embedded and edge computing systems, is the company’s most recent product in this field.
275 trillion operations per second ( TOPS) are delivered by Orin, an 8x improvement over Jetson AGX Xavier, the company’s previous system. Updates in deep learning, vision acceleration, memory bandwidth, and support for bidirectional sensors are also included.
While cloud-based services and significant amounts of processing power are needed to process AI algorithms, as AI chipsets become more capable of doing the work at the edge, more systems will be developed to handle those tasks.
Security and privacy issues
Data at the edge can be problematic from a security perspective, especially when it’s being handled by various devices that might not be as safe as unified or cloud-based systems. It’s critical that IT recognizes possible security risks and ensures that those systems can be secured as the number of IoT devices increases. This includes using access-control techniques, data encryption, and perhaps VPN tunneling.
The dependability of an edge device can also be impacted by different device requirements for processing power, electricity, and network connectivity. For devices that process data at the edge to guarantee that the data is delivered and processed effectively when a second node goes over, redundancy and failover management are essential.
