Neil Stroud has over 25 years of experience in the semiconductor industry. He has worked for well-known companies such as Arm, Intel, NEC and Samsung. Over the past 15 years, Stroud has been an industry expert in the field of functional safety and has worked closely with companies in the automotive, industrial, avionics and transportation segments. Since November 2020, the electrical engineering graduate has been Vice President Marketing & Business Development at CoreAVI.

The Industrial Internet of Things is generating more and more data. This data complexity needs to be mastered. What role does edge computing play in this?

Stroud: Given the amount of data being generated, it is neither efficient nor effective to transfer all the data to the cloud for processing. That's why edge computing plays a fundamental role here. There is an increasing need for secure operation of IoT applications, for example in industrial automation and factory environments where machines and robots work in close proximity to humans. In these safety applications, timing is critical and must take place directly on site - the additional latency of cloud computing is unacceptable. For these safety applications and markets, CoreAVI offers solutions because we see an increasing demand for secure edge applications such as secure AI/ML and computer vision.

At the edge, sensor data is pre-selected, software applications are processed or even AI computation is performed. What should users consider with regard to the edge software landscape? Which technologies should/must be taken into account?

Stroud: There are a number of key trends in software related to edge computing. Firstly, with the innovations taking place in the IoT landscape, it is becoming increasingly difficult to integrate the number of software elements from different sources. Therefore, interoperability and open standards are critical to the success and acceleration of software distribution.

CoreAVI was founded in the UK in 2005.

© Pixabay / CC0

Secondly, virtualization and container architectures are inevitable as the consolidation of workloads becomes more common to meet the significant increase in computing power requirements. In terms of security, this approach enables the separation of secure and non-secure software functions so that they can coexist on the same hardware platform and work correctly independently of each other.

Finally, open source solutions are becoming increasingly important. This is a particularly important trend in the field of industrial automation, which has traditionally been built on proprietary closed-source stacks. CoreAVI's software stack is based on open standards such as Vulkan and OpenVX.

As the tasks grow, so do the hardware requirements. What should users pay attention to when choosing the right edge computing hardware?

Stroud: Apart from the obvious selection criteria such as I/O (input/output), heat dissipation and size of the hardware platform, the bigger challenge is to select the right amount of computing power not only for current applications, but also to leave enough headroom for application development and innovation. This is always a delicate balance as it has a direct impact on cost and potentially complexity. The biggest cost factor in any project is increasingly the software, so this should be developed with scalability and reuse in mind. The underlying hardware platform is increasingly becoming a commodity. So the only option is to design the software stack and the application in such a way that they do not require a specific hardware architecture. CoreAVI has pioneered this philosophy for security applications, focusing on true scalable solutions that enable developers and operators to scale efficiently across multiple hardware platforms, reducing the total cost of ownership.