Edge AI and IoT — Pros, Cons, and Use Cases

What is Edge Computing?

When we’re talking about edge computing versus cloud computing, we’re discussing where your data resides and where the actual computing happens.

In cloud computing, data that’s been collected from a computer or device is uploaded to the cloud, where it’s stored and processed. Think Google Drive, Dropbox, or iCloud.

In edge computing, that same processing happens at or near the source of the data instead of sending it over the cloud. In IoT, that means the computing happens at the “thing” level – the connected device.

If your IoT edge device incorporates AI, the algorithms that govern your AI are processed locally on a hardware device, using the data that your IoT sensors collect. For this reason, edge AI doesn’t need a network connection to do its job.

How Will Edge AI Benefit IoT Networks?

Edge computing makes it possible for AI technologies that are typically serviced by a SaaS offering to work offline, or in situations with low latency or low bandwidth requirements.

This capability makes edge AI especially valuable for IoT. Throughout an IoT development project, you have to make tradeoffs between performance and network latency. Pushing all the computation into the cloud is much faster and gives you more control, but can also cause issues with responsiveness, negatively impacting the customer experience.

If your device can’t access a strong network signal, things start to fall apart.. Additionally, cloud computing opens the data up to more security risks that don’t arise when the computing is done locally.

With edge AI, companies can deploy their machine learning models to run locally on edge devices, helping to counteract issues with both performance and latency. AI systems can deliver real-time feedback to enhance mission-critical applications. Because the data isn’t being sent through the cloud, it’s also more secure.

Edge AI Use Cases: The Future of Industrial IoT

In the short term, edge AI will most likely benefit industrial-heavy applications such as manufacturing and supply chain. The investment required to implement edge AI systems is still high, so most industry leaders will need to see a clear ROI to justify the decision.

In the Industrial Internet of Things (IIoT), that ROI may be more clear. For example, in manufacturing, you could use edge AI to enable predictive maintenance, troubleshooting and anticipating issues within a complex physical system. IoT sensors could manage and optimize the supply chain. Edge AI could even be used to automate product testing and inspection, increasing quality while reducing resource expenditure.

The Downsides of Edge Computing for IoT

There is still a large vacuum for standards and processes in the IoT – especially the edge computing space. Many vendors are working on ideal processes and protocols here. However, they are lagging years behind the infrastructure that we take for granted when building on the open web.

To develop AI products that can be deployed to the edge not only requires capabilities in the AI/ML space, but also in hardware, software, networking, and of course security. Over time, this will become easier as projects such as LF EDGE become more widely adopted. These standards will allow more tools to be developed in the open-source space. Companies can then use those tools to build powerful systems, without engineers having to reinvent solutions on the networking and security side.

What about my existing IoT network?

Can you implement edge AI on your existing IoT network? It depends heavily on the existing infrastructure.

If your current architecture already consists of programmable gateways, you might be able to deploy ML models to these nodes if the compute capabilities are sufficient. Chances are, however, that if the architecture wasn’t designed from the ground up to support advanced edge computing applications, that it might be difficult.

What’s the best way to get started with edge AI in IoT?

Start by considering the full spectrum of devices – the IoT devices or “things” aren’t the only new hardware you need to think about. A wide variety of components, including micro-datacenters and IoT gateways in the field, will become part of networked environments. Your edge infrastructure needs will depend on how much latency your system can tolerate along with the complexity of the operations you need to perform on the data.

AI on the edge is just now starting to break out of research and into implementation. You can expect lots of exciting developments in this space over the next few years.

To learn more about how IoT development can enhance your product & service offerings, drop us a line today.