Wevolver and Syntiant are creating a series that explore the work of innovators and the future of pervasive AI. Syntiant is developing ultra-low-power AI processors. Because they believe in the importance of innovation, Syntiant is engaging in these fireside chats with engineers and designers who are on the cutting edge of their field.
Wienke Giezeman’s company The Things Industries uses something called the long range, wide area (LoRaWAN) networking protocol, which provides long range, low power and secure characteristics that are ideal for telemetry use cases – think the Internet of Things and connected devices, but on a level that helps enterprises dive deep into their data. The problems that his customers face are quite diverse – but the ecosystem that The Things Industries builds, that creates networks, devices and solutions - has been a powerful answer. It’s being used by companies to monitor everything from bearings on conveyor belts, to cattle, or activity in smart buildings.
“How this works is that you have a small sensor, with pretty small data points. You might learn that a bearing is almost broken, a cow is gone, or there’s somebody in the room. What these data points have in common, is that they're very small, and they're almost binary. Second, the networks are most of the time not available – and if it’s WiFi or cellular, it will make the sensor consume a huge amount of energy. LoRaWAN fits in a place where you want to have small pieces of data, but you need to be able to install a sensor that can last for a long time, because you don't want to end up replacing your batteries every few weeks on these sensors. You need the right sensor for the right problem.”
Using AI on edge IoT devices enables real-time integral feedback on critical data points. “By grading quality information out of rough sensor data, you can catch a data point with a high quality measurement that lets you know if a part of your system needs immediate attention, maintenance, or even if you could take a preventative measure.”
Edge AI helps harness the data, alleviating the fact that often there isn’t enough bandwidth to send all the data points that a sensor measures to the cloud for processing. As Edge AI and fields like tinyML further grow and develop they promise to power much future growth of IoT applications. And importantly, these approaches can also reduce the environmental impact of IoT systems.
Running more and more devices and computation comes at an environmental cost. Therefore, IoT systems need to reduce their energy consumption and environmental impact.
Wienke: “There’s been an emergence of a lot of e-waste regulation, which we highly support, and with the products that we make, we tried to ensure use of common batteries and tap into existing circular economies that have proper recycling facilities. This is a major topic in IoT, and it's also very important, because you need to manage the devices properly.”
IoT can also enable systems and organizations to reduce carbon emissions. The right measurements and data can improve efficiency or lower energy usage such as in smart buildings where lights and climate control are only used when there are humans around.
As Wienke says “It's not going to generate any value when it ends up in a dashboard. [..] If you see a graph of your IoT sensor, then you're only at 10%, you need to inject that data into the enterprise IT systems.”
This video is part of a series of fireside chats in which Wevolver and Syntiant partner to engage with global innovators. In previous discussions we spoke with Arduino CEO Fabio Violante, Star Wars Animatronic Designer Gustav Hoegen and Fashiontech Designer Anouk Wipprecht. I encourage you to stay tuned and to follow Syntiant's profile for more of these conversations.