Texas semiconductor company Silicon Labs has revealed details of how some of its customers are preparing for the launch of the Matter standard using SoCs it launched earlier this year.

The BG24 and MG24 devices focus on Matter, AI and machine learning (ML), multiprotocol and Bluetooth. More than fifty global users participated in the alpha programme, and Silicon Labs has shared some of the successes from early adopters.

Viessman, a heating and refrigeration provider, for example, is taking advantage of the low-energy requirements of the BG24 and MG24 SoCs to create battery-powered heating and refrigeration products.

The MG24 has been designed for smart IoT devices targeting Zigbee, OpenThread and Matter protocols with features that include a 2.4GHz radio, low power consumption, 1.5Mbyte of flash and 256kbyte of RAM. It also offers a wide selection of peripherals and low current consumption, making it possible for Viessmann to introduce its battery-powered ViCare heating system and refrigeration products.

The ViCare system integrates Zigbee gateway functionality into appliances with no additional equipment required. The MG24 also has an integrated analogue-to-digital converter and DC-DC converter, both of which reduce the size of the PCB and make it possible to design very small form factor applications.

Edge Impulse is using the BG24 and MG24 to deliver an embedded ML platform for companies building AI-aware products. Embedded developers can use Edge Impulse to design automated data labelling, pre-built digital signal processing and ML blocks, live classification testing and digital twins that are less complex, more contextual and easier to develop.

SensiML is using the built-in AI and ML accelerator on the BG24 and MG24 SoCs to explore intelligent applications. Silicon Labs and SensiML partnered to deliver rapid development of TinyML smart IoT sensing applications.

Using Silicon Labs’ ML development tools, designers can enhance embedded applications with AI and ML capabilities, even in low-power wireless IoT devices. ML computing at the edge enables a variety of smart industrial and home applications including sensor-data processing for anomaly detection, predictive maintenance, audio pattern recognition such as glass-break sensing, and simple-command word recognition. The SensiML analytics toolkit accelerates the development of optimised AI sensor models for intelligent endpoints allowing insights to be generated locally in real time at the embedded device.

“Integrating Edge Impulse with the built-in machine learning accelerator on the BG24 and MG24 enables up to four times faster processing of machine learning algorithms with up to six times lower power consumption while offloading the main CPU for other applications, enabling smarter and faster edge devices with long battery life and new potential workloads,” said Zach Shelby, CEO at Edge Impulse. “By minimising latency and traffic over the internet for time-sensitive applications, we are strengthening privacy and security, taking full advantage of MG24 and BG24 right at the edge.” 

Nanoleaf, a smart lighting vendor for the home, is using the MG24’s support of Matter to build smart home products that can integrate into the user’s ecosystem of choice. With the MG24, Nanoleaf hopes to lead the way for the Matter standard to create a unified smart home rooted in open communications and flexibility.

Tuya, an IoT development platform, is using the MG24 and Matter to unify the 400,000 IoT products it supports that account for 200 million devices every year. It created a development platform that has accumulated over 510,000 registered developers from over 200 countries and regions. Smart devices powered by Tuya are sold through 100,000 online and offline sales channels worldwide.

In selecting the MG24 to be part of the Tuya platform, the company looked at three characteristics. First, it had to have enough computing capability and RAM to manage the systems the company is helping its customers build. Secondly, Tuya needed a variety of IO to build more types of IoT devices. Finally, it prefers chips that support Matter so its customers can join in the smart home connectivity standard.

Leedarson, which helps manufacturers build, test and deploy IoT products, is using Matter on the MG24 so its customers can take advantage of interoperability and have confidence that a single application can scale across projects. It specialises in the R&D and manufacturing of smart home devices to design, build, test and deliver products that help consumers experience the potential of the IoT. The company has been an enthusiastic driver of the Matter standard.