Transforming data at the source of collection minimizes latency and enables optimized processing for time-critical applications.
Artificial intelligence (AI) at the network edge is a cornerstone that will influence the future direction of the technology industry. If AI is driving change, then semiconductors are driving the new era defined by machine learning (ML), neural networks, 5G connectivity and the advent of blockchain, twins digital and the metaverse.
Despite recent disruptions to the chip industry due to supply chain and, more recently, macroeconomic factors, the confluence of AI and the Internet of Things (IoT), known as AIoT, is poised to shift the world from cloud-centric intelligence to more distributed intelligence. architecture.
According to IDC Research, a staggering 73.1 zettabytes of data are expected to be generated by IoT devices in 2025. As a result, endpoint data will grow at a CAGR of 85% from 2017 to 2025, bringing intelligence from the cloud to the endpoint to run AI/ML workloads on tiny machines (TinyML). Some of the most disruptive applications include the development of “voice as a user interface” to improve human-machine communication, as well as environmental sensing and predictive analysis and maintenance. Major growth segments include wearables, smart homes, smart cities, and smart industrial automation.
What are the benefits of integrating intelligence into the terminal? Many industrial IoT applications operate in environments constrained by memory capacity, limited computing and battery power, and suboptimal connectivity. Additionally, these applications often require real-time responses that can be mission and system critical. Expecting these devices and apps to work in a cloud-centric intelligence architecture just doesn’t work.
This is where the power of integrating endpoint intelligence scales from standard industrial IoT implementations to what we call AIoT for industrial applications.
Transforming data at the source of collection minimizes latency and enables optimized processing for time-critical applications. Since the data is not processed and transported over the network, security issues related to data transfer and flow are significantly minimized. Another benefit is that data management can be tied to the root of trust at the endpoint, making the implementation impervious to attacks. Because data processing is handled at or very close to the source, we can take full advantage of data gravity and reduce power consumption associated with turning on radios or moving data across the network.
Our commitment to our customers is to lead the industry in terminal computing technology with a wide range of microcontrollers and microprocessors. This has already enabled designers to leverage our ecosystem of IoT and AI/ML building blocks by tapping into a technology ecosystem that includes over 300 commercial-grade software building blocks provided by Renesas’ trusted partners.
Our growing AIoT portfolio also explains our recent acquisition of Reality AI, a new platform powering edge and endpoint AI in industrial IoT applications using Renesas processors. Reality AI automatically finds a wide range of signal processing transformations and generates custom machine learning models, while maintaining traceability in its approach and providing valuable hardware design insights. Models run on nearly every MCU and MPU core available from Renesas, with new ones being added all the time.
This puts an incredibly powerful tool in the hands of designers to help solve their toughest problems, as the model development is specifically aimed at non-visual sensing use cases and based on advanced signal processing mathematics and edge deployment. This enables advanced analytics capable of supporting full hardware design and complete frameworks, including data collection, instrumentation, firmware, and ML workflows. Other solutions simply generate algorithms and models that often represent only 5% of typical project costs, while ignoring the remaining 95% of development expenses.
This approach to AIoT design enables developers to reduce unplanned equipment downtime, improve production efficiency, and perform sophisticated quality assurance tasks that are expensive or difficult to replicate in the current test environment.
In a real-world use case tested under 51 different environmental and load conditions in a three-ton residential HVAC system, Reality AI was able to achieve better than 95% accuracy when detecting and distinguishing between single fault conditions. The test also detected indoor and outdoor airflow blockage and load faults as low as 5% of OEM specifications in heating and cooling modes.
The convergence of AI and IoT for industrial applications is a megatrend with great potential. The acquisition of Reality AI unlocks the potential to combine advanced signal processing with AI at the edge and supported by Renesas hardware, software, tools and ecosystem to provide all the building blocks including you need to unleash your creativity.
Sailesh Chittipeddi is Executive Vice President and General Manager of the IoT and Infrastructure Business Unit at Renesas.
#edge #IoT #disrupting #industrial #market