Smart sensors, battery monitors, and other small electronic devices are being asked to run machine learning algorithms, but they lack the computing power and energy to do it well. This project develops methods for these resource-limited "edge" devices to share knowledge with each other, so that a network of cheap, low-power sensors can collectively achieve the accuracy of a much more powerful system. The problem is that today’s AI-at-the-Edge devices—the fastest growing electronics sector globally, with a 20.64% compound annual growth rate—are constrained by tight energy budgets and limited physical access. Current approaches either demand too much power or fail to scale. This research tackles that gap by creating low-cost, energy-efficient mechanisms for knowledge transfer between devices. If successful, the new methods could deliver machine learning accuracy with 3–4 orders of magnitude better energy efficiency than existing systems. The practical impact would be felt in applications like environmental monitoring and electrical battery safety control, where continuous, intelligent sensing is needed but high-performance hardware is impractical. The project validates its approach through simulations, prototyping, and a concrete IoT-scale demonstration.
View original technical description
Modern information and communication technologies produce electronic devices that are deployed at the edge, such as for example smart sensors acquiring information about environmental conditions. Such devices are increasingly expected not only to perform simple data conversion from one form to another but also perform computations such as data analysis, classification and even decision making. Collectively such devices are called AI-at-the-Edge, which arguably form the fastest growing electronics technology in the UK and the World (CAGR 20.64% in the next five years). A key challenge of enabling such devices with intelligence is the fact they are limited in resources, such as compute power, energy budget, physical accessibility. So, the main question is how to equip such resource-limited devices with machine learning (ML) capabilities? To tackle this challenge this project will develop low-cost (e.g. energy-efficient) mechanisms for sharing knowledge between edge devices. The project's success will be measured in terms of its new methods capable to deliver knowledge transfer between edge devices helping scale up their ML accuracy with at least 3-4 orders of magnitude energy efficiency compared to existing AI-at-the-Edge systems. The project outcomes in theory and design methodology will be validated by means of extensive simulations, prototyping, and testing, and, ultimately, via an embodiment of the proposed solutions into a concrete IoT-scale application, such as environmental monitoring and electrical battery safety control.
Plain English summaries and category classifications on this site are generated by AI and may not perfectly reflect the original research.
Is something wrong? Let us know