Harvesting energy from ambient light combined with artificial intelligence, can revolutionize the Internet of Things. Based on smart and adaptive operation, the energy consumption of sensor devices is reduced, and battery waste is avoided. (Image: Ella Maru Studio)

Newcastle University researchers have created high-efficiency, sustainable solar cells that harness ambient light to power Internet of Things (IoT) devices.

A research group from the School of Natural and Environmental Sciences, Led by Dr Marina Freitag, created dye-sensitized photovoltaic cells based on a copper(II/I) electrolyte, achieving an unprecedented power conversion efficiency of 38% and 1.0V open-circuit voltage at 1,000 lux (fluorescent lamp). The cells are non-toxic and environmentally friendly.

Published in the journal Chemical Science, the research has the potential to revolutionize the way IoT devices are powered, making them more sustainable and efficient, and opening up new opportunities in industries such as healthcare, manufacturing, and smart city development.

"Our research marks an important step towards making IoT devices more sustainable and energy efficient. By combining innovative photovoltaic cells with intelligent energy management techniques, we are paving the way for a multitude of new device implementations that will have far-reaching applications in various industries,” said Freitag.

The team introduced an energy management technique, employing long short-term memory (LSTM) artificial neural networks to predict changing deployment environments and adapt the computational load of IoT sensors accordingly. This dynamic energy management system enables the energy-harvesting circuit to operate at optimal efficiency, minimizing power losses or brownouts.

This study demonstrates how the synergy of artificial intelligence and ambient light as a power source can enable the next generation of IoT devices. The energy-efficient IoT sensors, powered by high-efficiency ambient photovoltaic cells, can dynamically adapt their energy usage based on LSTM predictions, resulting in significant energy savings and reduced network communication requirements.