This project focuses on advancing imaging technologies for Irradiance and cloud cover (albedo) measurement using drone swarms over large solar PV plants. By leveraging high-resolution imaging sensors and AI-driven data processing, the project aims to enhance solar forecasting accuracy. Validation will be conducted in a realistic simulation environment ensuring a cost-effective and scalable approach to aerial environmental monitoring.

Advanced Imaging for solar efficiency

Harnessing drone vision for cloud analysis: the project explores the use of high-resolution RGB-D imaging technologies mounted on coordinated drone swarms to capture real time cloud dynamics. Unlike static ground sensors aerial imaging provides a broader and more adaptive perspective, improving solar irradiation modelling. The research focuses on optimizing image acquisition, processing and interpretation to maximize energy forecasting accuracy.

Simulation driven technology validation

Testing imaging solutions in a relevant simulation / digital twin environment: to ensure robust performance all imaging and drone coordination strategies will be validated in a high-fidelity simulation environment like Gazebo. This approach enables precise testing of image processing algorithms, sensor calibration and autonomous flight patterns under realistic weather conditions eliminating the need for costly physical prototypes.

Collaborative research and industry impact

Advancing imaging in renewable energy applications: this project brings together industry experts and academic experts in imaging, AI, and renewable energy. It offers an industrial application for recently developed but still theoretical drone coordination and solar mapping strategies. By refining airborne imaging methodologies the outcomes will support improved solar plant efficiency, better grid integration and scalable solutions for environmental monitoring beyond solar energy applications.