Detection in Solar Panel Using ML Algorithm

Dust on solar panels reduces energy generation and increases maintenance costs. Automatic dust detection using machine learning is explored in this research, comparing four models-MobileNetV3, CNN, Efficient Net, and InceptionV3- using webcam images shared on Google Drive. Performance is gauged based on accuracy, efficiency, and computational requirements under various conditions. The study determines the strengths and weaknesses of every model, making it easier to select the most appropriate algorithm for real-time dust detection. Through accurate detection of dust, this technique optimizes solar energy production, reduces maintenance costs, enhances the efficiency of solar panels, extends lifespan, and makes solar energy systems selfsustaining. This research contributes to the development of costeffective and reliable maintenance methods for renewable energy. The best algorithm is InceptionV3 overall, with 99% accuracy and it works well in detecting dust on the solar panel.