In this paper, a Tiny Machine Learning (TinyML) model is developed for fault classification of photovoltaic (PV) modules. A dataset based on visible images of healthy and faulty PV modules has been collected at different locations. The examined defects are: discolored cells, cracked PV modules, bubble formation, bird droppings, dirt accumulation, sand deposit, corrosion, shading effect, and snail trails. The Edge Impulse platform has been used to develop and optimize our TinyML model, which is then integrated onto a low-power microcontroller for a real time application. The simulation results show a good overall classification accuracy of 92% whereas experimental results demonstrate the ability of the developed TinyML model to be deployed for real-world and low-cost applications.
