Solar Panel Fault Detection Using Low Complex Convolution Neural Network Deep Learning Model

The use of Photovoltaic (PV) systems to collect energy from the sun has emerged as a viable option for meeting the world's increasing energy demands while reducing dependency on fossil fuels. At the core of these systems are solar panels, which convert sunlight into power. However, like other technical equipment, solar panels are susceptible to defects and failures. Recently, solar panel defect detection has become essential for ensuring the effective and reliable operation of PV systems. This paper presents a solar panel fault detection model using deep learning. We propose a low-complexity Convolutional Neural Network (CNN) consisting of Convolution 1D, activation, max pooling, and dense layers. The 1D CNNs automatically extract relevant features from the input data, detecting patterns in various positions of the input sequence. Low-complexity CNNs have fewer parameters and memory requirements, which is crucial for devices with limited resources. The proposed model achieved a fault detection accuracy of 98%.