An AdaBoost Ensemble Model for Fault Detection and Classification in Photovoltaic Arrays
Ehtisham Lodhi, Fei–Yue Wang, Gang Xiong, Adil Dilawar, Tariku Sinshaw Tamir, Hub Ali
Abstract
The photovoltaic (PV) arrays are susceptible to numerous faults. Fault diagnosis is essential in improving a PV system’s output power, reliability, and life span. This research paper suggests an AdaBoost Ensemble Model (AEM) approach for detecting and classifying PV system faults. The AEM approach includes several weak base learners stacked sequentially so that they learn from the mistakes of prior weak learners to produce an improved predictive model. This study considers open-circuit fault (OCF), short-circuit fault (SCF), and degradation fault (DF). A complete quantitative evaluation of the suggested AEM approach is compared to earlier machine learning classification techniques to diagnose faults in PV arrays. The results of the proposed AEM approach are superior to those of the traditional methods, with an accuracy of 97.84 percent in fault detection. The findings indicate that the AEM approach improves classification performance while preserving a powerful generalization capability for PV system fault diagnostics. Consequently, the proposed AEM approach is more effective at detecting and classifying faults in PV array systems.