Intelligent fault identification strategy of photovoltaic array based on ensemble self-training learning

Identifying Photovoltaic (PV) array faults is crucial for improving the service life and consolidating system performance overall. The strategies based on the supervised Machine Learning (ML) approach represent an attractive solution to identify the PV array faults. However, attainable labeled data to train supervised ML algorithms present challenges in practice. Therefore, this work introduces a novel strategy that employs an ensemble learning concept in conjunction with a semi-supervised learning approach based on a self-training philosophy to realize the faults diagnosis of an arc, line-to-line, power tracker unit, open-circuit, and partial shading, under different of aspects which can directly be impacting faults behavior. The developed ensemble learning paradigm comprises multiple merged ML models, which enhances the overall diagnostics performance. Moreover, it works to alleviate the resource-intensive process, which, in turn, contributes to overcoming standard supervised ML algorithms limitations. To ensure high fault diagnostic capabilities through the proposed fault identification strategy, the principal component analysis is introduced to mitigate the correlation between variables. Moreover, the Bayesian optimization method is adopted to control the behaviors of training ML algorithms, providing models with better characterization results. The merits of the proposed strategy are corroborated through simulation and experimental case studies.