부산대학교 도서관

With the large expansion of photovoltaic generation, the importance of fault diagnosis is fundamental for optimal system performance and reliability guarantee, thus increasing system efficiency. An overview of Artificial Neural Networks (ANNs) and Support Vector Machines (SVMs) that are used for fault detection and diagnosis (FDD) in photovoltaic systems is presented in this paper. The application of these methodologies is addressed along with their fundamental principles. Reviewing several studies that have used ANNs and SVMs for fault identification and diagnosis in solar PV systems, their benefits and drawbacks are highlighted. Lastly, some potential future research topics based on these are explored.