Sie können Bookmarks mittels Listen verwalten, loggen Sie sich dafür bitte in Ihr SLUB Benutzerkonto ein.
Medientyp:
E-Artikel
Titel:
PV Fault Detection Using Positive Unlabeled Learning
Beteiligte:
Jaskie, Kristen;
Martin, Joshua;
Spanias, Andreas
Erschienen:
MDPI AG, 2021
Erschienen in:
Applied Sciences, 11 (2021) 12, Seite 5599
Sprache:
Englisch
DOI:
10.3390/app11125599
ISSN:
2076-3417
Entstehung:
Anmerkungen:
Beschreibung:
<jats:p>Solar array management and photovoltaic (PV) fault detection is critical for optimal and robust performance of solar plants. PV faults cause substantial power reduction along with health and fire hazards. Traditional machine learning solutions require large, labeled datasets which are often expensive and/or difficult to obtain. This data can be location and sensor specific, noisy, and resource intensive. In this paper, we develop and demonstrate new semi supervised solutions for PV fault detection. More specifically, we demonstrate that a little-known area of semi-supervised machine learning called positive unlabeled learning can effectively learn solar fault detection models using only a fraction of the labeled data required by traditional techniques. We further introduce a new feedback enhanced positive unlabeled learning algorithm that can increase model accuracy and performance in situations such as solar fault detection when few sensor features are available. Using these algorithms, we create a positive unlabeled solar fault detection model that can match and even exceed the performance of a fully supervised fault classifier using only 5% of the total labeled data.</jats:p>