Machine learning based met data anomaly labelling

• Published in: Journal of physics. Conference series 2022-04, Vol.2257 (1), p.12015
• Main Authors: Talayero, Ana P., Yürüşen, Nurseda Y., Ramos, Francisco José Sánchez, Gastón, Roberto Lázaro
• Format: Article
• Language: English
• Subjects: Algorithms; Classifiers; Decision making; Labels; Machine learning; Physics; Preprocessing; Resource allocation; Scanning; Wind power
• ISSN: 1742-6588; 1742-6596
• DOI: 10.1088/1742-6596/2257/1/012015

Data preprocessing is the initial and utmost critical phase of wind resource assessment and wind power curve performance analysis. Without ensuring high quality and site representative data availability, an evaluation for the wind resource potential of a wind farm site means investment decision making involving a great deal of uncertainty. The current practice in the field is to use fix rules and via data scanning by manual labouring of data field experts. Although rule-based (if-else, interval-based) prefiltering applications can be found in some commercial software, and these rules are also limited for addressing the needed preprocessing requirements fully. Therefore, this process is time consuming and causes inefficient resource allocation considering the manual scanning process performed by data scientists & experts. In this study, reviewed data by experts are used as data with correct labels, and then efficient classifiers are generated by applying machine learning algorithms to unfiltered and filtered data. It is reported that tree-based classifiers are performing better.