Ensembled methodology for the comtrade analysis regarding medium voltage side in wind park

• Autor: Arias Velasquez, Ricardo Manuel
• Formato: artículo
• Fecha de Publicación: 2024
• Institución: Universidad Tecnológica del Perú
• Repositorio: UTP-Institucional
• Lenguaje: inglés
• OAI Identifier: oai:repositorio.utp.edu.pe:20.500.12867/14088
• Enlace del recurso: https://hdl.handle.net/20.500.12867/14088
• Nivel de acceso: acceso abierto
• Materia: Comtrade; Oscillography; Event; https://purl.org/pe-repo/ocde/ford#2.11.03

This research proposes a methodology for automated COMTRADE analysis using ensembled algorithms for fault analysis in medium voltage circuits, specifically for wind park feeders. Traditional fault detection methods face significant limitations, such as CT saturation and DC offset, underscoring the need for improved approaches. The proposed methodology integrates Random Committee, XGBoost (XGB), and Light XGB algorithms, optimized through grid search, achieving an accuracy of 99.397 %. This ensemble approach significantly reduces classification errors, false positives, and false negatives compared to single algorithm methods. This research has the analysis of 3929 events for training and 829 fault events for test, it revealed a high correlation between current and fault spectra; the methodology demonstrated superior performance in fault location analysis, with terminal faults showing the most severe transient recovery voltage (TRV) peak values, while kilometer faults exhibited higher transient recovery restoration voltage growth rates. The fault location analysis was conducted by comparing simulation-derived overvoltage with standard TRV graphs, aligned with IEC 62271-100 standards. Circuit breakers exhibited higher TRV tolerance with lower fault currents. Terminal faults, particularly symmetrical three-phase faults, were identified as the most severe, typically occurring at peak TRV values. Its findings reduced classification errors, from 41 to 5 events, and decreased the false negative rate from 1.81 % to 0.24 % compared to Random Forest. Validation with virtual relays showed a reduction in RCE from 5.3 % to 0.63 %.