| Texto completo | |
| Autor(es): |
Grilo, C. V. C.
;
Davi, M. J. B. B.
;
Lessa, L. S.
;
Coury, D. V.
;
Fernandes, R. A. S.
Número total de Autores: 5
|
| Tipo de documento: | Artigo Científico |
| Fonte: | Electric Power Systems Research; v. 250, p. 8-pg., 2026-01-01. |
| Resumo | |
Electric power systems are continuously evolving to meet the growing demand. International agreements aim to increase the share of sustainable energy sources, which enhances the relevance of inverter-based resources (IBRs) interconnection lines. However, in power grids with IBRs, protection systems face challenges due to the behavior of voltages and currents. While phasor-based fault location is widely used, it is significantly impacted by fault resistance. Thus, the present article proposes an approach that combines apparent impedance techniques with machine learning (ML), using data exclusively from the substation, to accurately estimate fault locations in IBRs interconnection lines. Initially, a ML-based approach estimates the fault resistance and applies a compensation factor to estimate the fault current. The approach proved promising, reducing average errors in the fault location task to less than 1% without requiring new meters in the system, communication structures between transmission line terminals, or meters with higher sampling frequencies. (AU) | |
| Processo FAPESP: | 20/15230-5 - Centro de Pesquisa e Inovação de Gases de Efeito Estufa - RCG2I |
| Beneficiário: | Julio Romano Meneghini |
| Modalidade de apoio: | Auxílio à Pesquisa - Programa Centros de Pesquisa Aplicada |
| Processo FAPESP: | 24/17884-3 - Metodologias para a Proteção e o Diagnóstico de Faltas em Sistemas Dominados por Fontes Baseadas em Inversores do tipo Grid-Forming |
| Beneficiário: | Moisés Junior Batista Borges Davi |
| Modalidade de apoio: | Bolsas no Brasil - Pós-Doutorado |