Fault detection of large amounts of photovoltaic systems

Autoren Patrick Traxler
Editoren
TitelFault detection of large amounts of photovoltaic systems
BuchtitelOnline Proceedings of the ECML PKDD 2013 Workshop on Data Analytics for Renewable Energy Integration (DARE'13)
Typin Konferenzband
Jahr2013
Seitenhttp://www.ecmlpkdd2013.org/wp-content/uploads/2013/09/dare2013_paper4_traxler.pdf
SCCH ID#1356
Abstract

We study a model-based approach to detect sustainable faults of photovoltaic systems. We describe models and algorithms which al- low us to analyze a large amount of photovoltaic systems. Our approach is based on median regression. We assume that we know the irradiance and produced energy of a photovoltaic system. The particular challenge of the data analysis problem we study here is the possible huge amount of photovoltaic systems and their continuous streams of data.