Automatic fault detection for Building Integrated Photovoltaic (BIPV) systems using time series methods

摘要: Purpose Faults in the actual outdoor performance of Building Integrated Photovoltaic (BIPV) systems can go unnoticed for several months since energy productions are subject to significant variations that could mask faulty behaviors. Even large BIPV deficits be hard detect. The purpose this paper is develop a cost-effective approach automatically detect faults using historical as only source information typically collected all systems. Design/methodology/approach Energy time series nature. Therefore, methods used two categories (outliers and structure changes) monthly systems. research methodology consists automatic detection outliers productions, changes productions. Findings The proposed applied 89 results confirm detected presence short-term variations, seasonality, long-term degradation performance. Originality/value Unlike existing methods, does not require ratio calculation, operating condition data, such solar irradiation, or output neighboring It uses about distinguish between other properties including trends.