Detecting clipping in photovoltaic solar plants using fuzzy systems on the feature space

We propose the use of a fuzzy system evaluating a feature space extracted from the daily power production profile of a photovoltaic solar plant. The fuzzy system proposed is able to detect inverter power limiting situations, as well as stages where the photovoltaic solar plant is showing steady state power production. The approach has been validated using an experimental real grid connected photovoltaic plant located in Spain. The results demonstrate that the method is suitable for online detection, as well as for labeling incoming online data from the photovoltaic power production for a posteriori off-line analysis. (C) 2016 Elsevier Ltd. All rights reserved.