Survey on adaptative neural fuzzy inference system (ANFIS) architecture applied to photovoltaic systems

Solar energy has been considered as one of the leading renewable energy sources for electric power generation. Therefore, intending to deal with a low energy conversion efficiency of photovoltaic (PV) materials problems, artificial intelligence (AI) techniques are playing an essential role in enhancing the performance and reliability of photovoltaic systems. Consequently, many researchers have focused their studies on using AI applied to photovoltaic solar energy. Adaptative neural fuzzy inference system (ANFIS) has shown excellent performance and potential use among AI methods. Therefore, ANFIS architecture has been widely applied in PV systems, and many papers were found. However, a survey with classifications or comparisons was not detected. In this regard, this paper surveys the literature about ANFIS architecture applied to photovoltaic systems. And, to help the readers, the authors propose new categorization based on applicability. The six different categorizations are Solar irradiance forecasting; Photovoltaic output power estimation; Parameter identification for photovoltaic system sizing; Maximum power point tracking (MPPT); Inverter control; and Fault diagnosis photovoltaic systems. Furthermore, in each categorization, a comparison is made among the papers approached. Finally, a comparison among ANFIS architecture and other techniques also are presented in each categorization.