The method for photovoltaic module temperature ultra-short-term forecasting based on RBF neural network

摘要

As module temperature plays an important role in the conversion efficiency of photovoltaic(PV) module, an accurate prediction will be very helpful in improving PV power forecasting. In this article, a method of ultra-short-term forecasting for PV module temperature based on RBF neural network was proposed, which had a prediction aging of the next 4 hour, time resolution of prediction point was 15-minute, and prediction rolling cycle of 15-minutes. In the case study, this approach continuously provides reasonable temperature forecasting of the PV module. It is indicated that this approach is of significance in practical application.