Characterisation and Modeling of Organic Solar Cells by Using Radial Basis Neural Networks

Neural network architectures have been proven useful to model the intrinsic characteristics of photovoltaic cells. The possibility to get rid of an a priori model is one of the many advantages of such an approach as well as the resulting accuracy, robustness and speed. Neural networks have been used to model the characteristics of traditional silicon-based photovoltaic modules, and in this work we have investigated a model for new generation organic solar cells. Silicon-based cells were generally prone to be modeled by simple circuital parameter sets, however for organic cells the process is generally impervious. For this reason, we show that the application of Radial Basis Neural Networks has resulted advantageous to modeling. We have used such networks together with an algorithmic solution to automatically parametrize the Voltage-Current characteristics of organic photovoltaic modules.