Design optimization of solar chimney power plant by finite elements based numerical model and cascade neural networks

Power output fluctuation is a common problem in the various generating systems of renewable energies. The hybrid energy storage system with water and soil is adopted to decrease the fluctuation of solar chimney power generating systems in the present study. The aim of this paper is a cross-comparison between finite element method (FE) and neural networks (NN) simulation results which were produced for a chosen set of parameters not already considered during the networks training. As main result we propose a prediction tool for investigating the design and performance of a solar system in different working scenarios, not included in reference database exploited for the NN training process.