Artificial Neural Networks and Genetic Algorithms for the Optimisation of Solar Thermal Systems

Abstract

This paper presents a new method to optimise solar energy systems in order to maximise their economic benefits. The system is modelled with TRNSYS computer program. An artificial neural network is trained using a small number of annual TRNSYS simulation results, to learn the correlation of collector area and storage tank size on the auxiliary energy required by the system and thus on the net solar energy price. Subsequently a genetic algorithm is employed to estimate the optimum size of these two parameters, which maximise the net solar energy price, thus the design time is reduced substantially and the solution obtained is more accurate that the trial and error method used traditionally in these optimisations.