Thermal Modeling and Prediction of Soilless Greenhouse in Arid Region Based on Particle Swarm Optimization. Experimentally Validated

In this study, a grey-box model for greenhouse thermal prediction of a greenhouse under moderate desert climate conditions has been proposed. Our contribution stands on reformulating a white-box model to make it not dependent on the availability of accurate values of the static parameters of its elements. The model has become less complicated by alleviating the coupling between its parameters, which makes it easier for the identification algorithm to find the optimal parameter values. Particle swarm optimisation has been used to identify the parameters of the proposed model by calibrating it against the experimental data. A greenhouse prototype located in M'ziraa, Biskra, Algeria, and its data acquisition system have been built and used to validate the proposed thermal prediction method. The simulation results show that the desired optimality has been successfully achieved using particle swarm optimization. The experimental validation process has confirmed the suitability of this model to be implemented to study and predict the greenhouse temperature, and it has emphasized the successful prediction with satisfactory accuracy.