Modeling of a greenhouse using Particle Swarm Optimization

The Particle Swarm Optimization (PSO) algorithm is applied in this work to identify some parameters of a greenhouse model whose values are difficult to obtain. The model is described as functions of the outside climate and actuators actions without control. The parameters of the model are obtained applying PSO to minimize a proposed error function. The obtained model is validated using real data from a greenhouse prototype. Validation shows a good agreement with the dynamic behavior of the inside air temperature and relative humidity, which are the main variables of interest.