Greenhouse air temperature predictive control using the particle swarm optimisation algorithm

The particle swarm optimisation algorithm is proposed as a new method to design a model-based predictive greenhouse air temperature controller subject to restrictions. Its performance is compared with the ones obtained by using genetic and sequential quadratic programming algorithms to solve the constrained optimisation air temperature control problem. Controller outputs are computed in order to optimise future behaviour of the greenhouse environment, regarding set-point tracking and minimisation of the control effort over a prediction horizon of 1h with 1-min sampling period, for a greenhouse located in the north of Portugal. Since the controller must be able to predict the greenhouse environmental conditions over the specified time interval, it is necessary to use mathematical models that describe the greenhouse climate, as well as to predict the outside weather. These requirements are met by using auto regressive models with exogenous inputs and time series auto-regressive models to simulate the inside and outside climate conditions, respectively. These models have time variant parameters and so, recursive identification techniques are applied to estimate their values in real-time. The models employ data from the climate inside and outside the greenhouse, as well as from the control inputs. Simulations with the proposed methodology to design the model-based predictive air temperature controller are presented. The results indicate a better efficiency of the particle swarm optimisation algorithm as compared with the efficiencies obtained with a genetic algorithm and a sequential quadratic programming method.