Multiscale fuzzy model-based short term predictive control of greenhouse microclimate

This paper describes the application of fuzzy model predictive control to regulate the micro-climate of agricultural processes. The design of fuzzy models are based on time-scale decomposition of greenhouse climate processes to deal with rapidly fluctuating external inputs and the differences in dynamic response times of the various physical and physiological phenomena taking place. The appropriate control actions are selected from a pre-specified set of control combinations, using the well-known branch-and-bound algorithm. The simulation results revealed that the proposed approach was able to maintain the temperature and humidity inside the greenhouse around the desired reference points.