This paper uses a decentralized model-based predictive controller approach for the design of discrete-time control systems aiming at regulating the air tempera-ture and heat supply in greenhouses. It also proposes alternative techniques for the approximation of the decentralized part of the control and the on-line improvement of the overall control problem. A state space model is used to predict the corresponding local indoor temperature over a long-range time period and approximate models are used to predict the interactions among the subsystems. The sun radiation and outdoor temperature are treated as external disturbances that affect the overall system dyna-mics. A series of energy fluxes consist the heating system and the predictive control-lers have proved to be powerful in controlling the supply temperature.