This article presents a comparison of commercial and model based predictive control strategies aimed at optimizing efficiency of classical heating systems used in greenhouse temperature control. Two kind of heating systems are considered: aerial pipes with hot water and air-fan heaters. By using simple linearized models of the system around the predefined setpoints and a generalized predictive control strategy, the performance is improved without requiring modifications in the heating systems. The main strength of this paper lies in the fact that the MPC algorithm has been tested in a greenhouse. Copyright © 2005 IFAC