In France, buildings account for a large part of the energy consumption and carbon emissions. Both are mainly due to Heating, Ventilation and AirConditioning (HVAC) systems. Because older, oversized or poorly maintained systems may be using more energy and costing more to operate than necessary, new management approaches are needed. In addition, energy efficiency can be improved in central heating and cooling systems by introducing zoned operation. So, the present work deals with the predictive control of multizone HVAC systems in non-residential buildings. First, a real non-residential building located in Perpignan (south of France) has been modelled using the EnergyPlus software. We used the Predicted Mean Vote (PMV) index as a thermal comfort indicator and developed low-order ANN-based models to be used as controller's internal models. A genetic algorithm allowed the optimization problem to be solved. Using the proposed strategy, the operation of all the HVAC subsystems is optimized by computing the right time to turn them on and off, in both heating and cooling modes. Energy consumption is minimized and thermal comfort requirements are met. In order to appraise the proposed management strategy, it has been compared to basic scheduling techniques. The simulation results highlight the pertinence of a predicitive approach for multizone HVAC systems management.