Predictive Control of Multizone HVAC Systems in Non-residential Buildings

In France, buildings account for a large part of the energy consumption and carbon emissions. Both are mainly due to Heating, Ventilation and Air-Conditioning (HVAC) systems. So, the present work deals with the predictive control of multizone HVAC systems in nonresidential buildings. We used the PMV (Predicted Mean Vote) 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. The proposed strategy allows the operation time of each HVAC sub-system to be optimized (and, as a result, electrical power consumption) and thermal comfort requirements to be met. In order to test this approach, a real non-residential building located in Perpignan (south of France) has been modelled using the EnergyPlus software. The results we obtained in simulation allows the pertinence of the predicitive strategy to be highlighted.