Artificial neural networks for the prediction of cooling loads of HVAC systems: a case study under tropical climate

摘要

The prediction of cooling loads of HVAC systems is necessary to size the maximum capacity of the system within a building and to predict its energy consumptions. This paper deals with the use of artificial neural networks (ANN) for the modelling of the cooling loads (total, sensible and latent capacities) of HVAC systems and to predict therefore the energy consumption of these systems. Firstly, we present the model approach and the ANN. Then, a neural model for the sensible and total power is presented. The prediction is compared to manufacturer data in one hand, and on the other hand to mathematical models.