Development of a Neural Network-based Building Model and Application to Geothermal Heat Pumps Predictive Control
Résumé
The use of artificial neural networks in the field of building energy management has led to remarkable results over the recent years. In this study, the development of room temperature neural network models, to be used for predictive control of geothermal heat pump systems, is discussed. The training process, including the determination of optimal input data, algorithm and structure, is detailed. The prediction performance of the developed neural network is compared to linear ARX models. Simulated data used for training and validation is generated using the TRNSYS environment. The developed model is then implemented into a predictive controller for geothermal heat pumps systems. Simulation results showed that the predictive controller can provide up to 17% energy savings in comparison with conventional controllers.