Development of an artificial neural network model to predict the optimal pre-cooling time in office buildings

This paper presents an application of the artificial neural network(ANN), which is a generic technique for mapping the nonlinear relationships between inputs and outputs without knowing the details of these relationships in building control system. The purpose of this study is to develop an optimized artificial neural network model to determine the optimal pre-cooling time in office buildings. For this, programs for learning of an ANN model based on back-propagation learning and predicting room air temperature based on the finite difference method were developed, and learning data for various building conditions were collected through program simulation for predicting room air temperature using systems of experimental design. Then, the optimized ANN model was presented through learning of ANN and its performance to determine the optimal pre-cooling time was evaluated.