Applying Neural Networks to Model Monthly Energy Consumption of Commercial Buildings in Singapore(ICCAS2004)

The methodology for modeling building energy consumption is well established for energy saving calculation in the temperate zone both for performance-based energy retrofitting contracts and measurement and verification (M&V) projects. Mostly, statistical regression models based on utility bills and outdoor dry-bulb temperature have been applied to baseline monthly and annual whole building energy use. This paper presents the application of neural networks (NN) to model landlord energy consumption of commercial buildings in Singapore. Firstly, a brief background information on NN and its application on the building energy research is provided. Secondly, five commercial buildings with various characteristics were selected for case studies. Monthly mean outdoor dry-bulb temperature ($T_0$), Relative Humidity (RH) and Global Solar Radiation (GSR) are used as network inputs and the landlord monthly energy consumption of the same period is the output. Up to three years monthly data are taken as training data. A forecast has been made for another year for all the five buildings. The performance of the NN analysis was evaluated using coefficient of variance (CV). The results show that NNs is powerful at predicting annual landlord energy consumption with high accuracy.