Short-term prediction of energy consumption of air conditioners based on weather forecast

In residential houses, air conditioners consume a lot of electrical energy. In order to improve energy efficiency for residential houses, short-term prediction of energy consumption of air conditioners is required. In this paper, we propose the use of our thermal simulation to simulate the change of room temperature based on weather forecast information and predict the energy consumption of an air conditioner in a residential house. In order to calculate solar radiation heat flux, which contributes a lot to the change of room temperature, we utilize a neural network model to predict global solar radiation using training data obtained from weather stations. We also utilize a PID control model to simulate the operation of air conditioners. The accuracy of our simulation is verified by experiments carried out at a real testbed house.