Model predicting the state of the AC with the indoor temperature and occupancy.
When the space is unoccupied, the AC is always off. When the space is occupied, the lower the indoor temperature is, the lower the chance to turn on the AC and higher the chance to turn off the AC.
The model is documented in the paper "Ren, X., Yan, D. and Wang, C., 2014. Air-conditioning usage conditional probability model for residential buildings. Building and Environment, 81, pp.172-182."
The model parameters are regressed from the field study in China in 2014.