In this paper, the adapted time-series regression (ATSR) model is used for developing appliance energy usage profiles for a building which utilizes meter readings, and individual appliance usage using data measurements from installed power meter respectively. For this purpose, statistical models were produced for a building as well as for individual appliances. This assists in understanding the usage patterns for all types of appliances and identifies the factors that may affect the pattern. In addition, establishing a general model for a building based on different appliance use will provide more precise data than developing a model based on total consumption for the building. This will provide an insight into the contribution of each appliance on total consumption.
General TermsMachine learning, computational science, energy informatics.