In Switzerland, about 40 % (90 TWh) of the energy needs are due to buildings and about 70 % of these needs come from heating. Therefore, improving the efficiency of buildings has a high potential for energy savings. This paper presents innovative solutions for the automation of energy services in residential buildings, based solely on the disaggregation of the centralized electricity consumption measurement of the household. The developed method was successfully used on electricity consumption data recorded in 14 households over a year to (1) extract the heat pump consumption from the aggregated consumption, (2) split the heat pump consumption into space heating and domestic hot water consumption and (3) split the remaining consumption into four categories: base load, low power, medium power, and high power. With a daily average error on the prediction of the heat pump consumption below 3.5 % and daily average errors on the prediction of the number of cycles and the operating time of the heat pump both around 1 %, the described method can be used for the development of energy service prototypes allowing to better understand and optimize the energy functioning of residential buildings with potential savings for the residents.