Using attention to model long-term dependencies in occupancy behavior.

Models simulating household energy demand based on different occupant and household types and their behavioral patterns have received increasing attention over the last years due the need to better understand fundamental characteristics that shape the demand side. Most of the models described in the literature are based on Time Use Survey data and Markov chains. Due to the nature of the underlying data and the Markov property, it is not sufficiently possible to consider day to day dependencies in occupant behavior. An accurate mapping of day to day dependencies is of increasing importance for accurately reproducing mobility patterns and therefore for assessing the charging flexibility of electric vehicles. This study bridges the gap between energy related activity modelling and novel machine learning approaches with the objective to better incorporate findings from the field of social practice theory in the simulation of occupancy behavior. Weekly mobility data are merged with daily time use survey data by using attention based models. In a first step an autoregressive model is presented, which generates synthetic weekly mobility schedules of individual occupants and thereby captures day to day dependencies in mobility behavior. In a second step, an imputation model is presented, which enriches the weekly mobility schedules with detailed information about energy relevant at home activities. The weekly activity profiles build the basis for modelling consistent electricity, heat and mobility demand profiles of households. Furthermore, the approach presented forms the basis for providing data on socio-demographically differentiated occupant behavior to the general public.