Behavioural approach for the simulation of electrical consumption at the neighbourhood level

—We address the problem of simulating domestic activities related to electrical consumption. Continuously growing electrical energy requirements have become an issue as resources to produce it are limited. Human factors have to be taken into account in order to better predict electric consumption and optimize its production. We propose a framework based on a psychological scheme and on stochastic features. The decision process is based on the representation of habits and the use of heat maps. Inclusion of planning-related behaviour is performed by a non-parametric voting method using relational properties among domestic activities. The results show a good fitting between the predictions and ground truth.