Intelligent occupancy-driven thermostat by dynamic user profiling

Matching system functionality and user needs by learning from user behaviour enables a significant reduction in energy consumption. Habits and routine behaviour are exploited and captured in user profiles to automatically create customized heating schedules. However, over time the user conduct can change either gradually or abruptly and old occupancy patterns could become obsolete. Hence, a self-learning system should be able to cope with these changes and adapt the identified user profiles accordingly. An approach to track changing behaviour and update the corresponding user profiles, and hence heating schedules, is presented. The proposed strategy is evaluated by comparing prediction accuracy and potential energy savings to the case where learning is static and to incremental learning strategies. The results are illustrated by means of a real-life dataset of a single-user office.