Optimal statistical designs for energy saving building remodeling

In this thesis I address the problem of energy consumption reduction in existing buildings, providing comfort levels for inhabitants. In the first part I will describe some aspects of the environmental problem related to energy consumption and will be presented some possible solutions suggested in literature. The core of this work will be the application on a real case of study (a building composed by 3 offices) in which the mentioned objectives depend on a set of independent and control variables such as internal temperature, humidity, dimmerization and presence of people. In particular this research will find the best configurations of the control variables in order to reduce energy consumption, mantaining optimal comfort levels. The approach that I adopted is based on a class of statistical predictive models and optimization algorithms.