Towards the integration of energy performance certificates (EPC) and simplified building performance simulations using machine learning: initial findings

Energy performance certificates (EPCs) are useful tools that not only provide an indication on the efficiency of buildings, but also help raising awareness on the importance of improving their performance. However, the current implementation of EPCs is affected by issues that prevent their full potential to be exploited: lack of standardization across countries, frequency of errors and complexity of the calculation method are some examples. This study assesses the possibility of using machine learning as an alternative to the current quasi-steady state calculation method and represents a first step towards the development of a hybrid calculation tool.