Athanasios Tsanas in Oxford and Angeliki Xifara in Cardiff have developed an automatic tool which can accurately predict the needs for heating load and cooling load (thus, the required energy throughout the year) of a residential building when eight standard building parameters are provided (relative compactness, surface area, wall area, roof area, overall height, orientation, glazing area, glazing area distribution). The results are based on training a statistical machine learning algorithm using 768 diverse buildings.The research has created a useful tool for civil engineers and architects in their ongoing search for energy efficiency.
