LAUSR

Abstract Thermal simulations are a commonly used tool for energy efficiency analysis of buildings. Regional meteorological station networks are a prime source of weather data inputs, required for building thermal simulations. However, local measurements from weather stations are not always available, and when they are, accessing these data can be expensive. This paper analyses a novel use of a numerical weather prediction mesoscale model, the Global Forecast System (GFS) sflux model, as a source of input data for transient thermal simulations. Two interpolation techniques (nearest neighbour and universal kriging) were used to generate local weather datasets from GFS outputs at 27 locations spread over an area of 29,574 km2 in Galicia (northwest Spain). The performance of the GFS estimations was tested against weather measurements obtained from a governmental weather agency. A reference building with the most common features was selected for running thermal simulations in the TRNSYS environment, focusing on heating demand, with estimated weather data as input. The results highlight that GFS-interpolated datasets consistently performs better than using measured data from the nearest weather station. This clearly supports the use of GFS as an appropriate weather source for building simulations, providing good-quality, free and global-scale local weather inputs.