Abstract
Building management systems (BMSs) with predictive control strategies rely on accurate weather forecasts to optimise heating and cooling operations. These strategies depend on precise climatic inputs to adjust system operations dynamically. Typically, weather forecast data is sourced from the internet and is generated by numerical weather prediction (NWP) models using advanced mathematical simulations. However, these models fail to account for localised nano-climatic variations, such as significant temperature and irradiance differences between the north and south sides of a building or the actual environmental conditions around the on-site sensors. These nano-climatic effects directly influence the calculation of the future thermal load of the building, which is crucial for predictive control approaches. To address this challenge, we propose a hybrid methodology that integrates NWP forecasts with local measurements from on-site sensors, improving NWP forecast accuracy. Our approach employs Inverse Distance Weighting (IDW) to interpolate NWP outputs to a specific geographical position and applies exponential smoothing for further finetuning by using historical error patterns. This methodology enhances the predictive accuracy of temperature and irradiance forecasts, achieving reductions of up to 60% to 80% in temperature errors and up to 20% to 30% in irradiance errors. Based on the finetuned weather forecast, the accuracy of building’s thermal load prediction is improved up to 86% compared to the predictions with IDW weather forecast.