A cost-effective and heuristic approach for building energy consumption prediction: BES model calibration and forecasting algorithm

Abstract

Building energy simulation methods for predicting energy consumption suffer from limitations, including high costs, time-consuming processes, and significant prediction errors. To address these issues, this study presents a novel approach to enhance the accuracy and cost-effectiveness of building energy consumption prediction through BES model calibration. Additionally, an algorithm utilizing Weather profiles is introduced for energy consumption prediction. The proposed model introduces the concept of the unit volume, simplifying the construction of BES models, while prediction errors are addressed through the integration of statistical models. Furthermore, a weather profile database is established, and a heuristic algorithm incorporating outdoor forecast data is proposed. The results of a case study conducted on two buildings demonstrate that both BES models exhibit significantly improved predictive performance during both heating and cooling seasons, surpassing the recommended standards set by ASHRAE.