Simplified model for the short-term forecasting of heat loads in buildings. (December 2022)

• Record Type: Journal Article
• Authors: Eguizabal, Markel; Garay-Martinez, Roberto; Flores-Abascal, Iván
• Is Part Of: Energy reports. Volume 8(2022)Supplement 16
• Page Start: 79
• Page End: 85
• Publication Date: 2022-12
• Subjects: Regression model -- Heating demand -- Building -- Lagged value; Power resources -- Periodicals; Energy industries -- Periodicals; Power resources; Periodicals; Electronic journals; 621.04205
• DOI: 10.1016/j.egyr.2022.10.224
• Languages: English
• ISSNs: 2352-4847

Abstract

Abstract: A data-driven model is used to predict one-hour ahead heat loads based on present and recent history of weather and heat loads. A computationally inexpensive method is built to deliver load forecasting based on existing data quality and resolution from smart meters. Optimal model formulation is discussed and optimized at 4-hour historical values. The model is trained and tested against synthetic data from a building energy simulation, resulting in absolute error <4% and R 2 values in the range of 0.92 to 0.94.