Simplified model for the short-term forecasting of heat loads in buildings

Markel Eguizabal; Roberto Garay-Martinez; Iván Flores-Abascal

doi:10.1016/j.egyr.2022.10.224

Simplified model for the short-term forecasting of heat loads in buildings

Markel Eguizabal
, Roberto Garay-Martinez^*
, Iván Flores-Abascal

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

9 Citations (Scopus)

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 R² values in the range of 0.92 to 0.94.

Original language	English
Pages (from-to)	79-85
Number of pages	7
Journal	Energy Reports
Volume	8
DOIs	https://doi.org/10.1016/j.egyr.2022.10.224
Publication status	Published - Dec 2022
Externally published	Yes

Keywords

Building
Heating demand
Lagged value
Regression model

Access to Document

10.1016/j.egyr.2022.10.224

Cite this

@article{5d3d3e6486df4889a10537553d8ea55b,

title = "Simplified model for the short-term forecasting of heat loads in buildings",

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 R2 values in the range of 0.92 to 0.94.",

keywords = "Building, Heating demand, Lagged value, Regression model",

author = "Markel Eguizabal and Roberto Garay-Martinez and Iv{\'a}n Flores-Abascal",

note = "Publisher Copyright: {\textcopyright} 2022 The Author(s)",

year = "2022",

month = dec,

doi = "10.1016/j.egyr.2022.10.224",

language = "English",

volume = "8",

pages = "79--85",

journal = "Energy Reports",

issn = "2352-4847",

publisher = "Elsevier Ltd.",

}

TY - JOUR

T1 - Simplified model for the short-term forecasting of heat loads in buildings

AU - Eguizabal, Markel

AU - Garay-Martinez, Roberto

AU - Flores-Abascal, Iván

PY - 2022/12

Y1 - 2022/12

N2 - 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 R2 values in the range of 0.92 to 0.94.

AB - 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 R2 values in the range of 0.92 to 0.94.

KW - Building

KW - Heating demand

KW - Lagged value

KW - Regression model

UR - https://www.scopus.com/pages/publications/85140328445

U2 - 10.1016/j.egyr.2022.10.224

DO - 10.1016/j.egyr.2022.10.224

M3 - Article

AN - SCOPUS:85140328445

SN - 2352-4847

VL - 8

SP - 79

EP - 85

JO - Energy Reports

JF - Energy Reports

ER -

Simplified model for the short-term forecasting of heat loads in buildings

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this