RTU Research Information System
Latviešu English

Publikācija: Heating Demand Forecasting with Multiple Regression: Model Setup and Case Study

Publication Type Full-text conference paper published in conference proceedings indexed in SCOPUS or WOS database
Funding for basic activity Contract research work
Defending: ,
Publication language English (en)
Title in original language Heating Demand Forecasting with Multiple Regression: Model Setup and Case Study
Field of research 2. Engineering and technology
Sub-field of research 2.2 Electrical engineering, Electronic engineering, Information and communication engineering
Authors Kārlis Baltputnis
Romāns Petričenko
Dmitrijs Soboļevskis
Keywords district heating, forecasting, regression, automation, cogeneration
Abstract Accurate demand forecasting in district heating networks is an essential and imperative task in the everyday operation of both, the network itself and the heating energy suppliers. Multiple regression is one of the possible approaches to solving the forecasting problem with sufficient accuracy and little computational effort. This paper presents a polynomial regression model and offers several additions for its further improvement. It is found that grouping the model residuals by hour-of-day allows notably reducing the forecast error. The value of other modifications and the optimum size of the training set can vary over time, thus an automatic model parameter selection before each new forecast is advised.
DOI: 10.1109/AIEEE.2018.8592144
Hyperlink: https://ieeexplore.ieee.org/document/8592144/ 
Reference Baltputnis, K., Petričenko, R., Soboļevskis, D. Heating Demand Forecasting with Multiple Regression: Model Setup and Case Study. In: 2018 IEEE 6th Workshop on Advances in Information, Electronic and Electrical Engineering (AIEEE 2018), Lithuania, Vilnius, 8-10 November, 2018. Piscataway, NJ: IEEE, 2018, pp.91-95. ISBN 978-1-7281-2000-3. e-ISBN 978-1-7281-1999-1. Available from: doi:10.1109/AIEEE.2018.8592144
Full-text Full-text
Publication version
License
Additional information Citation count:
  • Scopus  0
ID 28070