A comparison of models for forecasting the residential natural gas demand of an urban area
ID Hribar, Rok (Author), ID Potočnik, Primož (Author), ID Šilc, Jurij (Author), ID Papa, Gregor (Author)

.pdfPDF - Presentation file, Download (880,51 KB)
MD5: D646CD746C7C6E432CA7AB48725FCB82
URLURL - Source URL, Visit https://www.sciencedirect.com/science/article/pii/S0360544218321728?via%3Dihub This link opens in a new window

Forecasting the residential natural gas demand for large groups of buildings is extremely important for efficient logistics in the energy sector. In this paper different forecast models for residential natural gas demand of an urban area were implemented and compared. The models forecast gas demand with hourly resolution up to 60 h into the future. The model forecasts are based on past temperatures, forecasted temperatures and time variables, which include markers for holidays and other occasional events. The models were trained and tested on gas-consumption data gathered in the city of Ljubljana, Slovenia. Machine-learning models were considered, such as linear regression, kernel machine and artificial neural network. Additionally, empirical models were developed based on data analysis. Two most accurate models were found to be recurrent neural network and linear regression model. In realistic setting such trained models can be used in conjunction with a weather-forecasting service to generate forecasts for future gas demand.

Keywords:demand forecasting, buildings, energy modeling, forecast accuracy, machine learning
Work type:Article
Typology:1.01 - Original Scientific Article
Organization:FS - Faculty of Mechanical Engineering
Publication status:Published
Publication version:Version of Record
Number of pages:Str. 511-522
Numbering:Vol. 167
PID:20.500.12556/RUL-106552 This link opens in a new window
ISSN on article:0360-5442
DOI:10.1016/j.energy.2018.10.175 This link opens in a new window
COBISS.SI-ID:31841575 This link opens in a new window
Publication date in RUL:05.03.2019
Copy citation
Share:Bookmark and Share

Record is a part of a journal

Shortened title:Energy
COBISS.SI-ID:25394688 This link opens in a new window

Secondary language

Keywords:napovedovanje odjema, zgradbe, energetsko modeliranje, natančnost napovedi, strojno učenje


Funder:ARRS - Agencija za raziskovalno dejavnost Republike Slovenije
Project number:P2-0098, P2-0241, PR-07606
Name:Računalniške strukture in sistemi, Sinergetika kompleksnih sistemov in procesov

Similar documents

Similar works from RUL:
Similar works from other Slovenian collections: