A comparison of models for forecasting the residential natural gas demand of an urban area
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.
2019
2019-03-15 12:13:02
1033
demand forecasting, buildings, energy modeling, forecast accuracy, machine learning
napovedovanje odjema, zgradbe, energetsko modeliranje, natančnost napovedi, strojno učenje
Rok
Hribar
70
Primož
Potočnik
70
Jurij
Šilc
70
Gregor
Papa
70
UDK
4
004.9:620.9(045)
ISSN pri članku
9
0360-5442
DOI
15
10.1016/j.energy.2018.10.175
COBISS_ID
3
31841575
OceCobissID
13
25394688
RAZ_Hribar_Rok_i2019.pdf
991294
Predstavitvena datoteka
2019-03-15 12:15:16