A comparison of models for forecasting the residential natural gas demand of an urban area

Hribar, Rok (author), Potočnik, Primož (author), Šilc, Jurij (author), Papa, Gregor (author)

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.

• Language: English
• 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
• Year: 2019
• Number of pages: Str. 511-522
• Numbering: Vol. 167
• PID: 20.500.12556/RUL-106552
• UDC: 004.9:620.9(045)
• ISSN on article: 0360-5442
• DOI: 10.1016/j.energy.2018.10.175
• COBISS.SI-ID: 31841575
• Publication date in RUL: 05.03.2019

Record is a part of a journal

• Title: Energy
• Shortened title: Energy
• Publisher: Pergamon Press
• ISSN: 0360-5442
• COBISS.SI-ID: 25394688

Secondary language

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

Projects

• Funder: ARRS - Slovenian Research Agency
• Project number: P2-0098, P2-0241, PR-07606
• Name: Računalniške strukture in sistemi, Sinergetika kompleksnih sistemov in procesov