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

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

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.

• Jezik: Angleški jezik
• Ključne besede: demand forecasting, buildings, energy modeling, forecast accuracy, machine learning
• Vrsta gradiva: Članek v reviji
• Tipologija: 1.01 - Izvirni znanstveni članek
• Organizacija: FS - Fakulteta za strojništvo
• Status publikacije: Objavljeno
• Različica publikacije: Objavljena publikacija
• Leto izida: 2019
• Št. strani: Str. 511-522
• Številčenje: Vol. 167
• PID: 20.500.12556/RUL-106552
• UDK: 004.9:620.9(045)
• ISSN pri članku: 0360-5442
• DOI: 10.1016/j.energy.2018.10.175
• COBISS.SI-ID: 31841575
• Datum objave v RUL: 05.03.2019

Gradivo je del revije

• Naslov: Energy
• Skrajšan naslov: Energy
• Založnik: Elsevier
• ISSN: 0360-5442
• COBISS.SI-ID: 25394688

Sekundarni jezik

• Jezik: Slovenski jezik
• Ključne besede: napovedovanje odjema, zgradbe, energetsko modeliranje, natančnost napovedi, strojno učenje

Projekti

• Financer: ARRS - Agencija za raziskovalno dejavnost Republike Slovenije
• Številka projekta: P2-0098, P2-0241, PR-07606
• Naslov: Računalniške strukture in sistemi, Sinergetika kompleksnih sistemov in procesov