Naslov
Short-term natural gas consumption forecasting by using smart meters to determine the statistical distribution of consumers

Autori
Smajla , Ivan ; Vulin , Domagoj ; Karasalihović Sedlar , Daria ; Jukić , Lucija

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Digital Proceedings of the 5th SEE Conference on Sustainable Development of Energy, Water and Environment Systems / - Zagreb, Republika Hrvatska, 2022

Skup
5th SEE Conference on Sustainable Development of Energy, Water and Environment Systems

Mjesto i datum
Vlora, Albanija, 22.05.2022. - 26.05.2022

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Natural gas consumption, forecasting methods, statistical distribution, smart metering, remote reading

Sažetak
The development of gas smart meters has enabled the collection of data on daily natural gas consumption which can be used to develop and improve methods and models for natural gas consumption forecasting. The objective of this research was to achieve an accurate short-term natural gas consumption forecast that can greatly reduce the need for buying or selling balancing energy and thus ensure not only the better financial position of the supplier, but also the optimization of the natural gas transmission and distribution system. This paper presents the development of method for short-term forecasting of total natural gas consumption which is applicable in different distribution areas. Daily natural gas consumption data collected from the more than 800 gas smart meters over a period of two months was used for the determination of corelation between lognormal distribution variables and temperature. The defined corelations between distribution variables and temperature were used for upscaling consumption to a specific number of final consumers, i.e., to obtain the total consumption of natural gas in the observed area for the first week of March 2021. Although the model didn’t achieve as high quality MAPE (18.97%) as some of the observed models in the literature, results obtained can still be considered as a quality ones given that the model was using consumption data of only 813 users for upscaling/forecasting consumption for as many as 39 361 consumers in the observed area.

Izvorni jezik
Engleski

Znanstvena područja
Rudarstvo, nafta i geološko inženjerstvo

POVEZANOST RADA