EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Forecasting monthly residential natural gas demand in two cities of Turkey using just-in-time-learning modeling

Burak Alakent iD, Erkan Isikli iD, Cigdem Kadaifci iD, Tonguc S Taspinar iD

PLOS One · 11.06.2025 · 20 (6) · e0325538

DOI: 10.1371/journal.pone.0325538 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 11.06.2025. Verfasst von Burak Alakent und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Chemical Engineering, Bogazici University, Istanbul, Turkey. Hauptthemen laut MEDLINE: Natural Gas, Machine Learning. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 104 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Natural gas (NG) is relatively a clean source of energy, particularly compared to fossil fuels, and worldwide consumption of NG has been increasing almost linearly in the last two decades. A similar trend can also be seen in Turkey, while another similarity is the high dependence on imports for the continuous NG supply. It is crucial to accurately forecast future NG demand (NGD) in Turkey, especially, for import contracts; in this respect, forecasts of monthly NGD for the following year are of utmost importance. In the current study, the historical monthly NG consumption data between 2014 and 2024 provided by SOCAR, the local residential NG distribution company for two cities in Turkey, Bursa and Kayseri, was used to determine out-of-sample monthly NGD forecasts for a period of one year and nine months using various time series models, including SARIMA and ETS models, and a novel proposed machine learning method. The proposed method, named Just-in-Time-Learning-Gaussian Process Regression (JITL-GPR), uses a novel feature representation for the past NG demand values; instead of using past demand values as column-wise separate features, they are placed on a two-dimensional (2-D) grid of year-month values. For each test point, a kernel function, tailored for the NGD predictions, is used in GPR to predict the query point. Since a model is constructed separately for each test point, the proposed method is, indeed, an example of JITL. The JITL-GPR method is easy to use and optimize, and offers a reduction in forecast errors compared to traditional time series methods and a state-of-the-art combination model; therefore, it is a promising tool for NGD forecasting in similar settings.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Natural GasMachine LearningTurkeyForecastingCitiesHumansModels, Theoretical

Substanzen

Natural Gas

Autor:innen und Institutionen

  • Department of Chemical Engineering, Bogazici University, Istanbul, Turkey.
  • Department of Industrial Engineering, Faculty of Management, Istanbul Technical University, Istanbul, Turkey.
  • SOCAR Türkiye, Vadistanbul Bulvar, Ayazağa Mahallesi, Azerbaycan Caddesi, Istanbul, Turkey.

ORCID-Profile: Burak Alakent, Erkan Isikli, Cigdem Kadaifci, Tonguc S Taspinar

Zitieren

APA

Alakent, B., Isikli, E., Kadaifci, C., & Taspinar, T. S. (2025). Forecasting monthly residential natural gas demand in two cities of Turkey using just-in-time-learning modeling. PLOS One, 20(6), e0325538. https://doi.org/10.1371/journal.pone.0325538

Vancouver

Alakent B, Isikli E, Kadaifci C, Taspinar TS. Forecasting monthly residential natural gas demand in two cities of Turkey using just-in-time-learning modeling. PLOS One. 2025;20(6):e0325538. doi:10.1371/journal.pone.0325538

BibTeX
@article{Alakent2025,
  author = {Alakent, Burak and Isikli, Erkan and Kadaifci, Cigdem and Taspinar, Tonguc S},
  title = {Forecasting monthly residential natural gas demand in two cities of Turkey using just-in-time-learning modeling},
  journal = {PLOS One},
  year = {2025},
  volume = {20},
  number = {6},
  pages = {e0325538},
  doi = {10.1371/journal.pone.0325538}
}
Kostenlos starten →