Robust Gas Demand Prediction Using Deep Neural Networks: A Data-Driven Approach to Forecasting Under Regulatory Constraints

Kostiantyn Pavlov (), Olena Pavlova, Tomasz Wołowiec, Svitlana Slobodian, Andriy Tymchyshak and Tetiana Vlasenko
Additional contact information
Kostiantyn Pavlov: Faculty of Economics and Management, Lesya Ukrainka Volyn National University, Voli Ave, 13, 43025 Lutsk, Ukraine
Olena Pavlova: Faculty of Economics and Management, Lesya Ukrainka Volyn National University, Voli Ave, 13, 43025 Lutsk, Ukraine
Tomasz Wołowiec: Science and International Cooperation of the Lublin Academy of WSEI, Projektowa 4, 20-209 Lublin, Poland
Svitlana Slobodian: Faculty of Mathematical and Computer Science, Vasyl Stefanyk Precarpathian National University, 57 Shevchenka Str., 76018 Ivano-Frankivsk, Ukraine
Andriy Tymchyshak: Faculty of Economics and Management, Lesya Ukrainka Volyn National University, Voli Ave, 13, 43025 Lutsk, Ukraine
Tetiana Vlasenko: Department of Management, Academy of Silesia, Ul. Rolna 43, 40-555 Katowice, Poland

Energies, 2025, vol. 18, issue 14, 1-19

Abstract: Accurate gas consumption forecasting is critical for modern energy systems due to complex consumer behavior and regulatory requirements. Deep neural networks (DNNs), such as Seq2Seq with attention, TiDE, and Temporal Fusion Transformers, are promising for modeling complex temporal relationships and non-linear dependencies. This study compares state-of-the-art architectures using real-world data from over 100,000 consumers to determine their practical viability for forecasting gas consumption under operational and regulatory conditions. Particular attention is paid to the impact of data quality, feature attribution, and model reliability on performance. The main use cases for natural gas consumption forecasting are tariff setting by regulators and system balancing for suppliers and operators. The study used monthly natural gas consumption data from 105,527 households in the Volyn region of Ukraine from January 2019 to April 2023 and meteorological data on average monthly air temperature. Missing values were replaced with zeros or imputed using seasonal imputation and the K-nearest neighbors. The results showed that previous consumption is the dominant feature for all models, confirming their autoregressive origin and the high importance of historical data. Temperature and category were identified as supporting features. Improvised data consistently improved the performance of all models. Seq2SeqPlus showed high accuracy, TiDE was the most stable, and TFT offered flexibility and interpretability. Implementing these models requires careful integration with data management, regulatory frameworks, and operational workflows.

Keywords: natural gas consumption and demand forecasting; neural networks; Seq2Seq; TiDE; Temporal Fusion Transformer; regulatory restrictions; energy systems; tariff policy; capacity balancing and reservation; machine learning; long short-term memory; time series analysis; SHAP processing of missing data (search for similar items in EconPapers)
JEL-codes: Q Q0 Q4 Q40 Q41 Q42 Q43 Q47 Q48 Q49 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1996-1073/18/14/3690/pdf (application/pdf)
https://www.mdpi.com/1996-1073/18/14/3690/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jeners:v:18:y:2025:i:14:p:3690-:d:1700436

Access Statistics for this article

Energies is currently edited by Ms. Agatha Cao

More articles in Energies from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().