Optimizing Gas Consumption Predictions: A Comprehensive Study of Individual and Hybrid Modeling Approaches with Practical Implications for Energy Policies

Authors

  • Changhao Zhang Henan University of Animal Husbandry and Economy; Zhengzhou, Henan, 450000, China
  • Mengyu Ren Henan University of Animal Husbandry and Economy; Zhengzhou, Henan, 450000, China

DOI:

https://doi.org/10.13052/spee1048-5236.45210

Keywords:

Gas Consumption Forecasting, Individual Modeling, Hybrid Modeling, CatBoost, MLP, XGBoost, SMA, SSA, Predictive Accuracy, Energy Management, Resource Allocation

Abstract

Natural gas, the cleanest fossil fuel, is increasingly important due to its abundance and lower carbon emissions. However, accurately forecasting gas demand remains challenging. To forecast gas usage, this study uses sophisticated machine learning (ML) techniques, including CatBoost, XGBoost, and MLP. Six prediction models and hyperparameter optimization are created and assessed. Hybrid XGBoost models, particularly XGBoost-SSA and XGBoost-SMA, demonstrate superior convergence and accuracy. Visual aids like correlation matrices and scatter plots provide insights into model performance. The research contributes to enhancing the efficiency of gas distribution operations, ensuring energy security, economic stability, and environmental sustainability. By integrating renewable energy and leveraging real-time analytics, the study addresses the evolving dynamics of gas consumption forecasting, offering valuable implications for energy policies and investment strategies.

Downloads

Download data is not yet available.

Author Biographies

Changhao Zhang, Henan University of Animal Husbandry and Economy; Zhengzhou, Henan, 450000, China

Changhao Zhang, male, native place: Luohe, Henan, born in March 1981. He graduated from Zhongnan University of Economics and Law in 2004. He is currently an associate professor in the School of Business Administration of Henan University of Animal Husbandry and Economy. He has long undertaken the teaching tasks of “Marketing”, “Marketing Case Analysis” and other courses. He has many years of enterprise practice experience and has rich professional skills and professional training guidance experience for students. His research focuses on digital marketing, digital economy, and green economy.

Mengyu Ren, Henan University of Animal Husbandry and Economy; Zhengzhou, Henan, 450000, China

Mengyu Ren, female, native place: Xuchang, Henan, born in September 1981. She graduated from Henan University of Technology in 2004. She is currently a lecturer in the School of Business Administration of Henan University of Animal Husbandry and Economy. She has long undertaken the teaching tasks of “ Business etiquette”, “Marketing Case Analysis” and other courses. She has many years of enterprise practice experience and has rich professional skills and professional training guidance experience for students. Her research focuses on digital marketing and Marketing management, etc.

References

J. Essandoh-Yeddu, “Natural gas market,” in Advances in Natural Gas Technology, IntechOpen, 2012.

J.-J. Her and H.-J. Lim, “An analysis of growth factors on the city-gas industry by input-output structural decomposition analysis,” Journal of Energy Engineering, vol. 21, no. 2, pp. 158–167, 2012.

S. I. and T. D. R. Center, M. Ishwaran, W. King, M. Haigh, T. Lee, and S. Nie, “The Global Natural Gas Market,” China’s Gas Development Strategies, pp. 345–378, 2017.

L. Baldacci, M. Golfarelli, D. Lombardi, and F. Sami, “Natural gas consumption forecasting for anomaly detection,” Expert Syst Appl, vol. 62, pp. 190–201, 2016, doi: 10.1016/j.eswa.2016.06.013.

W. Liu, X. Feng, Y. Xu, and X. Gu, “Framework Design and Implementation of Real-Time Monitoring and Dynamic Analyzing System of Urban Gas Network,” in ICPTT 2011: Sustainable Solutions For Water, Sewer, Gas, And Oil Pipelines, 2011, pp. 295–303.

T. N. Beloglazova and T. N. Romanova, “Effective Implementation of Digital Technologies in the Field of Gas Supply,” Problemele Energeticii Regionale, vol. 53, no. 1, pp. 141–151, 2022.

B. Soldo, “Forecasting natural gas consumption,” Appl Energy, vol. 92, pp. 26–37, 2012.

M. Mohebbi and B. Sobhani, “Enhancing Residential Electricity Consumption Forecasting with Meta-Heuristic Algorithms,” Advances in Engineering and Intelligence Systems, vol. 003, no. 02, pp. 143–175, 2024, doi: 10.22034/aeis.2024.458696.1197.

D. Bajatović, A. S. AnĐelković, I. Ćosić, and R. Maksimović, “Application of predictive models for natural gas needs-current state and future trends review,” Tehnički vjesnik, vol. 27, no. 2, pp. 648–655, 2020.

J. Liu, S. Wang, N. Wei, X. Chen, H. Xie, and J. Wang, “Natural gas consumption forecasting: A discussion on forecasting history and future challenges,” J Nat Gas Sci Eng, vol. 90, no. February, p. 103930, 2021, doi: 10.1016/j.jngse.2021.103930.

M. J. Verhulst, “The theory of demand applied to the French gas industry,” Econometrica, pp. 45–55, 1950.

R. Svoboda, S. Basterrech, J. Kozal, J. Platos, and M. Wozniak, “A Natural Gas Consumption Forecasting System for Continual Learning Scenarios based on Hoeffding Trees with Change Point Detection Mechanism,” Aug. 2024.

L. Zhang, X. Ma, H. Zhang, G. Zhang, and P. Zhang, “Multi-Step Ahead Natural Gas Consumption Forecasting Based on a Hybrid Model: Case Studies in The Netherlands and the United Kingdom,” Energies (Basel), vol. 15, no. 19, p. 7437, Oct. 2022, doi: 10.3390/en15197437.

H. Khajavi and A. Rastgoo, “Improving the prediction of heating energy consumed at residential buildings using a combination of support vector regression and meta-heuristic algorithms,” Energy, vol. 272, p. 127069, Jun. 2023, doi: 10.1016/j.energy.2023.127069.

X. Zhou et al., “Towards Universal Large-Scale Foundational Model for Natural Gas Demand Forecasting,” Sep. 2024.

J. Zhou, Q. Wang, H. Khajavi, and A. Rastgoo, “Sensitivity analysis and comparative assessment of novel hybridized boosting method for forecasting the power consumption,” Expert Syst Appl, vol. 249, p. 123631, Sep. 2024, doi: 10.1016/j.eswa.2024.123631.

X. Jin, “Energy Station Data,” 2024, doi: 10.6084/m9.figshare.24978645.v1.

Y. Zhang, Z. Zhao, and J. Zheng, “CatBoost: A new approach for estimating daily reference crop evapotranspiration in arid and semi-arid regions of Northern China,” J Hydrol (Amst), vol. 588, p. 125087, 2020.

W. S. McCulloch and W. Pitts, “A logical calculus of the ideas immanent in nervous activity,” Bull Math Biophys, vol. 5, pp. 115–133, 1943.

M. Askari and F. Keynia, “Mid-term electricity load forecasting by a new composite method based on optimal learning MLP algorithm,” IET Generation, Transmission and Distribution, vol. 14, no. 5, pp. 845–852, 2020, doi: 10.1049/iet-gtd.2019.0797.

T. Chen and C. Guestrin, “Xgboost: A scalable tree boosting system,” in Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, 2016, pp. 785–794.

J. Ma, J. C. P. Cheng, Z. Xu, K. Chen, C. Lin, and F. Jiang, “Identification of the most influential areas for air pollution control using XGBoost and Grid Importance Rank,” J Clean Prod, vol. 274, p. 122835, 2020.

S. Li, H. Chen, M. Wang, A. A. Heidari, and S. Mirjalili, “Slime mould algorithm: A new method for stochastic optimization,” Future Generation Computer Systems, vol. 111, pp. 300–323, 2020.

J. Xue and B. Shen, “A novel swarm intelligence optimization approach: sparrow search algorithm,” Systems science & control engineering, vol. 8, no. 1, pp. 22–34, 2020.

L. Zhang, Y. Chen, and Z. Yan, “Predicting the short-term electricity demand based on the weather variables using a hybrid CatBoost-PPSO model,” Journal of Building Engineering, vol. 71, p. 106432, Jul. 2023, doi: 10.1016/J.JOBE.2023.106432.

A. Rastgoo and H. Khajavi, “A novel study on forecasting the Airfoil self-noise, using a hybrid model based on the combination of CatBoost and Arithmetic Optimization Algorithm,” Expert Syst Appl, p. 120576, 2023.

Downloads

Published

2026-04-20

How to Cite

Zhang, C. ., & Ren, M. . (2026). Optimizing Gas Consumption Predictions: A Comprehensive Study of Individual and Hybrid Modeling Approaches with Practical Implications for Energy Policies. Strategic Planning for Energy and the Environment, 45(02), 531–560. https://doi.org/10.13052/spee1048-5236.45210

Issue

2026: Vol 45 Iss 2

Section

Articles