Oil Demand Forecasting from The Perspective of Alternatives

Yi Huang; Jing Yu; Wenhua Wu

doi:10.54097/zarzga50

Authors

Yi Huang
Jing Yu
Wenhua Wu

DOI:

https://doi.org/10.54097/zarzga50

Keywords:

Oil demand forecasting; Alternatives; Deep learning; Attention mechanism.

Abstract

In recent years, events such as oil sanctions, the Russia-Ukraine conflict, and the COVID-19 pandemic have led to global instability and extreme fluctuations in international oil prices. This has slowed the growth of oil consumption, while the development of new energy technologies and the introduction of alternative energy sources are gradually transforming China’s energy demand structure. Accurately forecasting oil demand has thus become crucial for national energy security and economic development. This paper predicts China’s future oil demand by examining commonly used energy sources and focusing on oil substitutes. Sixteen relevant factors were selected, and machine learning and neural network methods were applied to assess their impact on China's oil consumption demand. Experimental results demonstrate that considering oil substitutes in variable selection is feasible for predicting China’s oil demand. The combined LSTM and attention mechanism approach achieved the highest prediction accuracy, stability, and overall performance. The findings of this empirical study offer valuable insights for future research utilizing deep learning techniques to forecast oil demand.

Downloads

Download data is not yet available.

References

[1] Ou S, He X, Ji W, et al. Machine learning model to project the impact of COVID-19 on US motor gasoline demand[J]. Nature Energy, 2020, 5(9): 666-673.

[2] Wang Q, Zhang F. What does the China’s economic recovery after COVID-19 pandemic mean for the economic growth and energy consumption of other countries?[J]. Journal of Cleaner Production, 2021, 295: 126265.

[3] Zhang X, Pellegrino F, Shen J, et al. A preliminary simulation study about the impact of COVID-19 crisis on energy demand of a building mix at a district in Sweden[J]. Applied Energy, 2020, 280: 115954.

[4] Nakhli S R, Rafat M, Dastjerdi R B, et al. Oil sanctions and their transmission channels in the Iranian economy: A DSGE model[J]. Resources Policy, 2021, 70: 101963.

[5] Jian C, Ting L, Youhong Z. Analysis of oil consumption under different regional industrialization—An empirical study based on Path-STR model[J]. Chinese Journal of Management Science, 2017, 25(11): 47-57.

[6] Liu G W, Yan Q, Yang J B. World oil demand based on S-Curve Model of the transport sector[J]. Resources Science, 2018, 40(3): 547-557.

[7] Zhu H. Oil Demand Forecasting in Importing and Exporting Countries: AI-Based Analysis of Endogenous and Exogenous Factors[J]. Sustainability, 2023, 15(18): 13592.

[8] Huang Y, Li S, Wang R, et al. Forecasting oil demand with the development of comprehensive tourism[J]. Chemistry and Technology of Fuels and Oils, 2021, 57(2): 299-310.

[9] Weiqi X, Xue L, Yuejun J. Analysis of future trend prediction of China's petroleum consumption[J]. Operations Research and Management Science, 2009, 18(3): 1-7.

[10] Narayan P K, Smyth R. A panel cointegration analysis of the demand for oil in the Middle East[J]. Energy Policy, 2007, 35(12): 6258-6265.

[11] Dagoumas A, Perifanis T, Polemis M. An econometric analysis of the Saudi Arabia's crude oil strategy[J]. Resources Policy, 2018, 59: 265-273.

[12] Haitao C. GM (1, 1) model predicts China's oil demand[J]. Ecological Economy, 2014, 30(2): 127-131.

[13] Xi W F, Lu Y J, Chen Q, et al. Forecast of China’s Oil Demand Based on the Dynamic Gm (1,1) Model[J]. Journal of Yunnan Normal University,2015,35(04):41-45.

[14] Fatima T, Xia E, Ahad M. Oil demand forecasting for China: fresh evidence from structural time series analysis[J]. Environment, development and sustainability, 2019, 21: 1205-1224.

[15] Li H, Li H, Wang H. Research on Prediction of China's Oil Demand Based on the BP Neural Network Model[J]. Journal of China University of Petroleum (Edition of Social Science), 2015: 8-11.

[16] SUN M, DENG X, DONG T. Application of Neural Networks and Kalman Algorithm in Oil Demand Prediction[J]. Journal of Beijing Institute of Technology (Social Sciences Edition), 2013 (6): 10-15.

[17] Tang L F. CPSO-SVM Based Petroleum Demand Prediction[J]. Applied Mechanics and Materials, 2013, 273: 91-96.

[18] Behrang M A, Assareh E, Ghalambaz M, et al. Forecasting future oil demand in Iran using GSA (Gravitational Search Algorithm) [J]. Energy, 2011, 36(9): 5649-5654.

[19] Li J, Wang R, Wang J, et al. Analysis and forecasting of the oil consumption in China based on combination models optimized by artificial intelligence algorithms[J]. Energy, 2018, 144: 243-264.

[20] Al-Fattah S M, Aramco S. Application of the artificial intelligence GANNATS model in forecasting crude oil demand for Saudi Arabia and China[J]. Journal of Petroleum Science and Engineering, 2021, 200: 108368.

[21] Pindyck, R.S., Rubinfeld, D.L. Microeconomics. 9th ed [M]. Pearson, 2020.