ORIGINAL PAPER
Mid-term forecasting of crude oil prices using the hybrid CEEMDAN and CNN_LSTM deep learning model
1
Faculty of Informatics, University of Debrecen, Hungary
Submission date: 2024-03-06
Final revision date: 2024-06-17
Acceptance date: 2024-06-26
Publication date: 2024-12-11
Corresponding author
Herry Kartika Gandhi
Faculty of Informatics, University of Debrecen, Kassai, 4028, Debrecen, Hungary
Faculty of Informatics, University of Debrecen, Kassai, 4028, Debrecen, Hungary
Polityka Energetyczna – Energy Policy Journal 2024;27(4):19-38
KEYWORDS
forecastingcrude oil pricecomplete ensemble empirical mode decomposition with adaptive noiseconvolutional neural networklong short-term memory
TOPICS
ABSTRACT
Forecasting crude oil prices has always been a matter of discussion among energy experts. Due to a significant dependence of the global economy on crude oil, the volatility of the spot price can impact the supply and demand of the market. Moreover, crude oil is still the primary energy for transportation worldwide. Although renewable energy sources have developed significantly, crude oil has been dominant in transportation fuels in the last few decades. This study focuses on mid-term multi-step forecasting and provides a forecasting model that provides a robust prediction for 60 to 90 steps ahead. Our main objective is to develop a forecasting model that can maintain high accuracy and low errors. Our analysis uses a hybrid Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) and the Convolutional Neural Network, Long Short-Term Memory (CNN_LSTM) deep learning model. These three techniques, which have different advantages, are put together, and the combination of them is able to identify features (trend and seasonality) in historical data learning and perform high prediction accuracy for next-term prediction. We compared the proposed model with other decomposition and deep learning techniques. The proposed model shows lower Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE) values than other benchmark models for Brent and crude West Texas Intermediate (WTI) oil prices – the proposed model’s Mean Absolute Percentage Error (MAPE) results in better forecasting with MAPE values between 4 to 10. The simulation with box plot analysis also gives a quartile range value below 0.2, which shows the stability of the model in each iteration. Finally, the proposed model can provide a robust forecasting model for multi-step mid-term forecasting.
METADATA IN OTHER LANGUAGES:
Polish
Średniookresowe prognozowanie cen ropy naftowej przy użyciu hybrydowego modelu głębokiego uczenia CEEMDAN i CNN_LSTM
prognozowanie, cena ropy naftowej, kompletny rozkład trybu empirycznego zespołu z adaptacyjnym szumem, sieć neuronowa splotowa, pamięć długo-krótkotrwała
Prognozowanie cen ropy naftowej zawsze było przedmiotem dyskusji wśród ekspertów ds. energii. Ze względu na znaczną zależność światowej gospodarki od ropy naftowej, zmienność ceny spot może mieć wpływ na podaż i popyt na rynku. Ponadto ropa naftowa jest nadal podstawową energią dla transportu na całym świecie. Chociaż odnawialne źródła energii znacznie się rozwinęły, ropa naftowa dominuje w paliwach transportowych w ciągu ostatnich kilku dekad. Niniejsze badanie koncentruje się na prognozowaniu wieloetapowym w średnim okresie i dostarcza model prognostyczny, który zapewnia solidną prognozę na 60 do 90 kroków do przodu. Głównym celem jest opracowanie modelu prognostycznego, który może utrzymać wysoką dokładność i niskie błędy. Niniejsza analiza wykorzystuje hybrydowy model uczenia głębokiego Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) i model uczenia głębokiego Convolutional Neural Network, Long Short-Term Memory (CNN_LSTM). Dzięki połączeniu tych trzech różnych technik jesteśmy w stanie identyfikować cechy (trend i sezonowość) w uczeniu się danych historycznych i zapewniać wysoką dokładność prognozowania w przypadku prognozowania na następny okres. W artykule porównano proponowany model z innymi technikami dekompozycji i głębokiego uczenia. Proponowany model wykazuje niższe wartości średniego błędu bezwzględnego (MAE) i średniego błędu kwadratowego (RMSE) niż inne modele referencyjne dla cen ropy Brent i ropy West Texas Intermediate (WTI) – średni błąd procentowy bezwzględny proponowanego modelu (MAPE) skutkuje lepszym prognozowaniem z wartościami MAPE od 4 do 10. Symulacja z analizą wykresu pudełkowego daje również wartość zakresu kwartylowego poniżej 0,2, co pokazuje stabilność modelu w każdej iteracji. Wreszcie, proponowany model może zapewnić solidny model prognostyczny do wieloetapowego prognozowania średnioterminowego.
REFERENCES (29)
1.
Abdel-Khalek et al. 2019 – Abdel-Khalek, H., Schäfer, M., Vásquez, R., Unnewehr, J.F. and Weidlich, A. 2019. Forecasting cross-border power transmission capacities in Central Western Europe using artificial neural networks. Energy Informatics 2(12), pp. 1–13, DOI: 10.1186/s42162-019-0094-y.
2.
Abdollahi, H. 2020. A novel hybrid model for forecasting crude oil price based on time series decomposition. Applied Energy 267, pp. 115035–115045, DOI: 10.1016/j.apenergy.2020.115035.
3.
Bao et al. 2011 – Bao, Y., Zhang, X., Yu, L., Lai, K.K. and Wang, S. 2011. An integrated model using wavelet decomposition and least squares support vector machines for monthly crude oil prices forecasting. New Mathematics and Natural Computation 07(02), pp. 299–311, DOI: 10.1142/s1793005711001949.
4.
Brent Crude Oil Summary 2022. Trading Economics, in partnership with the World Bank. [Online] https://tradingeconomics.com/c... [Accessed: 2023-12-22].
5.
Cheng et al. 2021 – Cheng, Y., Zhu, Q., Peng, Y., Huang, X.F. and He, L.Y. 2021. Multiple strategies for a novel hybrid forecasting algorithm of ozone based on data-driven models. Journal of Cleaner Production 326, pp. 1–15, DOI: 10.1016/j.jclepro.2021.129451.
6.
Energy for Transportation. Stanford Understand Energy, United States. October 2023. [Online] https://understand-energy.stan... [Accessed: 2024-02-21].
7.
Fukushima, K. 1980. Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biological Cybernetics 36(4), pp. 193–202, DOI: 10.1007/BF00344251.
8.
Ghalayini, L. 2017. Modeling and forecasting spot oil price. Eurasian Business Review 7(3), pp. 355–373, DOI: 10.1007/s40821-016-0058-0.
9.
Hochreiter, S. and Schmidhuber, J. 1997. Long Short-Term Memory. Neural Computation 9(8), pp. 1735–1780, DOI: 10.1162/neco.1997.9.8.1735.
10.
Huang et al. 1996 – Huang, N.E., Shen, Z., Long, S.R., Wu, M.C., Shih, H.H., Yen, N., Tung, C.C. and Liu, H.H. 1996. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proceedings of the Royal Society A 454, pp. 903–995, 1998.
11.
Hubel, D.H. and Wiesel, T.N. 1959. Receptive fields of single neurones in the cat’s striate cortex. The Journal of Physiology 148(3), pp. 574–591, DOI: 10.1113/jphysiol.1959.sp006308.
12.
Kingma, D.P. and Ba, J.L. 2015. Adam: A method for stochastic optimization. 3rd International Conference on Learning Representations, ICLR 2015 – Conference Track Proceedings. arXiv:1412.6980.
13.
Lazzeri, F. 2020. Machine learning for time series forecasting with python. Wiley, p. 196, Indiana, DOI: 10.1002/9781119682394.
14.
Lewis, C.D. 1982. Industrial and Business Forecasting Methods: A Practical Guide to Exponential Smoothing and Curve Fitting. Butterworth Scientific, p. 40, London.
15.
Lu et al. 2021 – Lu, Q., Sun, S., Duan, H. and Wang, S. 2021. Analysis and forecasting of crude oil price based on the variable selection-LSTM integrated model. Energy Informatics 4(Suppl 2), pp. 47–66, DOI: 10.1186/s42162-021-00166-4.
16.
Ouahilal et al. 2017 – Ouahilal, M., Mohajir, M.El, Chahhou, M. and Mohajir, B.E.El. 2017. A novel hybrid model based on Hodrick–Prescott filter and support vector regression algorithm for optimizing stock market price prediction. Journal of Big Data 4(1), pp. 1–22, DOI: 10.1186/s40537-017-0092-5.
17.
Qunli et al. 2009 – Qunli, W., Ge, H. and Xiaodong, C. 2009. Crude oil price forecasting with an improved model based on wavelet transform and RBF neural network. Proceedings – 2009 International Forum on Information Technology and Applications, IFITA 2009 1, pp. 231–234, DOI: 10.1109/IFITA.2009.36.
18.
Ramyar, S. and Kianfar, F. 2019. Forecasting Crude Oil Prices: A Comparison Between Artificial Neural Networks and Vector Autoregressive Models. Computational Economics 53(2), pp. 743–761, DOI: 10.1007/s10614-017-9764-7.
19.
Saghi, F. and Rezaee, J.M. 2023. Integrating Wavelet Decomposition and Fuzzy Transformation for Improving the Accuracy of Forecasting Crude Oil Price. Computational Economics 61(2), pp. 559–591, DOI: 10.1007/s10614-021-10219-1.
20.
Shabri, A. and Samsudin, R. 2014. Daily crude oil price forecasting using hybridizing wavelet and artificial neural network model. Mathematical Problems in Engineering 2014, pp. 1–10, DOI: 10.1155/2014/201402.
21.
Spot Crude Oil Price: WTI 2022. Trading Economics, in partnership with the World Bank. [Online] https://tradingeconomics.com/u... [Accessed: 2023-12-22].
22.
Tissaoui et al. 2023 – Tissaoui, K., Zaghdoudi, T., Hakimi, A. and Nsaibi, M. 2023. Do Gas Price and Uncertainty Indices Forecast Crude Oil Prices? Fresh Evidence Through XGBoost Modeling. Computational Economics 62(2), pp. 663–687, DOI: 10.1007/s10614-022-10305-y.
23.
Torres et al. 2011 – Torres, M.E., Colominas, M.A., Schlotthauer, G. and Flandrin, P. 2011. A complete ensemble empirical mode decomposition with adaptive noise. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing – Proceedings (ICASSP), pp. 4144–4147, DOI: 10.1109/ICASSP.2011.5947265.
24.
Wu, Z. and Huang, N.E. 2009. Ensemble empirical mode decomposition: A noise-assisted data analysis method. Advances in Adaptive Data Analysis 1(1), pp. 1–41, DOI: 10.1142/S1793536909000047.
25.
Xiong et al. 2013 – Xiong, T., Bao, Y. and Hu, Z. 2013. Beyond one-step-ahead forecasting: Evaluation of alternative multi-step-ahead forecasting models for crude oil prices. Energy Economics 40, pp. 405–415, DOI: 10.1016/j.eneco.2013.07.028.
26.
Yu et al. 2008 – Yu, L., Wang, S. and Lai, K.K. 2008. Forecasting crude oil price with an EMD-based neural network ensemble learning paradigm. Energy Economics 30(5), pp. 2623–2635, DOI: 10.1016/j.eneco.2008.05.003.
27.
Yun et al. 2023 – Yun, P., Huang, X., Wu, Y. and Yang, X. 2023. Forecasting carbon dioxide emission price using a novel mode decomposition machine learning hybrid model of CEEMDAN-LSTM. Energy Science and Engineering 11(1), pp. 79–96, DOI: 10.1002/ese3.1304.
28.
Zhang et al. 2021 – Zhang, T., Tang, Z., Wu, J., Du, X. and Chen, K. 2021. Multi-step-ahead crude oil price forecasting based on two-layer decomposition technique and extreme learning machine optimized by the particle swarm optimization algorithm. Energy 229, pp. 1–13, DOI: 10.1016/j.energy.2021.120797.
29.
Zhang et al. 2022 – Zhang, Y., Wang, Y., Ma, F. and Wei, Y. 2022. To jump or not to jump: momentum of jumps in crude oil price volatility prediction. Financial Innovation 8(1), pp. 1–31, DOI: 10.1186/s40854-022-00360-7.
Share
RELATED ARTICLE
| eISSN: | 2720-569X |
| ISSN: | 1429-6675 |
We process personal data collected when visiting the website. The function of obtaining information about users and their behavior is carried out by voluntarily entered information in forms and saving cookies in end devices. Data, including cookies, are used to provide services, improve the user experience and to analyze the traffic in accordance with the Privacy policy. Data are also collected and processed by Google Analytics tool (more).
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
