A Novel Model for Spot Price Forecast of Natural Gas Based on Temporal Convolutional Network
Abstract
:1. Introduction
2. Related Work
- (1)
- We propose a unique time series forecasting model for forecasting natural gas spot prices. The unique dilated causal convolutions in TCN efficiently extend the model’s receptive field and minimize the amount of computation, allowing the model to improve prediction accuracy while also decreasing its operating time. The residual block structure in TCN ensures the deep network’s predictive ability. In addition, this model can more correctly capture natural gas price changes and forecast natural gas prices. Furthermore, the proposed model is simple and efficient, avoiding the redundancy introduced by hybrid models while maintaining excellent prediction accuracy.
- (2)
- The dynamic learning rate setting further improves the model’s predictive ability. The dynamic learning rate overcomes the problem of the model failing to converge due to a high learning rate, and the model easily falls into a locally optimal solution owing to a low learning rate, allowing the model to identify the optimal solution faster and with greater stability.
- (3)
- Comparing the model proposed in this research with the other three deep learning models, LSTM, GRU, and 1D-CNN, our model performs best at forecasting natural gas spot prices, demonstrating the usefulness and usability of TCN in natural gas spot price prediction. Accurate natural gas price forecasts can serve as critical supplements for personal investment planning, business strategic deployment, and the formation of national policies. Accurately forecasting natural gas prices will aid in ensuring national energy security and global economic stability, which are critical for practical purposes.
3. Methods
3.1. TCN
3.2. 1D-CNN
3.3. LSTM
3.4. GRU
4. Experiments and Results
4.1. Settings
4.2. Comparison of Prediction Results of Several Deep Learning Models
4.3. Multi-Step Prediction Performance and Elapsed Time in Several Models
4.4. Ablation Experiment with Dynamic Learning Rate Setting
4.5. Performance from Current Gas Price Forecast Studies
5. Discussion
6. Conclusions
Author Contributions
Funding
Data Availability Statement
Conflicts of Interest
References
- International Energy Agency (IEA) Gas Market Report, Q3-2021. Available online: https://www.iea.org/reports/gas-market-report-q3-2021 (accessed on 22 November 2022).
- Statistical Review of World Energy. Available online: https://www.bp.com/content/dam/bp/business-sites/en/global/corporate/pdfs/energy-economics/statistical-review/bp-stats-review-2021-full-report.pdf (accessed on 22 November 2022).
- Zou, C.; Yang, Z.; He, D.; Wei, Y.; Li, J.; Jia, A.; Chen, J.; Zhao, Q.; Li, Y.; Li, J.; et al. Theory, technology and prospects of conventional and unconventional natural gas. Pet. Explor. Dev. 2018, 45, 604–618. [Google Scholar] [CrossRef]
- Gürsan, C.; de Gooyert, V. The Systemic Impact of a Transition Fuel: Does Natural Gas Help or Hinder the Energy Transition? Renew. Sustain. Energy Rev. 2021, 138, 110552. [Google Scholar] [CrossRef]
- Luo, K.; Guo, Q.; Li, X. Can the Return Connectedness Indices from Grey Energy to Natural Gas Help to Forecast the Natural Gas Returns? Energy Econ. 2022, 109, 105947. [Google Scholar] [CrossRef]
- International Energy Agency (IEA) Gas. 2020. Available online: https://iea.blob.core.windows.net/assets/555b268e-5dff-4471-ac1d-9d6bfc71a9dd/Gas_2020.pdf (accessed on 22 November 2022).
- International Energy Agency (IEA) Gas Market Report, Q3-2022. Available online: https://iea.blob.core.windows.net/assets/c7e74868-30fd-440c-a616-488215894356/GasMarketReport%2CQ3-2022.pdf (accessed on 22 November 2022).
- Goncharuk, A.G.; Cirella, G.T. A Perspective on Household Natural Gas Consumption in Ukraine. Extr. Ind. Soc. 2020, 7, 587–592. [Google Scholar] [CrossRef]
- Huang, C.; Shen, Y.; Chen, Y.; Chen, H. A Novel Hybrid Deep Neural Network Model for Short-term Electricity Price Forecasting. Int. J. Energy Res. 2021, 45, 2511–2532. [Google Scholar] [CrossRef]
- Elaziz, M.A.; Ewees, A.A.; Alameer, Z. Improving Adaptive Neuro-Fuzzy Inference System Based on a Modified Salp Swarm Algorithm Using Genetic Algorithm to Forecast Crude Oil Price. Nat. Resour. Res. 2019, 29, 2671–2686. [Google Scholar] [CrossRef]
- Lin, L.; Jiang, Y.; Xiao, H.; Zhou, Z. Crude Oil Price Forecasting Based on a Novel Hybrid Long Memory GARCH-M and Wavelet Analysis Model. Physica A 2020, 543, 123532. [Google Scholar] [CrossRef]
- Ulgen, T.; Poyrazoglu, G. Predictor Analysis for Electricity Price Forecasting by Multiple Linear Regression. In Proceedings of the 2020 International Symposium on Power Electronics, Electrical Drives, Automation and Motion (SPEEDAM), Virtual Meeting, 24–26 June 2020; pp. 618–622. [Google Scholar]
- Dritsaki, C.; Stamatiou, P.P. Oil Consumption Forecasting Using ARIMA Models: An Empirical Study for Oil Consumption Forecasting Using ARIMA Models: An Empirical Study for Greece. Int. J. Energy Econ. Policy 2021, 11, 214–224. [Google Scholar] [CrossRef]
- Buchanan, W.K.; Hodges, P.; Theis, J. Which Way the Natural Gas Price: An Attempt to Predict the Direction of Natural Gas Spot Price Movements Using Trader Positions. Energy Econ. 2001, 23, 279–293. [Google Scholar] [CrossRef]
- Nguyen, H.T.; Nabney, I.T. Short-Term Electricity Demand and Gas Price Forecasts Using Wavelet Transforms and Adaptive Models. Energy 2010, 35, 3674–3685. [Google Scholar] [CrossRef] [Green Version]
- Salehnia, N.; Falahi, M.A.; Seifi, A.; Mahdavi Adeli, M.H. Forecasting Natural Gas Spot Prices with Nonlinear Modeling Using Gamma Test Analysis. J. Nat. Gas Sci. Eng. 2013, 14, 238–249. [Google Scholar] [CrossRef]
- Serletis, A.; Shahmoradi, A. Returns and Volatility in the NYMEX Henry Hub Natural Gas Futures Market. Quant. Empir. Anal. Energy Mark. 2007, 30, 193–204. [Google Scholar] [CrossRef]
- Abrishami, H.; Varahrami, V. Different Methods for Gas Price Forecasting. Cuad. Econ. 2011, 34, 137–144. [Google Scholar] [CrossRef] [Green Version]
- Busse, S.; Helmholz, P.; Weinmann, M. Forecasting Day Ahead Spot Price Movements of Natural Gas—An Analysis of Potential Influence Factors on Basis of a NARX Neural Network. In Multikonferenz Wirtschaftsinformatik 2012—Tagungsband der MKWI 2012; Institut für Wirtschaftsinformatik: St. Gallen, Switzerland, 2012; pp. 1395–1406. [Google Scholar]
- Wang, J.; Lei, C.; Guo, M. Daily Natural Gas Price Forecasting by a Weighted Hybrid Data-Driven Model. J. Pet. Sci. Eng. 2020, 192, 107240. [Google Scholar] [CrossRef]
- Čeperić, E.; Žiković, S.; Čeperić, V. Short-Term Forecasting of Natural Gas Prices Using Machine Learning and Feature Selection Algorithms. Energy 2017, 140, 893–900. [Google Scholar] [CrossRef]
- Su, M.; Zhang, Z.; Zhu, Y.; Zha, D. Data-Driven Natural Gas Spot Price Forecasting with Least Squares Regression Boosting Algorithm. Energies 2019, 12, 1094. [Google Scholar] [CrossRef] [Green Version]
- Su, M.; Zhang, Z.; Zhu, Y.; Zha, D.; Wen, W. Data Driven Natural Gas Spot Price Prediction Models Using Machine Learning Methods. Energies 2019, 12, 1680. [Google Scholar] [CrossRef] [Green Version]
- Livieris, I.E.; Pintelas, E.; Kiriakidou, N.; Stavroyiannis, S. An Advanced Deep Learning Model for Short-Term Forecasting U.S. Natural Gas Price and Movement. In IFIP Advances in Information and Communication Technology; Springer International Publishing: Berlin, Germany, 2020; Volume 585 IFIP, pp. 165–176. [Google Scholar]
- Bai, S.; Kolter, J.Z.; Koltun, V. An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling. arXiv 2018, arXiv:1803.01271. [Google Scholar]
- van den Oord, A.; Dieleman, S.; Zen, H.; Simonyan, K.; Vinyals, O.; Graves, A.; Kalchbrenner, N.; Senior, A.; Kavukcuoglu, K. WaveNet: A Generative Model for Raw Audio. arXiv 2016, arXiv:1609.03499. [Google Scholar]
- He, K.; Zhang, X.; Ren, S.; Sun, J. Deep Residual Learning for Image Recognition. In Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 12 June 2016; Volume 37, pp. 770–778. [Google Scholar]
- Yu, F.; Koltun, V. Multi-Scale Context Aggregation by Dilated Convolutions. In Proceedings of the 4th International Conference on Learning Representations, ICLR 2016—Conference Track Proceedings, San Juan, Puerto Rico, 23 November 2015. [Google Scholar]
- Shen, Y.; Ma, Y.; Deng, S.; Huang, C.-J.; Kuo, P.-H. An Ensemble Model Based on Deep Learning and Data Preprocessing for Short-Term Electrical Load Forecasting. Sustainability 2021, 13, 1694. [Google Scholar] [CrossRef]
- Abdeljaber, O.; Avci, O.; Kiranyaz, S.; Gabbouj, M.; Inman, D.J. Real-Time Vibration-Based Structural Damage Detection Using One-Dimensional Convolutional Neural Networks. J. Sound Vib. 2017, 388, 154–170. [Google Scholar] [CrossRef]
- LeCun, Y.; Boser, B.; Denker, J.S.; Henderson, D.; Howard, R.E.; Hubbard, W.; Jackel, L.D. Backpropagation Applied to Handwritten Zip Code Recognition. Neural Comput. 1989, 1, 541–551. [Google Scholar] [CrossRef]
- LeCun, Y.; Bottou, L.; Bengio, Y.; Haffner, P. Gradient-Based Learning Applied to Document Recognition. Proc. IEEE 1998, 86, 2278–2323. [Google Scholar] [CrossRef] [Green Version]
- Krizhevsky, A.; Sutskever, I.; Hinton, G.E. ImageNet Classification with Deep Convolutional Neural Networks. Commun. ACM 2017, 60, 84–90. [Google Scholar] [CrossRef] [Green Version]
- Harbola, S.; Coors, V. One Dimensional Convolutional Neural Network Architectures for Wind Prediction. Energy Convers. Manag. 2019, 195, 70–75. [Google Scholar] [CrossRef]
- Atef, S.; Eltawil, A.B. Assessment of Stacked Unidirectional and Bidirectional Long Short-Term Memory Networks for Electricity Load Forecasting. Electr. Power Syst. Res. 2020, 187, 106489. [Google Scholar] [CrossRef]
- Sherstinsky, A. Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) Network. Phys. D 2020, 404, 132306. [Google Scholar] [CrossRef] [Green Version]
- Kumar, S.; Hussain, L.; Banarjee, S.; Reza, M. Energy Load Forecasting Using Deep Learning Approach-LSTM and GRU in Spark Cluster. In Proceedings of the 2018 Fifth International Conference on Emerging Applications of Information Technology (EAIT) 2018, Kolkata, India, 12–13 January 2018; pp. 1–4. [Google Scholar] [CrossRef]
- Huang, C.; Shen, Y.; Kuo, P.; Chen, Y. Novel Spatiotemporal Feature Extraction Parallel Deep Neural Network for Forecasting Confirmed Cases of Coronavirus Disease 2019. Socioecon. Plann. Sci. 2020, 80, 100976. [Google Scholar] [CrossRef]
- Dataset. Available online: https://www.eia.gov/dnav/ng/hist/rngc1d.htm (accessed on 22 November 2022).
- Mouchtaris, D.; Sofianos, E.; Gogas, P.; Papadimitriou, T. Forecasting Natural Gas Spot Prices with Machine Learning. Energies 2021, 14, 5782. [Google Scholar] [CrossRef]
- Naderi, M.; Khamehchi, E.; Karimi, B. Journal of Petroleum Science and Engineering Novel Statistical Forecasting Models for Crude Oil Price, Gas Price, and Interest Rate Based on Meta-Heuristic Bat Algorithm. J. Pet. Sci. Eng. 2019, 172, 13–22. [Google Scholar] [CrossRef]
- Siddiqui, A.W. Predicting Natural Gas Spot Prices Using Artificial Neural Network. In Proceedings of the 2019 2nd International Conference on Computer Applications & Information Security (ICCAIS), Riyadh, Saudi Arabia, 1–3 May 2019; pp. 1–6. [Google Scholar]
- Gehring, J.; Auli, M.; Grangier, D.; Yarats, D.; Dauphin, Y.N. Convolutional Sequence to Sequence Learning. In Proceedings of the 34th International Conference on Machine Learning, ICML 2017, Sydney, Australia, 6–11 August 2017. [Google Scholar]
- Liang, C.; Ma, F.; Wang, L.; Zeng, Q. The Information Content of Uncertainty Indices for Natural Gas Futures Volatility Forecasting. J. Forecast. 2021, 40, 1310–1324. [Google Scholar] [CrossRef]
Evaluation | TCN | GRU | 1D-CNN | LSTM |
---|---|---|---|---|
RMSE | 0.687 | 0.783 | 0.805 | 0.953 |
MAE | 0.216 | 0.246 | 0.267 | 0.324 |
MAPE | 4.965 | 6.077 | 7.324 | 7.946 |
Forecast Performance | TCN | GRU | 1D-CNN | LSTM | |
---|---|---|---|---|---|
MAPE | +1 day | 4.965 | 6.077 | 7.324 | 7.946 |
+2 day | 6.959 | 7.891 | 9.409 | 9.172 | |
+3 day | 8.562 | 9.359 | 11.119 | 10.295 | |
+4 day | 9.459 | 10.417 | 12.061 | 11.234 | |
+5 day | 11.289 | 11.529 | 13.043 | 12.011 | |
Total elapsed time(s) | 179 | 616 | 128 | 811 |
Test | Proposed | w/o DLR |
---|---|---|
RMSE | 0.734 | 0.803 |
MAE | 0.219 | 0.365 |
MAPE | 4.946 | 9.915 |
Authors and Ref. | Data Date | Outcome | Proposed |
---|---|---|---|
Mouchtaris et al. [40] | December 2010–September 2020 | RMSE = 0.0384 | RMSE = 0.687 |
Čeperić et al. [21] | January 2010–January 2013 | RMSE = 13.75 | RMSE = 0.687 |
Naderi et al. [41] | October 2016–July 2017 | MAPE = 1.49% | MAPE = 4.965% |
Siddiqui. [42] | January 1997–October 2018 | MSE = 0.026 | MSE = 0.472 |
Su et al. [22] | January 2001–October 2018 | MAPE = 11.17% | MAPE = 4.965% |
Su et al. [23] | January 2001–December 2017 | MAE = 0.4493 | MAE = 0.224 |
Wang et al. [20] | January 1997–May 2019 | MAPE = 5.04% | MAPE = 4.965% |
Livieris et al. [24] | January 2015–December 2019 | RMSE = 0.093 | RMSE = 0.687 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Pei, Y.; Huang, C.-J.; Shen, Y.; Wang, M. A Novel Model for Spot Price Forecast of Natural Gas Based on Temporal Convolutional Network. Energies 2023, 16, 2321. https://doi.org/10.3390/en16052321
Pei Y, Huang C-J, Shen Y, Wang M. A Novel Model for Spot Price Forecast of Natural Gas Based on Temporal Convolutional Network. Energies. 2023; 16(5):2321. https://doi.org/10.3390/en16052321
Chicago/Turabian StylePei, Yadong, Chiou-Jye Huang, Yamin Shen, and Mingyue Wang. 2023. "A Novel Model for Spot Price Forecast of Natural Gas Based on Temporal Convolutional Network" Energies 16, no. 5: 2321. https://doi.org/10.3390/en16052321
APA StylePei, Y., Huang, C. -J., Shen, Y., & Wang, M. (2023). A Novel Model for Spot Price Forecast of Natural Gas Based on Temporal Convolutional Network. Energies, 16(5), 2321. https://doi.org/10.3390/en16052321