A TWO STAGE MODEL FOR DAY-AHEAD ELECTRICITY PRICE FORECASTING: INTEGRATING EMPIRICAL MODE DECOMPOSITION AND CATBOOST ALGORITHM

Abstract

Electricity price forecasting is crucial for the secure and cost-effective operation of electrical power systems. However, the uncertain and volatile nature of electricity prices makes the electricity price forecasting process more challenging. In this study, a two-stage forecasting model was proposed in order to accurately predict day-ahead electricity prices. Historical natural gas prices, electricity load forecasts, and historical electricity price values were used as the forecasting model inputs. The historical electricity and natural gas price data were decomposed in the first stage to extract more deep features. The empirical mode decomposition (EMD) algorithm was employed for the efficient decomposition process. In the second stage, the categorical boosting (CatBoost) algorithm was proposed to forecast day-ahead electricity prices accurately. To validate the effectiveness of the proposed forecasting model, a case study was conducted using the dataset from the Turkish electricity market. The proposed model results were compared with benchmark machine learning algorithms. The results of this study indicated that the proposed model outperformed the benchmark models with the lowest root mean squared error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and correlation coefficient (R) values of 8.3282%, 5.2210%, 6.9675%, and 86.2256%, respectively.

Keywords

• CatBoost regression
• Electricity price forecasting
• Empirical mode decomposition

References

1. J. Lago, G. Marcjasz, B. De Schutter, and R. Weron, “Forecasting day-ahead electricity prices: A review of state-of-the-art algorithms, best practices and an open-access benchmark,” Appl. Energy, vol. 293, no. December 2020, p. 116983, 2021, doi: 10.1016/j.apenergy.2021.116983.
2. R. Weron, “Electricity price forecasting : A review of the state-of-the-art with a look into the future,” Int. J. Forecast., vol. 30, no. 4, pp. 1030–1081, 2014, doi: 10.1016/j.ijforecast.2014.08.008.
3. L. Tschora, E. Pierre, M. Plantevit, and C. Robardet, “Electricity price forecasting on the day-ahead market using machine learning,” Appl. Energy, vol. 313, no. March, p. 118752, 2022, doi: 10.1016/j.apenergy.2022.118752.
4. P. Wang et al., “An Online Electricity Market Price Forecasting Method Via Random Forest,” IEEE Trans. Ind. Appl., vol. 58, no. 6, pp. 7013–7021, 2022.
5. C. Xiao, D. Sutanto, K. M. Muttaqi, M. Zhang, K. Meng, and Z. Y. Dong, “Online sequential extreme learning machine algorithm for better predispatch electricity price forecasting grids,” IEEE Trans. Ind. Appl., vol. 57, no. 2, pp. 1860–1871, 2021.
6. I. Shah, H. Bibi, S. Ali, L. Wang, and Z. Yue, “Forecasting one-day-ahead electricity prices for italian electricity market using parametric and nonparametric approaches,” IEEE Access, vol. 8, pp. 123104–123113, 2020.
7. H. Yang and K. R. Schell, “GHTnet : Tri-Branch deep learning network for real-time electricity price forecasting,” Energy, vol. 238, p. 122052, 2022, doi: 10.1016/j.energy.2021.122052.
8. H. Yang and K. R. Schell, “International Journal of Electrical Power and Energy Systems QCAE : A quadruple branch CNN autoencoder for real-time electricity price forecasting,” Int. J. Electr. Power Energy Syst., vol. 141, no. April, p. 108092, 2022, doi: 10.1016/j.ijepes.2022.108092.

9. J. Lago, F. De Ridder, and B. De Schutter, “Forecasting spot electricity prices: Deep learning approaches and empirical comparison of traditional algorithms,” Appl. Energy, vol. 221, no. April, pp. 386–405, 2018, doi: 10.1016/j.apenergy.2018.02.069.
10. S. Luo and Y. Weng, “A two-stage supervised learning approach for electricity price forecasting by leveraging different data sources,” Appl. Energy, vol. 242, no. February, pp. 1497–1512, 2019, doi: 10.1016/j.apenergy.2019.03.129.
11. T. Zhang, Z. Tang, J. Wu, X. Du, and K. Chen, “Short term electricity price forecasting using a new hybrid model based on two-layer decomposition technique and ensemble learning,” Electr. Power Syst. Res., vol. 205, no. July 2021, p. 107762, 2022, doi: 10.1016/j.epsr.2021.107762.
12. A. Meng et al., “Electricity price forecasting with high penetration of renewable energy using attention-based LSTM network trained by crisscross optimization,” Energy, vol. 254, p. 124212, 2022, doi: 10.1016/j.energy.2022.124212.
13. G. Memarzadeh and F. Keynia, “Short-term electricity load and price forecasting by a new optimal LSTM-NN based prediction algorithm,” Electr. Power Syst. Res., vol. 192, no. November 2020, p. 106995, 2021, doi: 10.1016/j.epsr.2020.106995.
14. Z. Shao, Q. Zheng, C. Liu, S. Gao, G. Wang, and Y. Chu, “A feature extraction- and ranking-based framework for electricity spot price forecasting using a hybrid deep neural network,” Electr. Power Syst. Res., vol. 200, no. September 2020, p. 107453, 2021, doi: 10.1016/j.epsr.2021.107453.
15. X. Xiong and G. Qing, “A hybrid day-ahead electricity price forecasting framework based on time series,” Energy, vol. 264, no. November 2022, p. 126099, 2023, doi: 10.1016/j.energy.2022.126099.
16. K. Bhatia, R. Mittal, J. Varanasi, and M. M. Tripathi, “An ensemble approach for electricity price forecasting in markets with renewable energy resources,” Util. Policy, vol. 70, no. July 2020, p. 101185, 2021, doi: 10.1016/j.jup.2021.101185.
17. M. Heidarpanah, F. Hooshyaripor, and M. Fazeli, “Daily electricity price forecasting using artificial intelligence models in the Iranian electricity market,” Energy, vol. 263, no. PE, p. 126011, 2023, doi: 10.1016/j.energy.2022.126011.
18. S. Demir, K. Mincev, K. Kok, and N. G. Paterakis, “Data augmentation for time series regression : Applying transformations , autoencoders and adversarial networks to electricity price forecasting ✩,” Appl. Energy, vol. 304, no. September, p. 117695, 2021, doi: 10.1016/j.apenergy.2021.117695.
19. W. Qiao and Z. Yang, “Forecast the electricity price of U . S . using a wavelet transform-based hybrid model,” Energy, vol. 193, p. 116704, 2020, doi: 10.1016/j.energy.2019.116704.
20. K. Iwabuchi, K. Kato, D. Watari, I. Taniguchi, and F. Catthoor, “Energy and AI Flexible electricity price forecasting by switching mother wavelets based on wavelet transform and Long Short-Term Memory,” Energy AI, vol. 10, no. May, p. 100192, 2022, doi: 10.1016/j.egyai.2022.100192.
21. D. H. Vu, K. M. Muttaqi, A. P. Agalgaonkar, and A. Bouzerdoum, “Short-term forecasting of electricity spot prices containing random spikes using a time-varying autoregressive model combined with kernel regression,” IEEE Trans. Ind. Informatics, vol. 15, no. 9, pp. 5378–5388, 2019.
22. A. Pourdaryaei, H. Mokhlis, H. A. Illias, S. H. A. Kaboli, and S. Ahmad, “Short-Term Electricity Price Forecasting via Hybrid Backtracking Search Algorithm and ANFIS Approach,” IEEE Access, vol. 7, pp. 77674–77691, 2019, doi: 10.1109/ACCESS.2019.2922420.
23. A. Pourdaryaei, H. Mokhlis, H. A. Illias, S. H. R. A. Kaboli, S. Ahmad, and S. P. Ang, “Hybrid ANN and artificial cooperative search algorithm to forecast short-term electricity price in de-regulated electricity market,” Ieee Access, vol. 7, pp. 125369–125386, 2019.
24. N. Bibi, I. Shah, A. Alsubie, S. Ali, and S. A. Lone, “Electricity Spot Prices Forecasting Based on Ensemble Learning,” IEEE Access, vol. 9, pp. 150984–150992, 2021, doi: 10.1109/ACCESS.2021.3126545.
25. A. L. I. N. Alkawaz and A. Abdellatif, “Day-Ahead Electricity Price Forecasting Based on Hybrid Regression Model,” IEEE Access, vol. 10, no. October, pp. 108021–108033, 2022, doi: 10.1109/ACCESS.2022.3213081.
26. S. Zhou, L. Zhou, M. Mao, H.-M. Tai, and Y. Wan, “An optimized heterogeneous structure LSTM network for electricity price forecasting,” IEEE Access, vol. 7, pp. 108161–108173, 2019.
27. R. Zhang, G. Li, and Z. Ma, “A deep learning based hybrid framework for day-ahead electricity price forecasting,” IEEE Access, vol. 8, pp. 143423–143436, 2020.
28. C. E. Shannon, “A mathematical theory of communication,” Bell Syst. Tech. J., vol. 27, no. 3, pp. 379–423, 1948.
29. N. E. Huang et al., “The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis,” Proc. R. Soc. London. Ser. A Math. Phys. Eng. Sci., vol. 454, no. 1971, pp. 903–995, 1998.
30. L. Prokhorenkova, G. Gusev, A. Vorobev, A. V. Dorogush, and A. Gulin, “CatBoost: unbiased boosting with categorical features,” Adv. Neural Inf. Process. Syst., vol. 31, 2018.
31. “Energy Exchange Istanbul,” 2023. https://www.epias.com.tr.