Market Clearing Price Prediction in The Turkish Energy Market: Comparison of Machine Learning Methods
DOI:
https://doi.org/10.63556/tisej.2025.1509Keywords:
Market Clearing Price (MCP), Energy Price Forecasting, Machine Learning, Turkey's Energy Market, Gaussian Process Regression (GPR)Abstract
The complex structure of energy markets and the predictability of prices in these markets hold great significance for both economic stability and sustainable development goals. Particularly in countries like Turkey, where energy demand is rapidly increasing, accurately forecasting the Market Clearing Price (MCP) enables market participants to make effective decisions and enhances the transparency of energy markets. This study comparatively analyzes the effectiveness of six different machine learning algorithms (Linear Regression, Decision Tree, Support Vector Machines, Gaussian Process Regression, Kernel Ridge Regression, and Neural Networks) for forecasting MCP in Turkey's energy market. Using energy market data from January 2012 to January 2023, the impacts of factors such as temperature, gross electricity consumption, total installed capacity, exchange rates, and Brent oil prices on MCP were examined. The results indicate that the Gaussian Process Regression (GPR) and Decision Tree (DT) models provide higher accuracy in MCP prediction compared to other methods. The GPR model demonstrated consistent performance in both training and testing phases, achieving the lowest RMSE and the highest R² values. Moreover, the DT model delivered stable results during the testing phase, ranking as the second-best performing model.
References
Arenas-Garcia, J., Petersen, K. B., Camps-Valls, G., & Hansen, L. K. (2013). Kernel Multivariate Analysis Framework for Supervised Subspace Learning: A Tutorial on Linear and Kernel Multivariate Methods. IEEE Signal Processing Magazine, 30(4), 16–29. https://doi.org/10.1109/MSP.2013.2250591
Bento, P. M. R., Pombo, J. A. N., Calado, M. R. A., & Mariano, S. J. P. S. (2018). A bat optimized neural network and wavelet transform approach for short-term price forecasting. Applied Energy, 210, 88–97. https://doi.org/10.1016/J.APENERGY.2017.10.058
Bertsimas, D., & King, A. (2016). OR Forum—An Algorithmic Approach to Linear Regression. Operations Research, 64(1), 2–16. https://doi.org/10.1287/opre.2015.1436
Bilgili, M., Ilhan, A., & Ünal, Ş. (2022). Time-series prediction of hourly atmospheric pressure using ANFIS and LSTM approaches. Neural Computing and Applications, 34(18), 15633–15648. https://doi.org/10.1007/s00521-022-07275-5
Cerjan, M., Petričić, A., & Delimar, M. (2019). HIRA Model for Short-Term Electricity Price Forecasting. Energies 2019, Vol. 12, Page 568, 12(3), 568. https://doi.org/10.3390/en12030568
Demircioğlu, M., & Eşİyok, S. (2022). Energy consumption forecast of Turkey using artificial neural networks from a sustainability perspective. International Journal of Sustainable Energy, 41(8), 1127–1141. https://doi.org/10.1080/14786451.2022.2026357
EPİAŞ. (2024). Enerji Piyasaları İşletme A.Ş. Erişim adresi: https://www.epias.com.tr
Gao, G., Lo, K., & Fan, F. (2010). Comparison of ARIMA and ANN Models Used in Electricity Price Forecasting for Power Market. 9, 120–126. https://doi.org/10.4236/epe.2017.94B015
Hamzaçebi, C., Es, H. A., & Çakmak, R. (2019). Forecasting of Turkey’s monthly electricity demand by seasonal artificial neural network. Neural Computing and Applications, 31(7), 2217–2231. https://doi.org/10.1007/s00521-017-3183-5
Kalfa, V. R., Arslan, B., & Ertuğrul, İ. (2021). Determining the Factors Affecting the Market Clearing Price by Using Multiple Linear Regression Method. Alphanumeric Journal, 9(1), 35–48. https://doi.org/10.17093/alphanumeric.882847
Karim, R., Alam, M. K., & Hossain, M. R. (2021). Stock market analysis using linear regression and decision tree regression. 2021 1st International Conference on Emerging Smart Technologies and Applications, ESmarTA 2021. https://doi.org/10.1109/esmarta52612.2021.9515762
Kemal, M., Y., Kucukcolak, N. I., & Kucukcolak, R. A. (2018). Market efficiency and risk premium in the Turkish wholesale electricity market. International Journal of Energy Economics and Policy, 8(5), 76–88.
Keskin, A., Ersin, I., & Atalan, A. (2024). Prıce Estımatıon Of Selected Graıns Products Based On Machıne Learnıng For Agrıcultural Economıc Development In Türkiye. The Journal of Animal and Plant Sciences, (5), 1290–1302. https://doi.org/10.36899/japs.2024.5.0811
Keskin, A., & Kara, B. (2021). The Relationship Between Electricity Generation, Electricity Consumption, and Economic Growth in Turkey 1975-2019. https://doi.org/10.4018/978-1-7998-8335-7.ch012
Keskin, A. (2025). Predicting and Reducing Patient Waiting Times in Dental Clinics Using Machine Learning: A Case Study from Türkiye. Black Sea Journal of Engineering and Science, 8(1), 243–248. https://doi.org/10.34248/bsengıneerıng.1574470
Khajeh, M. G., Maleki, A., Rosen, M. A., & Ahmadi, M. H. (2018). Electricity price forecasting using neural networks with an improved iterative training algorithm. International Journal of Ambient Energy, 39(2), 147–158. https://doi.org/10.1080/01430750.2016.1269674;wgroup:strıng:publıcatıon
Kölmek, M. A., & Navruz, I. (2015). Forecasting the day-ahead price in electricity balancing and settlement market of Turkey by using artificial neural networks. Turkish Journal of Electrical Engineering and Computer Sciences, 23(3), 841–852. https://doi.org/10.3906/elk-1212-136
Kruyt, B., van Vuuren, D. P., de Vries, H. J. M., & Groenenberg, H. (2009). Indicators for energy security. Energy Policy, 37(6), 2166–2181. https://doi.org/10.1016/j.enpol.2009.02.006
Kuo, P. H., & Huang, C. J. (2018). An Electricity Price Forecasting Model by Hybrid Structured Deep Neural Networks. Sustainability 2018, Vol. 10, Page 1280, 10(4), 1280. https://doi.org/10.3390/su10041280
Lago, J., De Ridder, F., & De Schutter, B. (2018). Forecasting spot electricity prices: Deep learning approaches and empirical comparison of traditional algorithms. Applied Energy, 221, 386–405. https://doi.org/10.1016/j.apenergy.2018.02.069
Li, K., Cursio, J. D., Jiang, M., & Liang, X. (2019). The significance of calendar effects in the electricity market. Applied Energy, 235, 487–494. https://doi.org/10.1016/j.apenergy.2018.10.124
Marrel, A., & Iooss, B. (2024). Probabilistic surrogate modeling by Gaussian process: A review on recent insights in estimation and validation. Reliability Engineering & System Safety, 247, 110094. https://doi.org/10.1016/j.ress.2024.110094
Mohammadi, S., Hesamzadeh, M. R., Vafamehr, A., & Ferdowsi, F. (2020). A Review of Machine Learning Applications in Electricity Market Studies. Proceedings of 2020 3rd International Colloquium on Intelligent Grid Metrology, smagrımet 2020, 15–22. https://doi.org/10.23919/smagrımet48809.2020.9264022
Naskath, J., Sivakamasundari, G., & Begum, A. A. S. (2023). A Study on Different Deep Learning Algorithms Used in Deep Neural Nets: MLP SOM and DBN. Wireless Personal Communications, 128(4), 2913–2936. https://doi.org/10.1007/S11277-022-10079-4/fıgures/7
Neupane, B., LeeWoon, W., & Aung, Z. (2017). Ensemble Prediction Model with Expert Selection for Electricity Price Forecasting. Energies 2017, Vol. 10, Page 77, 10(1), 77. https://doi.org/10.3390/en10010077
Polson, M., & Sokolov, V. (2020). Deep learning for energy markets. Applied Stochastic Models in Business and Industry, 36(1), 195–209. https://doi.org/10.1002/asm.2518
Purlu, M., Turkay, B. E., Andic, C., Aydin, E., Canol, B., & Kucukaslan, B. (2022). Market-Clearing Price Forecasting Using Keras in Turkish Day-Ahead Electricity Market. Proceedings - 2022 IEEE 4th Global Power, Energy and Communication Conference, GPECOM 2022, 517–522. https://doi.org/10.1109/gpecom55404.2022.9815603
Rafiei, M., Niknam, T., & Khooban, M. H. (2017). Probabilistic Forecasting of Hourly Electricity Price by Generalization of ELM for Usage in Improved Wavelet Neural Network. IEEE Transactions on Industrial Informatics, 13(1), 71–79. https://doi.org/10.1109/tıı.2016.2585378
Rao, A., Tedeschi, M., Mohammed, K. S., & Shahzad, U. (2024). Role of Economic Policy Uncertainty in Energy Commodities Prices Forecasting: Evidence from a Hybrid Deep Learning Approach. Computational Economics, 64(6), 3295–3315. https://doi.org/10.1007/S10614-024-10550-3/tables/4
Singh, N., Mohanty, S. R., & Dev Shukla, R. (2017). Short term electricity price forecast based on environmentally adapted generalized neuron. Energy, 125, 127–139. https://doi.org/10.1016/j.energy.2017.02.094
Song, Y.-Y., & Lu, Y. (2015). Decision tree methods: applications for classification and prediction. Shanghai Archives of Psychiatry, 27(2), 130–135. https://doi.org/10.11919/j.issn.1002-0829.215044
The MathWorks, Inc. (2024). MATLAB and Statistics Toolbox Release [2024a], Regression Learner. Massachusetts: The MathWorks, Inc.
Tschora, L., Pierre, E., Plantevit, M., & Robardet, C. (2022). Electricity price forecasting on the day-ahead market using machine learning. Applied Energy, 313, 118752. https://doi.org/10.1016/J.apenergy.2022.118752
Ugurlu, U., Oksuz, I., & Tas, O. (2018). Electricity Price Forecasting Using Recurrent Neural Networks. Energies 2018, Vol. 11, Page 1255, 11(5), 1255. https://doi.org/10.3390/en11051255
Weron, R. (2014). Electricity price forecasting: A review of the state-of-the-art with a look into the future. International Journal of Forecasting, 30(4), 1030–1081. https://doi.org/10.1016/j.ıjforecast.2014.08.008
Winzer, C. (2012). Conceptualizing energy security. Energy Policy, 46, 36–48. https://doi.org/10.1016/j.enpol.2012.02.067
Yang, W., Sun, S., Hao, Y., & Wang, S. (2022). A novel machine learning-based electricity price forecasting model based on optimal model selection strategy. Energy, 238, 121989. https://doi.org/10.1016/J.ENERGY.2021.121989
Yorulmuş, H., Uğurlu, U., & Taş, O. (2018). A long short term memory application on the Turkish intraday electricity price forecasting. PressAcademia Procedia, 7(1), 126–130. https://doi.org/10.17261/pressacademia.2018.867
Yunusova, P., & Kiran, M. S. (2022). Tree-Seed Programming for Modelling of Turkey Electricity Energy Demand. International Journal of Intelligent Systems and Applications in Engineering, 10(1), 142–152. https://doi.org/10.18201/ijisae.2022.278
Zahid, M., Ahmed, F., Javaid, N., Abbasi, R. A., Kazmi, H. S. Z., Javaid, A., … Ilahi, M. (2019). Electricity price and load forecasting using enhanced convolutional neural network and enhanced support vector regression in smart grids. Electronics, 8(2), 122. https://doi.org/10.3390/electronics8020122
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Abdulkadir KESKİN
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
