M5P Karar Ağacı Algoritması Kullanılarak Enerji Kaynakları ile Brüt Elektrik Üretim Miktarının Tahmini

Abstract

Enerji konusu ülkeler açısından önemli bir durumdur. Enerji üretimini yeteri düzeyde sağlayabilen ülkelerin halkına daha refah bir hayat sunduğu söylenebilir. Enerji üretiminde ön planda olan elektrik, günlük hayatın vazgeçilmez bir öğesidir. Elektrik üretim sektörü dinamik ve karmaşık bir yapıdadır. Ekonomi, sağlık, spor vb. gibi tüm alanlarda modern yaşamın ve toplumsal ilerlemenin temel taşı olarak görülmektedir. Elektrikte üretimi yeterli derecede sağlamak ülkeler açısından önemli bir gelişmişlik göstergesidir. Bu bağlamda çalışma brüt elektrik üretimi konusuna odaklanılmıştır. Türkiye’nin brüt elektrik üretim değerinin tahmininin ortaya konulması amaçlanmıştır. 1985-2020 yılları arasındaki verilere dayanarak, 2021-2024 yılları arasının tahminleri yapılmıştır. Çalışmada makine öğrenmesi algoritmalarından M5P karar ağacı algoritmasından yararlanılmıştır. Brüt elektrik üretim değerinin tahminine etki eden değişkenler için ikili korelasyon öznitelik seçim algoritması kullanılmıştır. Tüm değişkenler ile yapılan tahminlerde yaklaşık %71, etkili değişkenler ile yapılan tahminlerde %86 başarı elde edilmiştir. Etkili değişkenler ile yapılan tahminlerde performansın arttığı ve MAPE değerinin %2.97 seviyesine gerilediği görülmüştür. Çalışma sonucunda, Türkiye’nin brüt elektrik üretiminde ‘Yenilenebilir enerji ve atıklar’ değişkeninin geleneksel kaynaklardan daha yüksek bir etki düzeyine sahip olduğu ampirik olarak kanıtlanmıştır. Bu bulgular, enerji politika yapıcıları için stratejik bir rehber niteliğindedir. Ayrıca brüt elektrik üretim değerinin tahminine etki eden diğer değişkenler olarak ‘Net tüketim’, ‘Toplam kurulu güç’ ve ‘Sıvı yakıtlar’ bulunmuştur.

Keywords

• Tahmin
• Brüt Elektrik Üretimi
• Enerji Kaynakları
• M5P Karar Ağacı Algoritması

Supporting Institution

Yok

Ethical Statement

Etik Kurul onayına gerek olmayan çalışmadır.

Thanks

Yok

Prediction of the Gross Electricity Generation Amount with Energy Sources Using the M5P Decision Tree Algorithm

Abstract

Energy is considered an important issue for countries. It is stated that countries that can provide sufficient energy generation offer their people a more prosperous life. Electricity, which is at the forefront of energy generation, is regarded as an indispensable element of daily life. The electricity generation sector is characterized by a dynamic and complex structure. It is seen as the cornerstone of modern life and social progress in all areas such as the economy, health, and sports. The insurance of sufficient electricity generation is viewed as an important indicator of development for countries. In this context, this study focuses on gross electricity generation. A prediction of Türkiye's gross electricity generation value is aimed to be presented. Based on data from 1985 to 2020, predictions for the period 2021-2024 were made. The M5P decision tree algorithm from machine learning algorithms was used in the study. The Pairwise correlation feature selection algorithm was used for selecting the variables that affect the prediction of gross electricity generation value. Approximately 71% accuracy was achieved in the predictions made with all variables, and 86% accuracy was achieved in the predictions made with the effective variables. The findings reveal that utilizing effective variables significantly enhances predictive performance, with the MAPE value dropping to a notable 2.97%. A key empirical contribution of this study is the demonstration that ‘Renewable energy and waste’ exerts a more substantial influence on Türkiye’s gross electricity generation than traditional energy sources. Consequently, these results offer a robust strategic framework for energy policymakers in navigating the national energy transition. It was observed that performance was increased in the predictions made with effective variables. Furthermore, other effective variables for the prediction of gross electricity generation were found to be ‘Net consumption’, ‘Total installed capacity’, and ‘Liquid fuels’.

Keywords

• Prediction
• Gross Electricity Generation
• Energy Sources
• M5P Decision Tree Algorithm

Supporting Institution

No

Ethical Statement

This study does not require Ethics Committee approval.

Thanks

No

References

1. Akgündoğdu, A., Öz, I., & Uzunoğlu, C. P. (2019). Signal quality based power output prediction of a real distribution transformer station using M5P model tree. Electric Power Systems Research, 177, 106003. https://doi.org/10.1016/j.epsr.2019.106003
2. AlNuaimi, N., Masud, M. M., Serhani, M. A., & Zaki, N. (2022). Streaming feature selection algorithms for big data: A survey. Applied Computing and Informatics, 18(1/2), 113-135. https://doi.org/10.1016/j.aci.2019.01.001
3. Atalan, Y. A., Şahin, H., Keskin, A., & Atalan, A. (2025). Strategic forecasting of renewable energy production for sustainable electricity supply: A machine learning approach considering environmental, economic, and oil factors in Türkiye. PLoS One, 20(8), e0328290. https://doi.org/10.1371/journal.pone.0328290
4. Atems, B., & Hotaling, C. (2018). The effect of renewable and nonrenewable electricity generation on economic growth. Energy Policy, 112, 111-118. https://doi.org/10.1016/j.enpol.2017.10.015
5. Bakay, M. S., & Başarslan, M. S. (2025). Forecasting of Türkiye's net electricity consumption with metaheuristic algorithms. Utilities Policy, 95, 101929. https://doi.org/10.1016/j.jup.2025.101929
6. Behnood, A., Behnood, V., Gharehveran, M. M., & Alyamac, K. E. (2017). Prediction of the compressive strength of normal and high-performance concretes using M5P model tree algorithm. Construction and Building Materials, 142, 199-207. https://doi.org/10.1016/j.conbuildmat.2017.03.061
7. Bilgili, M., & Pinar, E. (2023). Gross electricity consumption forecasting using LSTM and SARIMA approaches: A case study of Türkiye. Energy, 284, 128575. https://doi.org/10.1016/j.energy.2023.128575
8. Blaifi, S. A., Moulahoum, S., Benkercha, R., Taghezouit, B., & Saim, A. (2018). M5P model tree based fast fuzzy maximum power point tracker. Solar Energy, 163, 405-424. https://doi.org/10.1016/j.solener.2018.01.071

9. Bolón-Canedo, V., Sánchez-Maroño, N., & Alonso-Betanzos, A. (2015). Recent advances and emerging challenges of feature selection in the context of big data. Knowledge-based Systems, 86, 33-45. https://doi.org/10.1016/j.knosys.2015.05.014
10. Bórawski, P., Bełdycka-Bórawska, A., Klepacki, B., Holden, L., Rokicki, T., & Parzonko, A. (2024). Changes in gross nuclear electricity production in the European Union. Energies, 17(14), 3554. https://doi.org/10.3390/en17143554
11. Costantini, M., Cuaresma, J. C., & Hlouskova, J. (2016). Forecasting errors, directional accuracy and profitability of currency trading: The case of EUR/USD exchange rate. Journal of Forecasting, 35(7), 652-668. https://doi.org/10.1002/for.2398
12. De Myttenaere, A., Golden, B., Le Grand, B., & Rossi, F. (2016). Mean absolute percentage error for regression models. Neurocomputing, 192, 38-48. https://doi.org/10.1016/j.neucom.2015.12.114
13. Filiz, E. (2023). Evaluation of match results of five successful football clubs with ensemble learning algorithms. Research Quarterly for Exercise and Sport, 94(3), 773-782. https://doi.org/10.1080/02701367.2022.2053647
14. Gere, A., Sipos, L., & Héberger, K. (2015). Generalized pairwise correlation and method comparison: Impact assessment for JAR attributes on overall liking. Food Quality and Preference, 43, 88-96. https://doi.org/10.1016/j.foodqual.2015.02.017
15. Gross, R., Blyth, W., & Heptonstall, P. (2010). Risks, revenues and investment in electricity generation: Why policy needs to look beyond costs. Energy Economics, 32(4), 796-804. https://doi.org/10.1016/j.eneco.2009.09.017
16. Guidi, G., Violante, A. C., & De Iuliis, S. (2023). Environmental impact of electricity generation technologies: a comparison between conventional, nuclear, and renewable technologies. Energies, 16(23), 7847. https://doi.org/10.3390/en16237847
17. Jiménez, F., Sánchez, G., Palma, J., Miralles-Pechuán, L., & Botía, J. (2021). Multivariate feature ranking of gene expression data. arXiv preprint arXiv:2111.02357. https://doi.org/10.48550/arXiv.2111.02357
18. Karmellos, M., Kosmadakis, V., Dimas, P., Tsakanikas, A., Fylaktos, N., Taliotis, C., & Zachariadis, T. (2021). A decomposition and decoupling analysis of carbon dioxide emissions from electricity generation: Evidence from the EU-27 and the UK. Energy, 231, 120861. https://doi.org/10.1016/j.energy.2021.120861
19. Kucukali, S., & Baris, K. (2010). Turkey’s short-term gross annual electricity demand forecast by fuzzy logic approach. Energy Policy, 38(5), 2438-2445. https://doi.org/10.1016/j.enpol.2009.12.037
20. Laureti, L., Massaro, A., Costantiello, A., & Leogrande, A. (2023). The impact of renewable electricity output on sustainability in the context of circular economy: a global perspective. Sustainability, 15(3), 2160. https://doi.org/10.3390/su15032160
21. Liantoni, F., & Agusti, A. (2020). Forecasting bitcoin using double exponential smoothing method based on mean absolute percentage error. JOIV: International Journal on Informatics Visualization, 4(2), 91-95. http://dx.doi.org/10.30630/joiv.4.2.335
22. Lin, B., & Shi, L. (2022). New understanding of power generation structure transformation, based on a machine learning predictive model. Sustainable Energy Technologies and Assessments, 51, 101962. https://doi.org/10.1016/j.seta.2022.101962
23. Makridakis, S., & Hibon, M. (2000). The M3-Competition: results, conclusions and implications. International Journal of Forecasting, 16(4), 451-476. https://doi.org/10.1016/S0169-2070(00)00057-1
24. Meade, N. (2002). A comparison of the accuracy of short term foreign exchange forecasting methods. International Journal of Forecasting, 18(1), 67-83. https://doi.org/10.1016/S0169-2070(01)00111-X
25. Mostafavi, E. S., Mostafavi, S. I., Jaafari, A., & Hosseinpour, F. (2013). A novel machine learning approach for estimation of electricity demand: An empirical evidence from Thailand. Energy Conversion and Management, 74, 548-555. https://doi.org/10.1016/j.enconman.2013.06.031
26. Mujammal, M. A. H., Moualdia, A., Boulkhrachef, S., Wira, P., Boudana, D., & Albasheri, M. A. (2025). Advancing wind energy conversion: smart maximum power point based on M5-Pruned algorithm for enhanced wind energy production. Production Engineering, 19(2), 347-368. https://doi.org/10.1007/s11740-024-01315-w
27. Nhu, V. H., Shahabi, H., Nohani, E., Shirzadi, A., Al-Ansari, N., Bahrami, S., ... & Nguyen, H. (2020). Daily water level prediction of Zrebar Lake (Iran): A comparison between M5P, random forest, random tree and reduced error pruning trees algorithms. ISPRS International Journal of Geo-Information, 9(8), 479. https://doi.org/10.3390/ijgi9080479
28. Ohler, A., & Fetters, I. (2014). The causal relationship between renewable electricity generation and GDP growth: A study of energy sources. Energy Economics, 43, 125-139. https://doi.org/10.1016/j.eneco.2014.02.009
29. O'Mahoney, A., & Denny, E. (2013). Electricity prices and generator behaviour in gross pool electricity markets. Energy Policy, 63, 628-637. https://doi.org/10.1016/j.enpol.2013.08.098
30. Pamuk, N. (2016). Empirical analysis of causal relationship between electricity production and consumption demand in Turkey using Cobb-Douglas model. Journal of Polytechnic, 19(4), 415-420. https://izlik.org/JA84ZR83BW
31. Quinlan, J. R. (1992). Learning with continuous classes. In 5th Australian joint conference on artificial intelligence (Vol. 92, pp. 343-348). https://doi.org/10.1142/1897
32. Rahman, M. N., Esmailpour, A., & Zhao, J. (2016). Machine learning with big data an efficient electricity generation forecasting system. Big Data Research, 5, 9-15. https://doi.org/10.1016/j.bdr.2016.02.002
33. Reich, N. G., Lessler, J., Sakrejda, K., Lauer, S. A., Iamsirithaworn, S., & Cummings, D. A. (2016). Case study in evaluating time series prediction models using the relative mean absolute error. The American Statistician, 70(3), 285-292. https://doi.org/10.1080/00031305.2016.1148631
34. Saha, S., Kundu, B., Paul, G. C., & Pradhan, B. (2023). Proposing an ensemble machine learning based drought vulnerability index using M5P, dagging, random sub-space and rotation forest models. Stochastic Environmental Research and Risk Assessment, 37(7), 2513-2540. https://doi.org/10.1007/s00477-023-02403-6
35. Santarisi, N. S., & Faouri, S. S. (2021). Prediction of combined cycle power plant electrical output power using machine learning regression algorithms. Eastern-European Journal of Enterprise Technologies, 6(8), 114. https://doi.org/10.15587/1729-4061.2021.245663
36. Scarlat, N., Prussi, M., & Padella, M. (2022). Quantification of the carbon intensity of electricity produced and used in Europe. Applied Energy, 305, 117901. https://doi.org/10.1016/j.apenergy.2021.117901
37. Sharif Ali, S. S., Razman, M. R., & Awang, A. (2020). The nexus of population, GDP growth, electricity generation, electricity consumption and carbon emissions output in Malaysia. International Journal of Energy Economics and Policy, 10(3), 84-89. https://doi.org/10.32479/ijeep.8987
38. Solyali, D. (2020). A comparative analysis of machine learning approaches for short-/long-term electricity load forecasting in Cyprus. Sustainability, 12(9), 3612. https://doi.org/10.3390/su12093612
39. Tüfekci, P. (2014). Prediction of full load electrical power output of a base load operated combined cycle power plant using machine learning methods. International Journal of Electrical Power & Energy Systems, 60, 126-140. https://doi.org/10.1016/j.ijepes.2014.02.027
40. Turkish Statistical Institute (TurkStat). (2025). Web page, https://data.tuik.gov.tr/. Access date: 05.12.2025. Wang, Y. & Witten, I. H. (1996). Induction of model trees for predicting continuous classes. (Working paper 96/23). Hamilton, New Zealand: University of Waikato, Department of Computer Science.
41. Xiaosan, Z., Qingquan, J., Iqbal, K. S., Manzoor, A., & Ur, R. Z. (2021). Achieving sustainability and energy efficiency goals: assessing the impact of hydroelectric and renewable electricity generation on carbon dioxide emission in China. Energy Policy, 155, 112332. https://doi.org/10.1016/j.enpol.2021.112332
42. Zhang, J., Zhang, M., Yang, J., & Zheng, X. (2024). Prediction of electricity load generated by combined cycle power plants using integration of machine learning methods and HGS algorithm. Computers and Electrical Engineering, 120, 109644. https://doi.org/10.1016/j.compeleceng.2024.109644
43. Zhang, Q., Weili, T., Yumei, W., & Yingxu, C. (2007). External costs from electricity generation of China up to 2030 in energy and abatement scenarios. Energy Policy, 35(8), 4295-4304. https://doi.org/10.1016/j.enpol.2006.12.026