Comparative Analysis of CatBoost and BiLSTM Models for Day-Ahead Electricity Consumption Forecasting: A Case Study of Aydın, Denizli, and Muğla Regions in Turkey
Abstract views: 14
/ 
PDF downloads: 11
DOI:
https://doi.org/10.5281/zenodo.14188717Keywords:
Electricity Consumption Forecasting, Machine Learning, Deep Learning, Bidirectional Long Short-Term Memory, CatboostAbstract
Electricity consumption forecasting plays a crucial role in effective electricity management,
particularly for city-specific predictions made by distribution and retail companies, as it enables optimized
operations and efficient electricity allocation. In the context of the Turkish electricity market, inaccurate
forecasts can lead to substantial financial burdens, underscoring the need for accurate and reliable
predictions to ensure the smooth functioning of the market. This study focuses on forecasting hourly
electricity consumption for the following day using data available up to the previous day for the Aydın,
Denizli, and Muğla regions. A three-year dataset was employed to compare the performance of two
powerful machine learning models, CatBoost and Bidirectional Long Short-Term Memory (BiLSTM),
known for their ability to handle complex data and capture patterns over time. The results show that both
models are effective in short-term electricity consumption forecasting. CatBoost demonstrated higher
accuracy in capturing daily consumption fluctuations, while BiLSTM exhibited superior performance
during high-demand periods, highlighting its ability to manage complex seasonal consumption patterns.
This study contributes to electricity forecasting by offering insights into the application of these models in
real-world scenarios, particularly in the context of the Turkish electricity market. Future work could explore
additional factors influencing consumption and further refine the models for enhanced forecasting accuracy.
Downloads
References
E. Yüksel Haliloğlu ve B. E. Tutu, "Türkiye İçin Kısa Vadeli Elektrik Enerjisi Talep Tahmini," Yaşar Üniversitesi E-Dergisi, vol. 13, no. 51, pp. 243–255, 2018.
TEİAŞ, "Türkiye Elektrik Üretim İletim İstatistikleri," [Online]. Available: https://www.teias.gov.tr/turkiye-elektrik-uretim-iletim-istatistikleri. [Accessed: Nov. 10, 2024].
F. Şener, "Yük Tahmin Yöntemleri ve Ankara Merkez Metropol Alan İçin Regresyon Analizi Yöntemi Kullanılarak Uygulanması," M.S. thesis, Gazi Üniversitesi Fen Bilimleri Enstitüsü, Ankara, 2005.
E. Boltürk, "Elektrik Talebi Tahmininde Kullanılan Yöntemlerin Karşılaştırılması," Ph.D. dissertation, Fen Bilimleri Enstitüsü, 2013.
T. Akman, C. Yılmaz, ve Y. Sönmez, "Elektrik Yükü Tahmin Yöntemlerinin Analizi," GMBD, vol. 4, no. 3, pp. 168–175, 2018.
U. Yoldaş, "Elektrik enerjisinde yük tahmini yöntemleri ve Türkiye’nin 2005–2020 yılları arasındaki elektrik enerjisi talep gelişimi ve arz planlaması," M.S. thesis, Gazi Üniversitesi Fen Bilimleri Enstitüsü, Ankara, 2006, pp. 1–16.
M. Ertilav ve M. Aktel, "TEDAŞ (Türkiye Elektrik Dağıtım Anonim Şirketi) Özelleştirmesi," Uluslararası Alanya İşletme Fakültesi Dergisi, vol. 7, no. 2, 2015.
Y. Biçen, "Türkiye elektrik enerjisi piyasası gelişim süreci: Gün öncesi ve dengeleme güç piyasası özellikleri," Karaelmas Fen ve Mühendislik Dergisi, vol. 6, no. 2, pp. 432–438, 2016.
A. U. Özgül, "Elektrik piyasalarında spot fiyat modelleri: Türkiye örneği," [Online]. Available: https://hdl.handle.net/11499/27287. [Accessed: Nov. 10, 2024]
C. Hamzaçebi ve F. Kutay, "Yapay sinir ağları ile Türkiye elektrik enerjisi tüketiminin 2010 yılına kadar tahmini," Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi, vol. 19, no. 3, pp. 227–233, 2004.
H. K. Ozturk, H. Ceylan, O. E. Canyurt, ve A. Hepbasli, "Electricity estimation using genetic algorithm approach: a case study of Turkey," Energy, vol. 30, no. 7, pp. 1003–1012, 2005.
A. K. Topalli, I. Erkmen, ve I. Topalli, "Intelligent short-term load forecasting in Turkey," International Journal of Electrical Power & Energy Systems, vol. 28, no. 7, pp. 437–447, 2006.
E. Erdogdu, "Electricity demand analysis using cointegration and ARIMA modelling: A case study of Turkey," Energy Policy, vol. 35, no. 2, pp. 1129–1146, 2007.
K. Karabulut, A. Alkan, ve A. S. Yilmaz, "Long Term Energy Consumption Forecasting Using Genetic Programming," Mathematical and Computational Applications, vol. 13, no. 2, pp. 71–80, 2008.
M. Bılgılı, "Estimation of net electricity consumption of Turkey," Journal of Thermal Science & Technology/Isı Bilimi ve Tekniği Dergisi, vol. 29, no. 2, 2009.
M. D. Toksarı, "Estimating the net electricity energy generation and demand using the ant colony optimization approach: case of Turkey," Energy Policy, vol. 37, pp. 1181–1187, 2009.
S. Kucukali ve K. Baris, "Turkey’s short-term gross annual electricity demand forecast by fuzzy logic approach," Energy Policy, vol. 38, no. 5, pp. 2438–2445, 2010.
M. Çunkaş ve A. A. Altun, "Long term electricity demand forecasting in Turkey using artificial neural networks," Energy Sources Part B: Economics, Planning, and Policy, vol. 5, no. 3, pp. 279–289, 2010.
Ö. Demirel, A. Kakilli, ve M. Tektaş, "ANFIS ve ARMA modelleri ile elektrik enerjisi yük tahmini," Gazi Üniversitesi Mühendislik-Mimarlık Fakültesi Dergisi, vol. 25, no. 3, pp. 601–610, 2010.
V. Yiğit, "Genetik algoritma ile Türkiye net elektrik enerjisi tüketiminin 2020 yılına kadar tahmini," International Journal of Engineering Research and Development, vol. 3, no. 2, pp. 37–41, 2011.
A. Sözen, O. Isikan, T. Menlik, ve E. Arcaklioglu, "The forecasting of net electricity consumption of the consumer groups in Turkey," Energy Sources Part B: Economics, Planning, and Policy, vol. 6, pp. 20–46, 2011.
K. Kavaklioglu, "Modeling and prediction of Turkey’s electricity consumption using support vector regression," Applied Energy, vol. 88, no. 1, pp. 368–375, 2011.
E. Bolturk, B. Oztaysi, ve I. U. Sari, "Electricity Consumption Forecasting Using Fuzzy Time Series," in IEEE Symposium on Computational Intelligence and Informatics, Budapest, Hungary, 20–22 Nov. 2012, pp. 245–249.
K. Boran, "The Box Jenkins approach to forecast net electricity consumption in Turkey," Energy Sources Part A: Recovery, Utilization, and Environmental Effects, vol. 36, no. 5, pp. 515–524, 2014.
K. Kavaklioglu, "Robust electricity consumption modeling of Turkey using singular value decomposition," International Journal of Electrical Power & Energy Systems, vol. 54, pp. 268–276, 2014.
F. Kaytez, M. Taplamacioglu, E. Çam, ve F. Hardalaç, "Forecasting electricity consumption: A comparison of regression analysis, neural networks and least squares support vector machines," International Journal of Electrical Power & Energy Systems, vol. 67, 2015.
İ. I. Esener, T. Yüksel, ve M. Kurban, "Short-term load forecasting without meteorological data using AI-based structures," Turkish Journal of Electrical Engineering and Computer Sciences, vol. 23, no. 2, pp. 370–380, 2015.
H. H. Çevik ve M. Çunkaş, "Short-term load forecasting using fuzzy logic and ANFIS," Neural Computing and Applications, vol. 26, no. 6, pp. 1355–1367, 2015.
Ö. Tanidir ve O. B. Tör, "Accuracy of ANN based day-ahead load forecasting in Turkish power system: Degrading and improving factors," Neural Network World, vol. 25, no. 4, p. 443, 2015.
M. E. Günay, "Forecasting annual gross electricity demand by artificial neural networks using predicted values of socio-economic indicators and climatic conditions: Case of Turkey," Energy Policy, vol. 90, pp. 92–101, 2016.
C. Karaca ve H. Karacan, "Çoklu regresyon metoduyla elektrik tüketim talebini etkileyen faktörlerin incelenmesi," Selçuk Üniversitesi Mühendislik, Bilim ve Teknoloji Dergisi, vol. 4, no. 3, pp. 182–195, 2016.
C. Hamzaçebi, H. A. Es, ve R. Çakmak, "Forecasting of Turkey’s monthly electricity demand by seasonal artificial neural network," Neural Computing and Applications, vol. 31, pp. 2217–2231, 2019.
E. Yukseltan, A. Yucekaya, ve A. H. Bilge, "Forecasting electricity demand for Turkey: Modeling periodic variations and demand segregation," Applied Energy, vol. 193, pp. 287–296, 2017.
B. Başoğlu ve M. Bulut, "Kısa dönem elektrik talep tahminleri için yapay sinir ağları ve uzman sistemler tabanlı hibrit sistem geliştirilmesi," Mühendislik ve Fen Bilimleri Dergisi, vol. 4, no. 2, pp. 51–61, 2017.
H. Toros and D. Aydın, "Prediction of short-term electricity consumption by artificial neural networks using temperature variables," Avrupa Bilim ve Teknoloji Dergisi, no. 14, pp. 393–398, 2018.
E. Y. Haliloğlu and B. E. Tutu, "Türkiye için kısa vadeli elektrik enerjisi talep tahmini," Journal of Yaşar University, vol. 13, no. 51, pp. 243–255, 2018.
A. Tokgöz, "Recurrent Neural Network-Based Approaches for Electricity Consumption Forecasting," M.S. thesis, Istanbul Technical University, Istanbul, Turkey, 2018.
C. Hamzaçebi, H. A. Es, and R. Çakmak, "Forecasting of Turkey’s monthly electricity demand by seasonal artificial neural network," Neural Computing and Applications, vol. 31, no. 7, pp. 2217–2231, 2019.
E. Doruk, "Sakarya Bölgesi̇ Hanehalki Elektri̇k Tüketi̇mi̇ni̇n Dinami̇k Lineer Model İle Tahmi̇ni̇," M.S. thesis, Sakarya Üniversitesi, Sakarya, Turkey, 2019.
N. Özkurt, H. Ş. Öztura, and C. Güzeliş, "24-hour Electricity Consumption Forecasting for Day ahead Market with Long Short-Term Memory Deep Learning Model," in Proc. 12th International Conference on Electrical and Electronics Engineering (ELECO), Bursa, Turkey, 26–28 Nov. 2020, pp. 173–177.
F. Kaytez, "A hybrid approach based on autoregressive integrated moving average and least-square support vector machine for long-term forecasting of net electricity consumption," Energy, vol. 197, p. 117200, 2020.
M. Çetinkaya and T. Acarman, "Next-Day Electricity Demand Forecasting Using Regression," in Proc. 2021 International Conference on Artificial Intelligence and Smart Systems (ICAIS), 2021, pp. 1549–1554, IEEE.
H. Özbay and A. Dalcali, "Effects of COVID-19 on electric energy consumption in Turkey and ANN based short-term forecasting," Turkish Journal of Electrical Engineering & Computer Sciences, vol. 29, no. 1, pp. 78–97, 2021.
Y. E. Unutmaz, A. Demirci, S. M. Tercan, and R. Yumurtaci, "Electrical energy demand forecasting using artificial neural network," in Proc. 2021 3rd International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA), Bursa, Turkey, Jun. 2021, pp. 1–6, IEEE.
K. D. Ünlü, "A data-driven model to forecast multi-step ahead time series of Turkish daily electricity load," Electronics, vol. 11, no. 10, p. 1524, 2022.
M. Saglam, C. Spataru, and O. A. Karaman, "Electricity demand forecasting with use of artificial intelligence: the case of Gokceada Island," Energies, vol. 15, no. 16, p. 5950, 2022.
Ş. Emeç and G. Akkaya, "Turkey's long-term electricity consumption forecast," Journal of Scientific & Industrial Research, vol. 81, no. 12, pp. 1336–1341, 2022.
M. Comert and A. Yıldız, "A novel artificial neural network model for forecasting electricity demand enhanced with population-weighted temperature mean and the unemployment rate," Turkish Journal of Engineering, vol. 6, no. 2, pp. 178–189, 2021.
T. Ağır, "Hourly electricity consumption estimation methodology based on the metaheuristic algorithms," Research Square, vol. 3, Art. no. rs-1795394/v1, 2022.
D. Guven and M. O. Kayalica, "Analysing the determinants of the Turkish household electricity consumption using gradient boosting regression tree," Energy for Sustainable Development, vol. 77, p. 101312, 2023.
Z. Pala, "Prediction of Electricity Consumption in Türkiye with Time Series," Muş Alparslan Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi, vol. 4, no. 1, pp. 32–40, 2023.
İ. Y. Yarbaşı and A. K. Çelik, "The determinants of household electricity demand in Turkey: An implementation of the Heckman Sample Selection model," Energy, vol. 283, p. 128431, 2023.
M. Saglam, C. Spataru, and O. A. Karaman, "Forecasting Electricity Demand in Turkey Using Optimization and Machine Learning Algorithms," Energies, vol. 16, no. 11, p. 4499, 2023.
S. Yiğit, S. Turgay, Ç. Cebeci, and E. S. Kara, "Time-Stratified Analysis of Electricity Consumption: A Regression and Neural Network Approach in the Context of Turkey," Wseas Transactions on Power Systems, vol. 19, pp. 96–104, 2024.
S. Shen, P. G. Njock, A. Zhou, and H.-M. Lyu, "Dynamic prediction of jet grouted column diameter in soft soil using Bi-LSTM deep learning," Acta Geotechnica, vol. 16, 2021.
M. Saadi, N. Bouteraa, A. Redjati, and B. Mohamed, "A novel method for bearing fault diagnosis based on BiLSTM neural networks," The International Journal of Advanced Manufacturing Technology, vol. 125, pp. 1–16, 2023.
"Recurrent Modern LSTM," Deep Learning Book. [Online]. Available: https://d2l.ai/chapter_recurrent-modern/lstm.html. [Accessed: Nov. 10, 2024].
S. Hochreiter and J. Schmidhuber, "Long short-term memory," Neural Computation, vol. 9, no. 8, pp. 1735–1780, 1997.
F. A. Gers, J. Schmidhuber, and F. Cummins, "Learning to forget: Continual prediction with LSTM," Neural Computation, vol. 12, no. 10, pp. 2451–2471, 2000.
L. Prokhorenkova, G. Gusev, A. Vorobev, and A. V. Dorogush, "CatBoost: unbiased boosting with categorical features," arXiv preprint arXiv:1706.09516, 2017.
"Enercast," [Online]. Available: https://www.enercast.de/. [Accessed: Nov. 10, 2024].
"pvlib-python," PVLib Documentation. [Online]. Available: https://pvlib-python.readthedocs.io/en/stable/. [Accessed: Nov. 10, 2024].
