TY  - JOUR
T1  - INTEGRATING ECONOMETRIC AND DEEP LEARNING MODELS FOR ENERGY PRICE PREDICTION: A HYBRID APPROACH USING WEATHER AND MARKET DATA
TT  - ENERJİ FİYATI TAHMİNİ İÇİN EKONOMETRİK VE DERİN ÖĞRENME MODELLERİNİN ENTEGRASYONU: HAVA DURUMU VE PİYASA VERİLERİNİ KULLANAN KARMA BİR YAKLAŞIM
AU  - Öztürk, Cemal
PY  - 2025
DA  - June
Y2  - 2025
DO  - 10.55071/ticaretfbd.1578209
JF  - İstanbul Ticaret Üniversitesi Fen Bilimleri Dergisi
PB  - İstanbul Ticaret Üniversitesi
WT  - DergiPark
SN  - 1305-7820
SP  - 135
EP  - 175
VL  - 24
IS  - 47
LA  - en
AB  - This study proposes a hybrid approach that integrates econometric and deep learning models—specifically, Vector Autoregression (VAR), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU)—to enhance electricity price forecasting. By combining historical data with external factors like weather and market indicators, this hybrid approach aims to improve prediction accuracy in volatile energy markets. The model captures complex temporal dependencies through a hybrid VAR, LSTM, and GRU structure and is tested on historical electricity price data supplemented with weather and market variables. Performance is evaluated using mean absolute error (MAE), root mean square error (RMSE), symmetric mean absolute percentage error (SMAPE), and root mean squared logarithmic error (RMSLE). Results show that deep learning models, particularly GRU, outperform VAR regarding MAE, RMSE, and RMSLE, suggesting superior predictive accuracy for absolute and relative forecasting tasks. However, SMAPE results highlight that the VAR model performs better in capturing proportional errors, suggesting its relative robustness in volatile price environments. Including weather and market data significantly improves the model’s robustness and accuracy. This study’s hybrid approach combines the interpretability of econometric models with the predictive power of deep learning, offering insights into the impact of external factors on energy prices. The model supports better decision-making and risk management for energy market participants in dynamic market environments.
KW  - Energy Price Forecasting
KW  - Gated Recurrent Unit (GRU)
KW  - Long Short-Term Memory (LSTM)
KW  - Deep Learning Models
KW  - Time Series Analysis
N2  - Bu çalışma, elektrik fiyat tahminini geliştirmek için üç farklı modeli, ekonometrik (Vektör Otoregresyon, VAR) ve derin öğrenme tekniklerini (Uzun Kısa Süreli Bellek, LSTM ve Geçitli Tekrarlayan Birim, GRU) entegre ederek hibrit bir yaklaşım önermektedir. Geçmiş verileri hava durumu ve piyasa göstergeleri gibi dış faktörlerle birleştiren bu hibrit yaklaşım, değişken enerji piyasalarında tahmin doğruluğunu artırmayı amaçlamaktadır. Model, hibrit bir VAR, LSTM ve GRU yapısı aracılığıyla karmaşık zamansal bağımlılıkları yakalar ve hava durumu ve piyasa değişkenleri ile desteklenen geçmiş elektrik fiyatı verileri üzerinde test edilir. Performans, ortalama mutlak hata (MAE), kök ortalama kare hata (RMSE), simetrik ortalama mutlak yüzde hata (SMAPE) ve kök ortalama karesel logaritmik hata (RMSLE) kullanılarak değerlendirilmiştir. Sonuçlar, özellikle GRU olmak üzere derin öğrenme modellerinin MAE, RMSE ve RMSLE açısından VAR'dan daha iyi performans gösterdiğini ve mutlak ve göreceli tahmin görevleri için üstün tahmin doğruluğu sağladığını ortaya koymaktadır. Bununla birlikte, SMAPE sonuçları VAR modelinin oransal hataları yakalamada daha iyi performans gösterdiğini vurgulamakta ve bu da değişken fiyat ortamlarında göreceli sağlamlığını ortaya koymaktadır. Hava durumu ve piyasa verilerinin dahil edilmesi, modelin sağlamlığını ve doğruluğunu önemli ölçüde artırmaktadır. Bu çalışmanın hibrit yaklaşımı, ekonometrik modellerin yorumlanabilirliği ile derin öğrenmenin tahmin gücünü birleştirerek dış faktörlerin enerji fiyatları üzerindeki etkisine dair içgörüler sunmaktadır. Model, dinamik piyasa ortamlarında enerji piyasası katılımcıları için daha iyi karar alma ve risk yönetimini desteklemektedir.
CR  - Cao, M., Wang, Y., Liu, J., Yin, Z., Guo, X., & Ren, X. (2022). Day ahead electricity price forecasting based on the deep belief network. Wireless Communications and Mobile Computing, 2022, 1–8. https://doi.org/10.1155/2022/3960597
CR  - Cao, H., Xiao, W., Sun, J., Gan, M. G., & Wang, G. (2024, July). Fusing data-and model-driven methods for RUL prediction in smart manufacturing systems. 2024 43rd Chinese Control Conference (CCC), 6945–6949. IEEE.
CR  - Catalão, J. P. S., Mariano, S. J. P. S., Mendes, V. M. F., & Ferreira, L. A. F. M. (2007). Short-term electricity prices forecasting in a competitive market: A neural network approach. Electric Power Systems Research, 77(10), 1297–1304. https://doi.org/10.1016/j.epsr.2006.09.022
CR  - Chughatta, K. (2023). Short-term electricity price forecasting using EEMD and GRU-NN. International Journal of Advanced Natural Sciences and Engineering Researches, 7(4), 420–427. https://doi.org/10.59287/ijanser.772
CR  - Chung, J., Gulcehre, C., Cho, K., & Bengio, Y. (2014). Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling. ArXiv. https://arxiv.org/abs/1412.3555
CR  - Dash, S. K., & Dash, P. K. (2019). Short-term mixed electricity demand and price forecasting using adaptive autoregressive moving average and functional link neural network. Journal of Modern Power Systems and Clean Energy, 7(5), 1241–1255. https://doi.org/10.1007/s40565-019-0535-0
CR  - Gers, F. A., Schmidhuber, J., & Cummins, F. (2000). Learning to forget: Continual prediction with LSTM. Neural Computation, 12(10), 2451-2471. https://doi.org/10.1162/089976600300015015
CR  - Geetha, G., Shanthini, C., & Geethanjali, P. (2024). Non-conventional feature-based LSTM model for prediction of bearing performance degradation. Engineering Research Express. https://doi.org/10.1088/2631-8695/ad8d33
CR  - Grifa, M. (2018). Electric energy price forecasting: Descriptive analysis and features selection. International Journal of Pure and Applied Mathematics, 117(1), 15. https://doi.org/10.12732/ijpam.v117i1.15
CR  - Guo, W., & Zhao, Z. (2017). A novel hybrid BND-FOA-LSSVM model for electricity price forecasting. Information, 8(4), 120. https://doi.org/10.3390/info8040120
CR  - Hamilton, J. D. (2020). Time series analysis. Princeton University Press.
CR  - Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735
CR  - Hu, G., Fu, S., Zhong, S., Lin, L., Liu, Y., Zhang, S., & Guo, F. (2024). Remaining useful life prediction of mechanical equipment based on time-series auto-correlation decomposition and CNN. Measurement Science and Technology. https://doi.org/10.1088/1361-6501/ad5c8c
CR  - Kaggle. (2024). Predict energy behavior of prosumers [Data set]. Retrieved November 4, 2024, from https://www.kaggle.com/competitions/predict-energy-behavior-of-prosumers/data
CR  - Kara, A. (2021). A hybrid prognostic approach based on deep learning for the degradation prediction of machinery. SAUCIS, 4(2), 216–226. https://doi.org/10.35377/saucis.04.02.912154
CR  - Lütkepohl, H. (2005). New introduction to multiple time series analysis. Springer.
CR  - 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
CR  - Lehna, M., Scheller, F., & Herwartz, H. (2022). Forecasting day-ahead electricity prices: A comparison of time series and neural network models taking external regressors into account. Energy Economics, 106, 105742. https://doi.org/10.1016/j.eneco.2021.105742
CR  - Liu, X., Shen, J., & Li, Y. (2010). A generalized auto-regressive conditional heteroskedasticity model for system marginal price forecasting based on weighted double Gaussian distribution. Power System Technology, 34, 139–144.
CR  - Liang, J., Liu, H., & Xiao, N. (2024). A hybrid approach based on deep neural network and double exponential model for remaining useful life prediction. Expert Systems with Applications, 249, 123563. https://doi.org/10.1016/j.eswa.2024.123563
CR  - Mandal, P., Senjyu, T., & Funabashi, T. (2006). Neural networks approach to forecast several hour ahead electricity prices and loads in deregulated market. Energy Conversion and Management, 47(15–16), 2128–2142. https://doi.org/10.1016/j.enconman.2005.11.015
CR  - Mandal, P., Srivastava, A. K., Senjyu, T., & Negnevitsky, M. (2010). A new recursive neural network algorithm to forecast electricity price for PJM day-ahead market. International Journal of Energy Research, 34(6), 507–522. https://doi.org/10.1002/er.1569
CR  - Marín, J. B., Orozco, E. T., & Velilla, E. (n.d.). Forecasting electricity price in Colombia: A comparison between neural network, ARMA process and hybrid models.
CR  - Meher, S. (2020). Estimating and forecasting residential electricity demand in Odisha. Journal of Public Affairs, 20(3), e2065. https://doi.org/10.1002/pa.2065
CR  - Muniain, P., & Ziel, F. (2020). Probabilistic forecasting in day-ahead electricity markets: Simulating peak and off-peak prices. International Journal of Forecasting, 36(4), 1193–1210. https://doi.org/10.1016/j.ijforecast.2019.11.006
CR  - Nogueira, F. (2014). Bayesian Optimization. Retrieved from https://github.com/fmfn/BayesianOptimization.
CR  - Peng, L., Liu, S., Liu, R., & Wang, L. (2018). Effective long short-term memory with differential evolution algorithm for electricity price prediction. Energy, 162, 1301–1314. https://doi.org/10.1016/j.energy.2018.05.052
CR  - Sims, C. A. (1980). Macroeconomics and Reality. Econometrica, 48(1), 1–48. https://doi.org/10.2307/1912017
CR  - Su, H., Peng, X., Liu, H., Quan, H., Wu, K., & Chen, Z. (2022). Multi-step-ahead electricity price forecasting based on temporal graph convolutional network. Mathematics, 10(14), 2366. https://doi.org/10.3390/math10142366
CR  - Sun, A., Miao, X., Xu, K., & Jia, C. (2024). An adaptive method for predicting bearing remaining useful life across various degradation stages. Measurement Science and Technology, 36(1), 016154. https://doi.org/10.1088/1361-6501/ad903e
CR  - Uğurlu, U., Öksüz, İ., & Taş, O. (2018). Electricity price forecasting using recurrent neural networks. Energies, 11(5), 1255. https://doi.org/10.3390/en11051255
CR  - Wang, J., Du, Y., & Wang, J. (2020). LSTM based long-term energy consumption prediction with periodicity. Energy, 197, 117197. https://doi.org/10.1016/j.energy.2020.117197
CR  - Wang, D., Gryshova, I., Kyzym, M., Salashenko, T., Khaustova, V., & Shcherbata, M. (2022). Electricity price instability over time: Time series analysis and forecasting. Sustainability, 14(15), 9081. https://doi.org/10.3390/su14159081
CR  - Wang, Y., Lu, K., Dong, R., Fan, Y., & Jiang, X. (2024). Review of rolling bearings performance degradation trend prediction. Noise & Vibration Worldwide, 55(11), 585–604. https://doi.org/10.1177/09574565241282690
CR  - Xie, X., Li, M., & Zhang, D. (2021). A multiscale electricity price forecasting model based on tensor fusion and deep learning. Energies, 14(21), 7333. https://doi.org/10.3390/en14217333
CR  - Xuan, H., Nepal, R., & Jamasb, T. (2020). Electricity market integration, decarbonization and security of supply: Dynamic volatility connectedness in the Irish and Great Britain markets.
CR  - Yan, L., Yan, Z., Li, Z., Ma, N., Li, R., & Qin, J. (2023). Electricity market price prediction based on quadratic hybrid decomposition and THPO algorithm. Energies, 16(13), 5098. https://doi.org/10.3390/en16135098
CR  - Yao, M., Xie, W., & Mo, L. (2021). Short-term electricity price forecasting based on BP neural network optimized by SAPSO. Energies, 14(20), 6514. https://doi.org/10.3390/en14206514
CR  - Zareipour, H., Canizares, C., & Bhattacharya, K. (2010). Economic impact of electricity market price forecasting errors: A demand-side analysis. IEEE Transactions on Power Systems, 25(1), 254–262. https://doi.org/10.1109/TPWRS.2009.2030380
CR  - Zhang, J., & Cheng, C. (2008, October 6–7). Day-ahead electricity price forecasting using artificial intelligence. In Proceedings of the Electric Power Conference (pp. 1–5). Vancouver, BC, Canada. https://doi.org/10.1109/EPC.2008.4763350
CR  - Zhang, J., Wei, Y., Li, D., Tan, Z., & Zhou, J. (2018). Short term electricity load forecasting using a hybrid model. Energy, 158, 774-781. https://doi.org/10.1016/j.energy.2018.06.012
CR  - Zhong, B. (2023). Deep learning integration optimization of electric energy load forecasting and market price based on the ANN–LSTM–transformer method. Frontiers in Energy Research, 11, 1292204. https://doi.org/10.3389/fenrg.2023.1292204
CR  - Zhou, S., Zhou, L., Mao, M., Tai, H., & Wan, Y. (2019). An optimized heterogeneous structure LSTM network for electricity price forecasting. IEEE Access, 7, 108161-108173. https://doi.org/10.1109/ACCESS.2019.2932999
UR  - https://doi.org/10.55071/ticaretfbd.1578209
L1  - https://dergipark.org.tr/tr/download/article-file/4334982
ER  -