Intelligent Electricity Load Forecasting Method using ARIMA-LSTM-Random Forest

• Autorzy: Aziukovskyi Oleksandr , Hnatushenko Volodymyr , Kashtan Vita , Polyanska Alla , Jamróz Andrzej

Identyfikatory

DOI

10.29227/IM-2025-01-18

Warianty tytułu

PL

Inteligentna metoda prognozowania obciążenia energią elektryczną z wykorzystaniem ARIMA-LSTM-Random Forest

• Języki publikacji: EN

Abstrakty

EN

The instability of energy systems caused by internal economic factors and external challenges, including geopolitical conflicts, significantly complicates the process of planning and managing energy resources. An essential tool for implementing energy-saving measures is introducing modern computer technologies, including artificial intelligence systems, in the energy sector. Intelligent technologies make it possible to use methods for predicting electrical load, including artificial intelligence algorithms. This paper proposes a combined ARIMA-LSTM-Random Forest model for forecasting electric load. The combination of the approaches allows considering both linear and nonlinear dependencies in the data, which is critical to ensure the accuracy of forecasts. Using data for the previous seven days provides enough information to identify seasonal trends and fluctuations, which makes this a promising prospect for medium-term forecasting in energy monitoring tasks. Thus, combining the ARIMA, LSTM, and Random Forest methods achieves high accuracy in forecasting electricity consumption. The proposed approach is an optimal solution since it combines the advantages of each model and compensates for their shortcomings. The proposed ARIMA-LSTM-Random Forest method significantly improved the results: MSE = 0.27, RMSE = 0.23, MAPE = 0.35%. The method minimized absolute and relative errors, confirming its advantage for this forecasting task. The results are promising for practical application in the load management of electric networks.

PL

Niestabilność systemów energetycznych, spowodowana wewnętrznymi czynnikami ekonomicznymi i wyzwaniami zewnętrznymi, w tym konfliktami geopolitycznymi, znacząco komplikuje proces planowania i zarządzania zasobami energetycznymi. Niezbędnym narzędziem wdrażania działań na rzecz oszczędności energii jest wprowadzenie do sektora energetycznego nowoczesnych technologii komputerowych, w tym systemów sztucznej inteligencji. Technologie inteligentne umożliwiają wykorzystanie metod prognozowania obciążenia elektrycznego, w tym algorytmów sztucznej inteligencji. W niniejszym artykule zaproponowano połączony model ARIMA-LSTM-Random Forest do prognozowania obciążenia elektrycznego. Połączenie tych podejść pozwala na uwzględnienie zarównoliniowych, jak i nieliniowych zależności w danych, co jest kluczowe dla zapewnienia dokładności prognoz. Wykorzystanie danychz ostatnich siedmiu dni dostarcza wystarczających informacji do identyfikacji trendów i wahań sezonowych, co czyni to obiecującą perspektywą dla prognozowania średnioterminowego w zadaniach monitorowania energii. Zatem połączenie metod ARIMA,LSTM i Random Forest pozwala osiągnąć wysoką dokładność prognozowania zużycia energii elektrycznej. Proponowane podejściejest rozwiązaniem optymalnym, ponieważ łączy zalety każdego modelu i kompensuje ich wady. Zaproponowana metoda ARIMA--LSTM-Random Forest znacząco poprawiła wyniki: MSE = 0,27, RMSE = 0,23, MAPE = 0,35%. Metoda zminimalizowała błędybezwzględne i względne, co potwierdza jej przewagę w tym zadaniu prognostycznym. Wyniki są obiecujące pod kątem praktycznychzastosowań w zarządzaniu obciążeniem sieci elektroenergetycznych.

Słowa kluczowe

EN

electricity load forecasting; intelligent method; ARIMA; LSTM; Random Forest

PL

prognozowanie obciążenia energią elektryczną; metoda inteligentna; ARIMA; LSTM; las losowy

• Wydawca: Polskie Towarzystwo Przeróbki Kopalin
• Czasopismo: Inżynieria Mineralna
• Rocznik: 2025
• Tom: Vol. 1, no. 1
• Strony: 123--132
• Opis fizyczny: Bibliogr. 37 poz., rys., tab., wykr.

Twórcy

autor

Aziukovskyi Oleksandr

• Electric Drive Department, Faculty of Electrical Engineering, Dnipro University of Technology, Dmytra Yavornytskoho Ave 19, Dnipro, Ukraine

• https://orcid.org/0000-0003-1901-4333

autor

Hnatushenko Volodymyr

• Information Technology and Computer Engineering Department, Faculty of Information Technologies, Dnipro University of Technology, Dmytra Yavornytskoho Ave 19, Dnipro, Ukraine

• https://orcid.org/0000-0003-3140-3788

autor

Kashtan Vita

• Information Technology and Computer Engineering Department, Faculty of Information Technologies, Dnipro University of Technology, Dmytra Yavornytskoho Ave 19, Dnipro, Ukraine

• https://orcid.org/0000-0002-0395-5895

autor

Polyanska Alla

• Management and Administration Department, Institute of Economics and Management, Ivano-Frankivska National Technikal University of Oil and Gas, Karpatska, 15, Ukraine
• AGH University of Krakow, Faculty of Management, al. Mickiewicza 30, 30-059 Kraków, Poland

• https://orcid.org/0000-0001-5169-1866

autor

Jamróz Andrzej

• AGH University of Krakow, Faculty of Management, al. Mickiewicza 30, 30-059 Kraków, Poland

• https://orcid.org/0000-0002-1847-8630

Bibliografia

• 1. Ye, H., Yang, B., Han, Y., & Chen, N. (2022). State-Of-The-Art Solar Energy Forecasting Approaches: Critical Potentials and Challenges. Frontiers in Energy Research, 10, 268. https://doi.org/10.3389/fenrg.2022.875790.
• 2. Kashtan, V., Hnatushenko, V. (2023). Deep Learning Technology for Automatic Burned Area Extraction Using Satellite High Spatial Resolution Images. In: Babichev, S., Lytvynenko, V. (eds) Lecture Notes in Data Engineering, Computational Intelligence, and Decision Making. ISDMCI 2022. Lecture Notes on Data Engineering and Communications Technologies, vol 149. Springer, Cham. https://doi.org/10.1007/978-3-031-16203-9_37.
• 3. Kashtan, V., Hnatushenko, V. (2023). Automated building damage detection on digital imagery using machine learning. Naukovyi Visnyk Natsionalnoho Hirnychoho Universytetu, № 6. P.134-140. https://doi.org/10.33271/nvngu/2023-6/134.
• 4. Kyrylenko O. (2022). Measures and Ways of Transforming Ukraine’s Energy Sector into an Intelligent Environmentally Friendly System. Visnyk Natsionalnoi Akademii Nauk Ukrainy. No 3. PP. 18-23. https://doi.org/10.15407/visn2022.03.018.
• 5. Kyrylenko, O., Shcherba, A., Kucheriava, I. (2021). Intellectual technologies for monitoring of technical state of up-to-date high-voltage cable power lines. Tekhnichna Elektrodynamika. 2021. 29-40. https://doi.org/10.15407/techned2021.06.029 .
• 6. Psyuk, V., & Polyanska, A. (2024). The usege of artificial intelligence in the activities of mining enterprises. E3S Web of Conferences, 526, 01016. https://doi.org/10.1051/e3sconf/202452601016
• 7. Polyanska, A., Pazynich, Y., Petinova, O., Nesterova, O., Mykytiuk, N., & Bodnar, G. (2024). Formation of a Culture of Frugal Energy Consumption in the Context of Social Security, pp. 60-87. The Journal of the International Committee for the History of Technology, 29(2), 60–87. https://doi.org/10.11590/icon.2024.2.03
• 8. Pavlychenko, A., Sala, D., Pyzalski, M., Dybrin, S., Antoniuk, O., & Dychkovskyi, R. (2025). Utilizing Fuel and Energy Sector Waste as Thermal Insulation Materials for Technical Buildings. Energies, 18(9), 2339. https://doi.org/10.3390/en18092339
• 9. Lewicka, D. (2020). Employee institutional trust as an antecedent of diverse dimensions of organisational commitment. Argumenta Oeconomica, 2019(1), 321–340. https://doi.org/10.15611/aoe.2020.1.13
• 10. Dychkovskyi, R.O., Tymoshenko, Y.V., Astafiev, D.O. (2014). Method of analytical investigation of wall advance speed and forms of line face influence on stress-strain state of a rock massif. Naukovyi Visnyk Natsionalnoho Hirnychoho Universytetu, (1), 11–16
• 11. Pivniak, H., Aziukovskyi, O., Papaika, Yu., Lutsenko, I., Neuberger, N. (2022). Problems of development of innovative power supply systems of Ukraine in the context of European integration. Naukovyi Visnyk Natsionalnoho Hirnychoho Universytetu, (5), 89-103. https://doi.org/10.33271/nvngu/2022-5/089.
• 12. Sytnyk, R., Hnatushenko, V., Hnatushenko, V. (2022). Decentralized Information System for Supply Chain Management Using Blockchain. IntelITSIS’2022: 3nd International Workshop on Intelligent Information Technologies and Systems of Information Security, Khmelnytskyi, Ukraine. http://ceur-ws.org/Vol-3156/paper45.pdf .
• 13. Smyl, S. (2020). A hybrid method of exponential smoothing and recurrent neural networks for time series forecasting. Int. J. Forecast. 36, 75–85. https://doi.org/10.1016/j.ijforecast.2019.03.017.
• 14. Kim, Y., Son, H.-g., and Kim, S. (2019). Short term electricity load forecasting for institutional buildings. Energy Rep. 5, 1270–1280. https://doi.org/10.1016/j.egyr.2019.08.086.
• 15. Aasim, Singh, S. N., Mohapatra, A (2021). Data driven day-ahead electrical load forecasting through repeated wavelet transform assisted SVM model. Appl. Sof Comput. 111, 107730. https://doi.org/10.1016/j.asoc.2021.107730.
• 16. Li, Y., Jia, Y., Li, L., Hao, J., and Zhang, X. (2020). Short term power load forecasting based on a stochastic forest algorithm. power Syst. Prot. control 48, 117–124. https://doi.org/10.1109/ICVRIS51417.2020.00202.
• 17. Wang, Y., Sun, S., Chen, X., Zeng, X., Kong, Y., Chen, J., et al. (2021a). Short-term load forecasting of industrial customers based on SVMD and XGBOOST. Int. J. Electr. Power and Energy Syst. 129, 106830. https://doi.org/10.1016/j.ijepes.2021.106830.
• 18. Dai, Y., Zhou, Q., Leng, M., Yang, X., and Wang, Y. (2022). Improving the bi-LSTM model with xgboost and attention mechanism: A combined approach for short-term power load prediction. Appl. Sof Comput. 130, 109632. https://doi.org/10.1016/j.asoc.2022.109632.
• 19. Mohammed, N. A., Al-Bazi, A. (2022). An adaptive backpropagation algorithm for long-term electricity load forecasting. Neural Comput. Appl. 34, 477–491. doi:10.1007/s00521-021-06384-x
• 20. Pavićević, M., Popović, T. (2022). Forecasting day-ahead electricity metrics with artificial neural networks. Sensors 22, 1051. https://doi.org/10.3390/s22031051.
• 21. Qiao, W. (2018). Intelligent pre-estimation method study on short-period power load. Jiangsu Electr. J., 13–17. https://doi.org/10.3390/en13226105.
• 22. Kong, W, Dong, Z,, Jia, Y, Hill, D,, Xu, Y., Zhang Y. (2017). Short-term residential load forecasting based on LSTM recurrent neural network. IEEE transactions on smart grid 2017; 10(1): 841–851.
• 23. Tan, M., Yuan, S., Li, S., Su, Y., Li, H., He, F. (2019). Ultra-short-term industrial power demand forecasting using LSTM based hybrid ensemble learning. IEEE transactions on power systems 2019; 35(4): 2937–2948.
• 24. Bouktif, S., Fiaz, A., Ouni, A., Serhani, M. (2018). Optimal deep learning lstm model for electric load forecasting using feature selection and genetic algorithm: Comparison with machine learning approaches. Energies; 11(7): 1636.
• 25. Tsegaye, S., Sanjeevikumar, P., Tjernberg, L., Fante, K. (2024) Short term load forecasting of electrical power distribution system using enhanced deep neural networks (DNNs). IEEE Access.
• 26. Mehra, A., Spreeuwers, L., & Strisciuglio, N. (2021). Deepfake Detection using Capsule Networks and Long Short-Term Memory Networks. Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, 407–414. https://doi.org/10.5220/0010289004070414
• 27. Wencheng, L., & Zhizhong, M. (2024). Short-Term Photovoltaic Power Forecasting Using Enhanced Bidirectional Long Short-Term Memory Networks. 2024 36th Chinese Control and Decision Conference (CCDC), 3308–3312. https://doi.org/10.1109/ccdc62350.2024.10587916
• 28. Dychkovskyi, R., Falshtynskyi, V., Ruskykh, V., Cabana, E., & Kosobokov, O. (2018). A modern vision of simulation modelling in mining and near mining activity. E3S Web of Conferences, 60, 00014. https://doi.org/10.1051/e3sconf/20186000014
• 29. Graw, J. H., Wood, W. T., & Phrampus, B. J. (2021). Predicting Global Marine Sediment Density Using the Random Forest Regressor Machine Learning Algorithm. Journal of Geophysical Research: Solid Earth, 126(1). https://doi.org/10.1029/2020jb020135
• 30. Pazynich, Y., Kolb, A., Korcyl, A., Buketov, V., & Petinova, O. (2024). Mathematical model and characteristics of dynamic modes for managing the asynchronous motors at voltage asymmetry. Polityka Energetyczna – Energy Policy Journal, 27(4), 39–58. https://doi.org/10.33223/epj/191779
• 31. Toronto Hydro website. https://www.torontohydro.com/SITES/ELECTRICSYSTEM/BUSINESS/YOURBILLOVERVIEW/NETSYSTEMLOADSHAPE/Pages/default.aspx
• 32. Kholodniak, Y., Havrylenko, Y., Halko, S., Hnatushenko, V., Suprun, O., Volina, T., Shchur, T. (2023). Improvement of the algorithm for setting the characteristics of interpolation monotone curve. Informatyka, Automatyka, Pomiary W Gospodarce I Ochronie Środowiska, 13(4), 44–50. https://doi.org/10.35784/iapgos.5392 .
• 33. Ruiyan, Z., Xingchen Z. (2024). Short-term power load forecasting based on ARIMA-LSTM. J. Phys.: Conf. Ser. 2803 012002. https://doi.org/10.1088/1742-6596/2803/1/012002.
• 34. Dongyan, F., Hai, S., Jun, Y., Kai, Z., Xia, Y., Zhixue, S. (2021). Well production forecasting based on ARIMA-LSTM model considering manual operations, Energy, Volume 220, 119708, https://doi.org/10.1016/j.energy.2020.119708.
• 35. Kasemset, C., Phuruan, K.t, Opassuwan, T. (2023). Shallot Price Forecasting Models: Comparison among Various Techniques. Production Engineering Archives. 29. 348-355. https://doi.org/10.30657/pea.2023.29.40.
• 36. Bareth, R., Yadav, A., Gupta, S., Pazoki, M. (2024). Daily average load demand forecasting using LSTM model based on historical load trends. IET Gener. Transm. Distrib. 18, 952–962. https://doi.org/10.1049/gtd2.13132
• 37. Sun, F., Huo, Y., Fu, L., Liu, H., Wang, X., Ma, Y. (2023). Load‐forecasting method for IES based on LSTM and dynamic similar days with multi‐features. Global Energy Interconnect. 6(3), 285–296. https://doi.org/10.1016/j.gloei.2023.06.003.