2. Home
  3. ARCHIVE
  4. 2025
  5. VOL 47, NO 2 (2025)
  6. pp. 48-66

MODEL FOR FORECASTING THE VOLUME OF ELECTRICITY CONSUMPTION USING THE «RANDOM FOREST» ALGORITHM

O.I. Kliuzko

Èlektron. model. 2025, 47(2):48-66

https://doi.org/10.15407/emodel.47.02.048

ABSTRACT

The article presents the peculiarities of applying the Random Forest (RF) algorithm for short-term forecasting of electricity consumption by consumers served by a supplier company. As a result of processing historical data using the RF algorithm, a forecasting model was developed that takes into account time, meteorological, and calendar features. Identification of the mo­del’s hyperparameters made it possible to achieve high accuracy in forecast calculations. The results of the experimental calculations demonstrate the effectiveness of the model, in particular, the possibility of finding its key qualifying parameters. The features of the model application in the decision-making system of the supplier company regarding the management of energy resources and minimization of the imbalance of electricity volumes in the market are shown.

KEYWORDS

Random Forest; forecasting; electricity consumption; machine learning; energy resources; predictive model.

REFERENCES

  1. Law of Ukraine No. 2019-VIII “On the electricity market”, 13 April 2017
  2. Xuan Y. et al., "Multi-Model Fusion Short-Term Load Forecasting Based on RF Feature Selection and Hybrid Neural Network," in IEEE Access, vol. 9, pp. 69002-69009, 2021, doi: 10.1109/ACCESS.2021.3051337.
  3. Pop, C.B., Chifu, V.R., Cordea, C., Chifu E.S. and Barsan, O. "Forecasting the Short-Term Energy Consumption Using Random Forests and Gradient Boosting," 2021 20th RoEduNet Conference: Networking in Education and Research (RoEduNet), Iasi, Romania, 2021, pp. 1-6, doi: 10.1109/RoEduNet54112.2021.9638276
  4. Lahouar, A. Ben Hadj Slama J. Day-ahead load forecast using random forest and expert input selection, Energy Conversion and Management, Volume 103, 2015, pp 1040-1051, ISSN 0196-8904, https://doi.org/10.1016/j.enconman.2015.07.041.
  5. Pang, X., Luan, C., Liu, L. et al. Data-driven random forest forecasting method of monthly electricity consumption. Electr Eng 104, 2045-2059 (2022). https://doi.org/10.1007/ s00202-021-01457-5
  6. Li, H., Zhou, Q., Tian J. and Lin, X. "Energy Demand Forecasting for an Office Building Based on Random Forests," 2020 IEEE 4th Conference on Energy Internet and Energy System Integration (EI2), Wuhan, China, 2020, pp. 29-32, doi: 10.1109/EI250167. 2020.9347021
  7. Rangelov, D., Boerger, M., Tcholtchev, N., Lämmel, P. and Hauswirth, M. "Design and Development of a Short-Term Photovoltaic Power Output Forecasting Method Based on RF, Deep Neural Network and LSTM Using Readily Available Weather Features," in IEEE Access, vol. 11, pp. 41578-41595, 2023, doi: 10.1109/ACCESS.2023.3270714.
  8. Magalhães, B., Bento, P., Pombo, J., Calado, M.d.R., Mariano, S. Short-Term Load Forecasting Based on Optimized Random Forest and Optimal Feature Selection. Energies 2024, 17, 1926. https://doi.org/10.3390/en17081926
  9. Sartini Sartini, Luthfia Rohimah, Yana Iqbal Maulana, Supriatin Supriatin, Dewi Yuliandari Optimization of RF Prediction for Industrial Energy Consumption Using Genetic Algorithms March 2023, PIKSEL Penelitian Ilmu Komputer Sistem Embedded and Lo­gic 11(1):35-44, DOI:10.33558/piksel.v11i1.5886
  10. Resolution of the NCRECP dated 28.12.2018 No. 2118 "On Approval of the Temporary Procedure for Determining Volumes of Electricity Purchases on the Electricity Market by Electricity Suppliers and Distribution System Operators for the Transitional Period" https://zakon.rada.gov.ua/rada/show/v2118874-18#n9
  11. Blinov, I., Parus, E., Klymenko, O., Kliuzko O. The method of comparative evaluations of commercial offers of electricity suppliers for consumers without hourly electricity mete­ring // Power engineering: economics, technique, ecology. 2023. P. 36-42. DOI: https://doi.org/10.20535/1813-5420.3.2023.289654
  12. Rangelov, D., Boerger, M., Tcholtchev, N., Lämmel P. and Hauswirth, M. “Design and Development of a Short-Term Photovoltaic Power Output Forecasting Method Based on RF, Deep Neural Network and LSTM Using Readily Available Weather Features” in IEEE Access, vol. 11, pp. 41578-41595, 2023, doi: 10.1109/ACCESS.2023.3270714.

Full text: PDF