Enhancing Electricity Consumption Forecasting in The Republic of Kazakhstan Using Machine Learning
DOI:
https://doi.org/10.37385/jaets.v6i2.7425Keywords:
Forecasting, Holt-Winters Models, SARIMA, LSTM, Dickey-Fuller TestAbstract
Accurate electricity consumption forecasting is critical for optimizing energy management and ensuring grid stability. This study uses advanced machine learning techniques to enhance electricity consumption forecasting in the Republic of Kazakhstan. The research analyzes historical electricity consumption data from 2002 to 2022. Considering seasonal and temporal dependencies. Various forecasting models, including Holt-Winters, Seasonal ARIMA (SARIMA), and Long Short-Term Memory (LSTM) networks, are applied and compared in terms of accuracy and reliability. The results indicate that while traditional statistical models effectively capture seasonal patterns, machine learning-based approaches, particularly LSTM, demonstrate superior performance in identifying complex nonlinear trends. The study discusses the practical implications of accurate electricity consumption forecasting for energy management, demand-side optimization, and policymaking. The findings contribute to developing intelligent analytical frameworks for improving energy efficiency and sustainability in Kazakhstan’s power sector. This study enhances electricity consumption forecasting in Kazakhstan using machine learning models, improving accuracy and energy management. Scientifically, it advances predictive analytics in power systems. Practically, it aids grid stability and demand planning. And sustainability. Internationally, the findings contribute to global forecasting methodologies, benefiting energy sectors worldwide. LSTM outperforms traditional models, offering robust solutions for dynamic electricity demand. This study uses advanced machine learning techniques to improve electricity consumption forecasting in the Republic of Kazakhstan. Historical monthly data from 2002 to 2022 were collected from the National Statistics Bureau. We compared statistical models (Holt-Winters, SARIMA) with a Long Short-Term Memory (LSTM) neural network. Results show that while classical methods effectively capture seasonal trends, LSTM more accurately models nonlinearities and longer-term dependencies. The implications include enhanced planning for energy providers and policymakers, leading to better demand-side management and grid stability. Our findings contribute to developing intelligent forecasting systems in Kazakhstan’s power sector and provide an example for other regions with similar energy challenges.
Downloads
References
Abiodun, O. I., Jantan, A., Omolara, A. E., Dada, K. V., Mohamed, N. A., & Arshad, H. (2018). State-of-the-art in artificial neural network applications: A survey. Heliyon, 4(11). https://doi.org/10.1016/j.heliyon.2018.e00938
Alba, E. L., Oliveira, G. A., Ribeiro, M. H. D. M., & Rodrigues, É. O. (2024). Electricity Consumption Forecasting: An Approach Using Cooperative Ensemble Learning with SHapley Additive Explanations. Forecasting, 6(3), 839-863. https://doi.org/10.3390/forecast6030042
Albahli, S. (2025). LSTM vs. Prophet: Achieving Superior Accuracy in Dynamic Electricity Demand Forecasting. Energies, 18 (2), 278. https://doi.org/10.3390/en18020278
An, Y., Zhou, Y., & Li, R. (2019). Forecasting India’s electricity demand using a range of probabilistic methods. Energies, 12(13), 2574. https://doi.org/10.3390/en12132574
Atakhanova, Z., & Howie, P. (2007). Electricity demand in Kazakhstan. Energy Policy, 35(7), 3729-3743. https://doi.org/10.1016/j.enpol.2007.01.005
Behera, I., Nanda, P., Mitra, S., & Kumari, S. (2024). Machine Learning Approaches for Forecasting Financial Market Volatility. Machine Learning Approaches in Financial Analytics, 431-451. https://doi.org/10.1007/978-3-031-61037-0_20
Bergmeir, C., & Benítez, J.M. (2012). On the Use of Cross-Validation for Time Series Predictor Evaluation. Information Sciences, 191, 192–213. https://doi.org/10.1016/j.ins.2011.12.028
Box, G.E.P., Jenkins, G.M., & Reinsel, G.C. (2015). Time Series Analysis: Forecasting and Control (5th ed.). Wiley.
Cole, A., Gandhi, S., Kazam, M. (2023). Artificial Intelligence and Computer Vision. Real Projects in Python, Keras, and TensorFlow. St. Petersburg: Piter, p. 624.
Cole, G., & Garcia, J. (2023). PyTorch-based RNN Architectures for Monthly Load. Journal of Engineering and Computing, 11(3), 66–80.
Chatfield, C. (1978). The Holt-Winters Forecasting Procedure. Journal of the Royal Statistical Society, 27(3), 264–279. https://doi.org/10.2307/2347162
Chen, T., & Guestrin, C. (2016, August). Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining (pp. 785-794).
Çunka?, M., & Altun, A. A. (2010). Long term electricity demand forecasting in Turkey using artificial neural networks. Energy Sources, Part B: Economics, Planning, and Policy, 5(3), 279-289. https://doi.org/10.1080/15567240802533542
EDF (Electricité de France). (2022). LSTM Deployment in French Energy Markets. [Corporate White Paper].
Eremenko, Y. I., Poleshchenko, D. A., & Tsygankov, Y. A. (2020, November). Prediction of Quality Indicators of Iron Ore Processing Operations Using Deep Neural Networks. In 2020 2nd International Conference on Control Systems, Mathematical Modeling, Automation and Energy Efficiency (SUMMA) (pp. 425-429). IEEE. https://doi.org/10.1109/SUMMA50634.2020.9280676
Gafarov, M., Konstantin, S., Nikolaev, S., Pavel N., Berdnikov, A., Zakharova, V., Reznichenko, S. (2021). A Complex Neural Network Model for Predicting Personal Success Based on Activity in Social Networks. EURASIA Journal of Mathematics, Science and Technology Education, 17(10). https://doi.org/10.29333/ejmste/11175
Gridin, V.N., Doenin, V.N., Panishchev, V.S., Bysov, I.D. (2019). Neural network for forecasting the loads of the sorting node. World of Transport, 17(3), 6–15.
Gulzat, T., Lyazat, N., Siladi, V., Gulbakyt, S., Maxatbek, S. (2020). Research on predictive models is based on classification with optimization parameters. Neural Network World, 5, 295-308.
Hernandez, L., Baladron, C., Aguiar, J. M., Carro, B., Sanchez-Esguevillas, A. J., Lloret, J., & Massana, J. (2014). A survey on electric power demand forecasting: future trends in smart grids, microgrids and smart buildings. IEEE Communications Surveys & Tutorials, 16(3), 1460-1495. https://doi.org/10.1109/SURV.2014.032014.00094
Hochreiter, S. (1998). The Vanishing Gradient Problem During Learning Recurrent Neural Nets and Problem Solutions. International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, 6. 107–116. https://doi.org/10.1142/S0218488598000094
Hochreiter, S., & Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation, 9(8), 1735–1780.
Hong, T., Pinson, P., & Fan, S. (2014). Global energy forecasting competition 2012. International Journal of Forecasting, 30(2), 357-363. https://doi.org/10.1016/j.ijforecast.2013.07.001
Hyndman, R. J. (2021). Detecting time series outliers. https://robjhyndman.com/hyndsight/tsoutliers/
Huang, X., Zhuang, X., Tian, F., Niu, Z., Chen, Y., Zhou, Q., & Yuan, C. (2025). A Hybrid ARIMA-LSTM-XGBoost Model with Linear Regression Stacking for Transformer Oil Temperature Prediction. Energies, 18(6), 1432. https://doi.org/10.3390/en18061432
Ivanyuk, V. A., Abdikeev, N. M., & Tsvirkun, A. D. (2020, December). Forecasting the dynamics of financial time series based on neural networks. In Journal of Physics: Conference Series (Vol. 1703, No. 1, p. 012030). IOP Publishing.
Kalekar, P. S. (2004). Time series forecasting using holt-winters exponential smoothing. Kanwal Rekhi school of information Technology, 4329008(13), 1-13.
Kaytez, F. (2020). A hybrid approach based on autoregressive integrated moving average and least-square support vector machine for long-term forecasting of net electricity consumption. Energy, 197, 117200. https://doi.org/10.1016/j.energy.2020.117200
Khalid, R. Z., Ullah, A., Khan, A., Khan, A., & Inayat, M. H. (2023). Comparison of standalone and hybrid machine learning models for prediction of critical heat flux in vertical tubes. Energies, 16(7), 3182. https://doi.org/10.3390/en16073182
Khan, I., Hou, F., & Le, H. P. (2021). The impact of natural resources, energy consumption, and population growth on environmental quality: Fresh evidence from the United States of America. Science of the Total Environment, 754, 142222. https://doi.org/10.1016/j.scitotenv.2020.142222
Kialashaki, A. & Reisel, J. R. (2014). Development and validation of artificial neural network models of the energy demand in the industrial sector of the United States. Energy, 76. 749-760. https://doi.org/10.1016/j.energy.2014.08.072
Kingma, D.P., & Ba, J. (2015). Adam: A Method for Stochastic Optimization. ICLR Proceedings, 1–13.
Kotsialos, A., Papageorgiou, M., & Poulimenos, A. (2005). Long?term sales forecasting using holt–winters and neural network methods. Journal of Forecasting, 24(5), 353-368. https://doi.org/10.1002/for.943
Kong, W., Dong, Z.Y., Jia, Y., Hill, D.J., Xu, Y., & Zhang, Y. (2019). Short-Term Residential Load Forecasting based on LSTM Recurrent Neural Network. IEEE Transactions on Smart Grid, 10(1), 841–851. https://doi.org/10.1109/TSG.2017.2753802
Kovalev, S.P. (2021). Application of deep learning neural networks in the mathematical support of digital twins of power systems. Systems and Means of Informatics, 31(1), 133–144.
Lai, Y., & Dzombak, D. A. (2020). Use of the autoregressive integrated moving average (ARIMA) model to forecast near-term regional temperature and precipitation. Weather and forecasting, 35(3), 959-976. https://doi.org/10.1175/WAF-D-19-0158.1
Lekan, T., Cena, J., & Harry, A. (2025). Comparison of Neural Networks with Traditional Machine Learning Models (eg, XGBoost, Random Forest).
Mirowski, P., Chen, S., Ho, T. K., & Yu, C. N. (2014). Demand Forecasting in Smart Grids. Bell Labs Technical Journal, 18(4). 135-158. https://doi.org/10.1002/bltj.21650
National Statistics Bureau of the Agency for Strategic Planning and Reforms of the Republic of Kazakhstan. (2022). Energy and commodity market statistics [Online database]. https://stat.gov.kz/
Omelyanenko, B., & Hill, R. (2020). Outlier Detection for Energy Data. Energy Informatics, 15(2), 34–45.
Park, W.G. & Kim, S. (2012). The Performance of Time Series Models to Forecast Short-Term Electricity Demand. Communications for Statistical Applications and Methods , 19(6), 869-876. https://doi.org/10.5351/CKSS.2012.19.6.869
Pierre, A., Akim, S. A., Semenyo, A. K., & Babiga, B. (2023). Peak Electrical Energy Consumption Prediction by ARIMA, LSTM, GRU, ARIMA-LSTM, and ARIMA-GRU Approaches. Energies, 16(12), 4739. https://doi.org/10.3390/en16124739
Scholle, F. (2018). Deep Learning in Python. St. Petersburg: Piter, p. 400.
Senchilo, N., & Babanova, I. (2020, October). Improving the energy efficiency of electricity distribution in the mining industry using distributed generation by forecasting energy consumption using machine learning. In 2020 International Multi-Conference on Industrial Engineering and Modern Technologies (FarEastCon) (pp. 1-7). IEEE. https://doi.org/10.1109/FarEastCon50210.2020.9271335
Sharma, S., Tim, U. S., Wong, J., Gadia, S., & Sharma, S. (2014). A brief review on leading big data models. Data Science Journal, 13, 138-157. https://doi.org/10.2481/dsj.14-041
Sikhimbayeva, D., Zulkharnay, A., Zhakupov, A., Yessilov, A., & Kuttybay, M. (2021). Analysis of Factors Affecting to the Development of Sub-Production Industry of the Republic of Kazakhstan. Montenegrin Journal of Economics, 17(3), 41-57.
Teleron, J. I., Gonzales, S. L., & Fajardo, A. C. (2025). Electrical energy demand forecasting using time series in LSTM and CNN-LSTM models in deep learning applications. Journal of Information Systems Engineering and Management, 10, 718–724. https://doi.org/10.52783/jisem.v10i15s.2511
Trask, A. (2019). Groking Deep Learning. St. Petersburg: Piter, p. 352.
Wang, H. R., Wang, C., Lin, X., & Kang, J. (2014). An improved ARIMA model for precipitation simulations. Nonlinear Processes in Geophysics, 21(6), 1159-1168. https://doi.org/10.5194/npg-21-1159-2014
Wang, S., Li, C., & Lim, A. (2019). Why are the ARIMA and SARIMA not sufficient. arXiv preprint arXiv:1904.07632. https://doi.org/10.48550/arXiv.1904.07632 .
Xu, D., Zhang, Q., Ding, Y., & Zhang, D. (2022). Application of a hybrid ARIMA-LSTM model based on the SPEI for drought forecasting. Environmental Science and Pollution Research, 29(3), 4128-4144. https://doi.org/10.1007/s11356-021-15325-z
Zhao, B., Guo, Y., Mao, X., Zhai, D., Zhu, D., Huo, Y., Sun, Z., & Wang, J. (2022). Prediction Method for Surface Subsidence of Coal Seam Mining in Loess Donga Based on the Probability Integration Model. Energies, 15(6), 2282. https://doi.org/10.3390/en15062282
CITEDNESS IN SCOPUS
CITEDNESS IN WOS
