Electricity Consumption Forecasting Using the LSTM Method in Iran's Industrial Sector

Document Type : IIIEC 2025

Authors

1 Master's Student, Faculty of Industrial Engineering, Iran University of Science and Technology, Tehran, Iran

2 Master's Student, Faculty of Electrical Engineering, Malek Ashtar University of Technology, Tehran, Iran

Abstract

Objective: The growing energy crisis, particularly in the electricity sector, caused by rising demand and depletion of fossil fuel resources, necessitates accurate electricity consumption forecasting. This study aims to develop a reliable prediction model using Long Short-Term Memory (LSTM) networks to capture long-term temporal dependencies and nonlinear patterns in electricity usage.
Methods: Key factors influencing electricity consumption were identified, and historical data were normalized and split into training and testing sets. A two-layer LSTM network with ReLU activation was employed to model electricity consumption patterns. The model’s predictive performance was evaluated using Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), Coefficient of Determination (R²), and Mean Absolute Percentage Error (MAPE).
Results: The LSTM model effectively captured complex temporal patterns in electricity consumption, producing predictions that closely matched actual values. The evaluation metrics demonstrated the model’s high accuracy and robustness compared to classical forecasting approaches.
Conclusion: The proposed LSTM-based approach provides a practical tool for accurate electricity consumption forecasting. These results can support energy planning, optimize electricity management, and reduce the economic and social costs associated with overconsumption, contributing to more sustainable energy provision.

Keywords

References

Al-Aziz, A. & Hawdan, D. (1999). Estimating the Demand for Energy in Jordan: A stock Watson Dynamic OLS (DOLS) Approach. Survey Energy Economics Center, Department of Economics.
Ang B.W. (1988). Electricity-output ration and sectoral electricity use. The case of East and South East Asian developing countries. Energy Policy, 16, NO. 2, PP. 115-121. https://doi.org/10.1016/0301-4215(88)90119-X.
Arjmand, A., Samizadeh, R., & Dehghani Saryazdi, M. (2019). Improved forecasting of short term electricity demand by using of integrated data preparation and input selection methods. Journal of Energy Management and Technology, 3(1), 48-57, https://doi.org/ 10.22109/jemt.2018.126045.1077.
Armano, G., & Pegoraro, PA. (2022). Assessing feature importance for short-term prediction of electricity demand in medium-voltage loads. Energies, 15(2), 549, https://doi.org/10.3390/en15020549.
Asgari, A. (2001). "Estimating residential electricity demand and its price and income elasticities. Budget and Planning Journal, Issues 63 and 62, pp. 119-103.https://jpbud.ir/article-1-770-fa.html
Changi Ashtiani, Ali, and Jallouli, M. (2012). The estimation of electricity demand function and prediction of its consumption to 2025 in Iran. Research on Economic Growth and Development, Second Year, Issue 7.
Collino, E., & Ronzio, D. (2021). Exploitation of a new short-term multimodel photovoltaic power forecasting method in the very short-term horizon to derive a multi-time scale forecasting system. Energies, 14(3), 789., https://doi.org/10.3390/en14030789.
Ding, S., Hipel, KW., & Dang, YG. (2018). Forecasting China's electricity consumption using a new grey prediction model. Energy, 149, 314-328, https://doi.org/10.1016/j.energy.2018.01.169.
Edomah, N. (2021). The governance of energy transition: lessons from the Nigerian electricity sector. Energy, sustainability and society, 11, 1-12. https://doi.org/10.1186/s13705-021-00317-1
Electric power distribution. (n.d.). Wikipedia. Retrieved July 23, 2025. from https://en.wikipedia.org/wiki/Electric_power_distribution.
Eltony, MN., & Mohammad, YH. (1993). The structure of demand for electricity in the gulf cooperation council countries. the Journal of Energy and Development, 18(2), 213-221.‏
Fakhraei, H. (1992). Final report on forecasting energy carrier demand in various consumption sectors.
Ghulam H., Zeng F., Li W., Xiao Y. )2019(. Deep learning-based sentiment analysis for roman urdu text. Procedia Computer Science 147:131–135, https://doi.org/10.1016/j.procs.2019.01.202.
Jalebi A., Khodam M., & Mohammad H. (2023) Forecasting the Price of Electricity in the Cash and Advance Markets and Designing the Optimal Model for Selling Electricity in the Mentioned Markets with the Copula Function. Computational Economics Quarterly, 2(2), 95-116, https://civilica.com/doc/1768539.
Kazemi, A. (1996). Analysis of electricity demand in the residential and industrial sectors. Master's thesis, University of Tehran.
Khiabani, N. (2016). "A computable dynamic general equilibrium model for evaluating the impacts of energy policies: Evidence from Iran." Iranian Economic Research, 21(69): 41-1. https://doi.org/10.22054/ijer.2017.7502.
Kim, J., Kim, J., Thu, HLT., & Kim, H. (2016, February). Long short term memory recurrent neural network classifier for intrusion detection. In 2016 international conference on platform technology and service (PlatCon) (pp. 1-5). IEEE. https://doi.org/10.1109/PlatCon.2016.7456805.
Latifalipur, M, Fallahi, MA, & Nazemi Maazabadi, S. (2015). Estimating Residential and Industrial Electricity Demand Functions of Iran, using Structural Time Series Model (STSM). Journal of Applied Economic Studies of Iran, 13, pp. 187-208.
Lee, J., Zhang, Z., & Paal, SG (2024). Data-Driven Models for Predicting Winter Storms-Induced Power Outages With Nonparametric Machine Learning Models. Available at SSRN 4704966. https://doi.org/10.2139/ssrn.4704966.
Rabbi, F., Tareq, SU., Islam, M M., Chowdhury, MA., & Kashem, MA. (2020, December). A multivariate time series approach for forecasting of electricity demand in bangladesh using arimax model. In 2020 2nd International Conference on Sustainable Technologies for Industry 4.0 (STI) (pp. 1-5). IEEE. ‏ https://doi.org/10.1109/STI50764.2020.9350326.
Raeisi-Gahruei, J., & Beheshti, Z. (2022). The electricity consumption prediction using hybrid red kite optimization algorithm with multi-layer perceptron neural network. Journal of Intelligent Procedures in Electrical Technology, 15(60), 19-40.‏
Rizvi, M. (2024).  Powering the future: Unleashing the potential of machine learning for intelligent energy forecasting and load prediction in smart grids. International Research Journal of Modernization in Engineering Technology and Science. https://doi.org/10.56726/IRJMETS48655.
Sadegi, SK., & Ebrahimi, S. (2013). Impact of Coal Consumption on Carbon Dioxide Emissions in Iran. Iranian Energy Economics, 2, no. 7 (2013): 43-73.
Samadi, S., Shahidi, A., & Mohammadi, F. (2009). Electricity demand analysis in Iran by using cointegration and ARIMA modeling (1363–1388). Knowledge and Development, 15(25), 113–136.
Saranj, A., & Zolfaghari, M. (2022). The electricity consumption forecast: Adopting a hybrid approach by deep learning and ARIMAX-GARCH models. Energy Reports, 8, 7657-7679. https://doi.org/10.1016/j.egyr.2022.06.007.
Selvaraj, M., Kulkarni, SM. & Rameshbabu, R. (2014). Performance analysis of a overhead power transmission line tower using polymer composite material. Procedia Materials Science, 5, 1340-1348. https://doi.org/ 10.1016/j.mspro.2014.07.451.
Shirsath, P. B., & Singh, A. K. (2010). A comparative study of daily pan evaporation estimation using ANN, regression and climate based models. Water resources management, 24(8), 1571-1581.https://doi.org/10.1007/s11269-009-9514-2.
 Tavanir Specialized Holding Company. (2023). Fifty-three years of the electricity industry in Iran in the mirror of statistics. Research and Human Resources Department. Information Technology, Communications, and Statistics Office - Statistics Group.
Tran NT., Luong VT., Nguyen NLT., Nghiem MQ. )2016(. Effective attention-based neural architectures for sentence compression with bidirectional long short-term memory. In: Proceedings of the 7th symposium on information and communication technology. 123–130 ArXiv arXiv:1508.04025. https://doi.org/10.48550/arXiv.1508.04025.
 
Bawack, R., Roderick, S., Badhrus, A., Dennehy, D., & Corbett, J. (2025). Indigenous knowledge and information technology for sustainable development. Information Technology for Development, 31(2), 233-250. https://doi.org/10.1080/02681102.2025.2472495
De Andrade, P. R., Patuzzo, G. V., & Cardoso, F. A. R. (2025). Industrial management: implementation of the TPM tool in a coffee industry. Brazilian Journal of Production Engineering, 11(1), 166-191. https://dx.doi.org/10.47456/bjpe.v11i1.46368
Dong, A. (2025). Information security in cloud computing. International Journal of Management Science Research, 8(6), 36-39.
Guo, Y., Song, Y., & Zhang, M. (2025). Value realization of intelligent emergency management: research framework from technology enabling to value creation. Data Science and Management, 8(1), 11-22. https://doi.org/10.1016/j.dsm.2024.06.001
Jin, W., & McElheran, K. (2025). Economies before scale: IT strategy and performance dynamics of young US businesses. Management Science, 71(9), 7449-7473. https://doi.org/10.1287/mnsc.2019.03116
Kantardzhieva, E. (2024, April). Growth opportunities in industrial management and engineering. In AIP Conference Proceedings (Vol. 3078, No. 1). AIP Publishing. https://doi.org/10.1063/5.0208271
Kim, J. H., & Kim, M. J. (2025). Analysis of urban management information technology systems: Ubiquitous City, Smart City, Metaverse, and Digital Twin. International Journal of Urban Sciences, 1-21. https://doi.org/10.1080/12265934.2025.2452501
Li, Z., Lei, H., Ma, Z., & Zhang, F. (2024). Code similarity prediction model for industrial management features based on graph neural networks. Entropy, 26(6), 505. https://doi.org/10.3390/e26060505
Metelenko, N., Voronkova, V., Nikitenko, V., Tubolets, I., Zelenin, Y., Marchenko, O., ... & Salnikova, M. (2025). Integration of environmental technologies into industrial management as a tool for ensuring sustainable development. Pakistan Journal of Life and Social Sciences, 23(1), 230–237. https://doi.org/10.57239/PJLSS-2025-23.1.0020
Odularu, O. I. (2025). A review on the germaneness of libraries in sustaining information technology services: rethinking towards futuristic strategies implementation. Library Management, 46(1/2), 109-131. https://doi.org/10.1108/LM-11-2023-0118
Pei, L. (2025). Application and development of computer science and technology in the era of artificial intelligence. Journal of Theory and Practice of Management Science, 5(3), 18-22. https://doi.org/10.53469/jtpes.2025.05(03).04  
Rüdele, K., & Wolf, M. (2024). Industrial management meets environmental reporting–how a learning factory for engineering education is used to teach accounting of greenhouse gas emissions. International Journal of Sustainability in Higher Education, 25(9), 397-418. https://doi.org/10.1108/IJSHE-04-2024-0301
Silviu, G. A. (2024). The use of artificial intelligence in industrial management. In International Conference on Machine and Industrial Design in Mechanical Engineering (pp. 819-828). Cham: Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-80512-7_80   
Management Science and Information Technology
Volume 2, Issue 2
June 2025
Pages 174-188

Files

Share

How to cite

Statistics