International Journal of Emerging Research in Engineering, Science, and Management
Vol. 5, Issue 1, pp. 86-92, Jan-Mar 2026.
https://doi.org/10.58482/ijeresm.v5i1.7

Received: 20 Jan 2026 | Revised: 18 Mar 2026 | Accepted: 23 Mar 2026 | Published: 28 Mar 2026

This work is licensed under a Creative Commons Attribution 4.0 International License.

Long-Term Electricity Demand Forecasting for Thailand’s Small Business Sector: An LSTM-Based Approach

Full Text PDF

Puttiphong Jaroonsiriphan

Kayun Chantarasathaporn

Khongdet Phasinam

Faculty of Engineering and Technology, Shinawatra University, Pathum Thani, Thailand.

Abstract: Accurate electricity demand forecasting is essential for Thailand’s energy system planning, particularly for the small business sector, whose consumption exhibits high variability (coefficient of variation: 26.34%). This study develops a Long Short-Term Memory (LSTM) model to forecast monthly electricity consumption of Thailand’s small business sector over a 12-month horizon from September 2025 to August 2026. The analysis is based on 284 months of historical consumption data (January 2002–August 2025) obtained from official national statistics. The forecasting framework employs Min–Max normalization and a supervised learning formulation with a 12-month lookback window. The dataset is chronologically divided into training (80%) and testing (20%) subsets, and model performance is evaluated using Root Mean Squared Error (RMSE) and Mean Absolute Percentage Error (MAPE). The optimized LSTM model achieves strong forecasting accuracy, with a training RMSE of 93.93 and MAPE of 5.45%, and a testing RMSE of 143.68 and MAPE of 6.25%. These results meet the criterion for highly accurate forecasting (MAPE < 10%), demonstrating the model’s ability to capture long-term trends and seasonal patterns while generalizing well to unseen data. The findings highlight the suitability of LSTM-based models for long-term electricity demand forecasting in high-volatility small-business sectors and underscore their practical relevance for energy planning and policy development in Thailand.

Keywords: Electricity Consumption, Demand Forecasting, Long Short-Term Memory, Mean Absolute Percentage Error, Small Business Sector.

References: 

  1. Energy Policy and Planning Office, “Thailand Power Development Plan 2018–2037,” Ministry of Energy [Online]. https://www.eppo.go.th/images/Infromation_service/public_relations/PDP2018/PDP2018Rev1.pdf.
    (Accessed: Nov. 25, 2025).
  2. M. Choudhary, S. Jain, and G. Arya, “Classical Models vs Deep Learning: Time Series Analysis,” in Communications in Computer and Information Science, 2022, pp. 276–286. doi: 10.1007/978-3-031-23724-9_26.
  3. A. R. Hans, A. K. Sharma, and V. D. Wangkheirakpam, “Electricity demand and price forecasting using LSTM for smart grid operations,” in Lecture Notes in Computer Science, 2025, pp. 236–250. doi: 10.1007/978-3-031-86193-2_16.
  4. P. Cihan, “Comparative performance analysis of deep learning, classical, and hybrid time series models in ecological footprint forecasting,” Applied Sciences, vol. 14, no. 4, p. 1479, Feb. 2024, doi: 10.3390/app14041479.
  5. Y. Ning, H. Kazemi, and P. Tahmasebi, “A comparative machine learning study for time series oil production forecasting: ARIMA, LSTM, and Prophet,” Computers & Geosciences, vol. 164, p. 105126, May 2022, doi: 10.1016/j.cageo.2022.105126.
  6. P. P. Phyo, C. Jeenanunta, and K. Hashimoto, “Electricity load forecasting in Thailand using deep learning models,” International Journal of Electrical and Electronic Engineering & Telecommunications, pp. 221–225, Jan. 2019, doi: 10.18178/ijeetc.8.4.221-225.
  7. R. K. Shiwakoti, C. Charoenlarpnopparut, and K. Chapagain, “A Deep Learning Approach for Short-Term Electricity Demand Forecasting: Analysis of Thailand data,” Applied Sciences, vol. 14, no. 10, p. 3971, May 2024, doi: 10.3390/app14103971.
  8. C. Siridhipakul and P. Vateekul, “Multi-step Power Consumption Forecasting in Thailand Using Dual-Stage Attentional LSTM,” 2019 11th International Conference on Information Technology and Electrical Engineering (ICITEE), Pattaya, Thailand, 2019, pp. 1-6, doi: 10.1109/ICITEED.2019.8929966.
  9. Aditya Pai H, Kritika Kumari Mishra, Mahesh T R, J V Muruga Lal Jeyan, Anu Sayal, “Enhanced household energy consumption forecasting using multivariate long short-term memory (LSTM) networks with weather data integration,” Results in Engineering, vol. 27, p. 106512, Jul. 2025, doi: 1016/j.rineng.2025.106512.
  10. National Statistical Office, “Government Data Account System, National Electricity Consumption (classified by user type),” Ministry of Digital Economy and Society [Online]. https://gdcatalog.go.th/dataset/gdpublish-dataset-11-341/resource/ff7f960e-0688-45c7-b668-5cf9449e534e. (Accessed: Nov. 29, 2025).
  11. A. De Myttenaere, B. Golden, B. L. Grand, and F. Rossi, “Mean Absolute Percentage Error for regression models,” Neurocomputing, vol. 192, pp. 38–48, Mar. 2016, doi: 10.1016/j.neucom.2015.12.114.
  12. C. D. Lewis, Industrial and Business Forecasting Methods: A Practical Guide to Exponential Smoothing and Curve Fitting, London: Butterworth Scientific, 1982.
  13. Z. Ullah, S. Maaz Shahid, J. Park, B. Min and S. Kwon, “LSTM-Based Online Learning for Real-Time Solar Power Forecasting,” in IEEE Access, vol. 13, pp. 160456-160465, 2025, doi: 10.1109/ACCESS.2025.3606910.
  14. M. Di Mauro, G. Galatro, F. Postiglione, W. Song, and A. Liotta, “Multivariate Time Series Characterization and Forecasting of VoIP Traffic in Real Mobile Networks,” in IEEE Transactions on Network and Service Management, vol. 21, no. 1, pp. 851-865, Feb. 2024, doi: 10.1109/TNSM.2023.3295748.
  15. B. Palaniyappan and S. K. Ramu, “Optimized LSTM-based electric power consumption forecasting for dynamic electricity pricing in demand response scheme of smart grid,” Results in Engineering, vol. 25, p. 104356, Feb. 2025, doi: 10.1016/j.rineng.2025.104356.
  16. X. Liu and W. Wang, “Deep Time Series Forecasting Models: A Comprehensive Survey,” Mathematics, vol. 12, no. 10, p. 1504, May 2024, doi: 10.3390/math12101504.
  17. A. Soni and A. Yadav, “Seasonal Autoregressive Integrated Moving Average Model for Forecasting Electrical Load of Chhattisgarh State,” 2025 Fourth International Conference on Power, Control and Computing Technologies (ICPC2T), Raipur, India, 2025, pp. 46-51, doi: 10.1109/ICPC2T63847.2025.10958744.
  18. D. G. Da Silva and A. A. De Moura Meneses, “Comparing Long Short-Term Memory (LSTM) and bidirectional LSTM deep neural networks for power consumption prediction,” Energy Reports, vol. 10, pp. 3315–3334, Oct. 2023, doi: 10.1016/j.egyr.2023.09.175.
  19. R. E. Alden, H. Gong, C. Ababei and D. M. Ionel, “LSTM Forecasts for Smart Home Electricity Usage,” 2020 9th International Conference on Renewable Energy Research and Application (ICRERA), Glasgow, UK, 2020, pp. 434-438, doi: 10.1109/ICRERA49962.2020.9242804.
Download PDF

This article is part of Volume 5, Issue 1 (Jan–Mar 2026)

© 2026 The Author(s). Published by IJERESM. This work is licensed under the Creative Commons Attribution 4.0 International License.

Archiving: All articles are permanently archived in Zenodo IJERESM Community.