Analysis of Long Short-Term Memory and Support Vector Regression Methods in Forecasting Electric Energy Sales: Case Study
Abstract
This study aims to predict the sales of electrical energy of PT PLN (Persero) Greater Jakarta Distribution Unit by using machine learning methods, specifically Long Short-Term Memory (LSTM) and Support Vector Regression (SVR). The data used includes electrical energy sales trends from 2016 to 2023 as well as external data from the Central Statistics Agency (BPS), which includes economic and demographic factors that affect energy demand, such as economic growth, population, and seasonal factors. LSTM was chosen for its ability to handle long-term dependencies in time series data, while SVR was used as a comparison to other regression methods. The resulting model is expected to provide more accurate predictions and be useful for PT PLN in planning the distribution of electrical energy efficiently. This research also contributes to the development of the application of machine learning in forecasting, which is growing in various sectors, including the energy sector, to improve operational efficiency and data-based decision making.
References
Akbar, R., Santoso, R., & Warsito, B. (2023). Semarang City Temperature Level Prediction Using Long Short-Term Memory (Lstm) Method. Gaussian Journal,11(4), 572–579. https://doi.org/10.14710/j.gauss.11.4.572-579
Arfan, A., & Lussiana, E. T. P. (2020). Comparison of long short-term memory algorithm with SVR on stock price prediction in Indonesia.
Aryani, D. (2012). Indonesia's energy policy scenario until 2035. Dissertation, University of Indonesia, (Http://Lontar. Ui. Ac. Id/Opac/Themes/Green/DataIdentifier. Jsp.
Aulia, A., Aprianti, B., Supriyanto, Y., & Rozikin, C. (2022). Gold Price Prediction Using Support Vector Regression (Svr) and Linear Regression (LR) Algorithms. Scientific Journal of Wahana Pendidikan,8 (5), 84-88. https://doi.org/10.5281/zenodo.6408864
Huda, M., & Kom, M. (2019). Data Mining Algorithm: Analyzing Data with Computers. bisachemical.
Meriani, A. P., & Rahmatulloh, A. (2024). Comparison of Gated Recurrent Unit (Gru) and Long Short Term Memory (Lstm) Linear Refression Algorithm in Gold Price Prediction Using Time Series Model. Journal of Applied Informatics and Electrical Engineering,12 (1). http://dx.doi.org/10.23960/jitet.v12i1.3808
Muhammad, M., & Syaifuddin, H. (2022). Implementation of Pdca Model in Electric Energy Resource Management. Journal of Science and Engineering,5 (1), 49-54. https://doi.org/10.33387/josae.v5i1.4676
Novianti, F., Ulinnuha, N., Hafiyusholeh, M., & Arianto, A. (2022). Prediction of Fuel Usage in PLTGU using support vector regression (SVR) method. J. Techno. COM,21 (2), 249-255. https://core.ac.uk/reader/521875530
Nugraha, R. E. (2024). Implementation of vader-lstm method in testing the effect of investor sentiment on stock price prediction. Faculty of Science and Technology UIN Syarif HIdayatullah Jakarta. https://repository.uinjkt.ac.id/dspace/handle/123456789/76660
Nugraha, R. H., Yuwono, E., Prasetyohadi, L., & Patria, H. (2022). Analysis of Customer Electric Energy Consumption and Cost of Production of Electric Energy Supply with Machine Learning. J-SAKTI (Journal of Computer Science and Informatics),6 (1), 47-56. http://dx.doi.org/10.30645/j-sakti.v6i1.424
Perdana, D., & Muklason, A. (2023). Machine Learning for Forecasting DKI Jakarta Air Pollution Standard Index Quality with ARIMAX-LSTM Hybrid Method. ILKOMNIKA: Journal of Computer Science and Applied Informatics,5 (3), 209-222. https://doi.org/10.28926/ilkomnika.v5i3.588
PLN. (2024). Statistical Report 2023. PT Perusahaan Listrik Negara. https://web.pln.co.id/statics/uploads/2024/07/Laporan-Statistik-2023-Ind.pdf
Purnama, D. I., & Hendarsin, O. P. (2020). Forecasting the Number of Passengers Departing by Air Transportation in Central Sulawesi Using Support Vector Regression (SVR). Jambura Journal of Mathematics,2 (2), 49-59. https://doi.org/10.34312/jjom.v2i2.4458
Putra, R. F., Mukhlis, I. R., Datya, A. I., Pipin, S. J., Reba, F., Al-Husaini, M., Mandowen, S. A., Zain, N. N. L. E., & Judijanto, L. (2024). Machine Learning Algorithms: Fundamentals, Techniques, and Applications. PT. Sonpedia Publishing Indonesia.
Rahmah, A. A. L. (2024). Analysis of multivariate long short-term memory model for air quality forecast of Dki Jakarta based on 2010-2022 data. Faculty of Science and Technology UIN Syarif HIdayatullah Jakarta. https://repository.uinjkt.ac.id/dspace/handle/123456789/77128
Ramadhan, M. F., Lestari, D., & Khaira, U. (2024). Bitcoin Price Prediction Using Long Short Term Memory Method. Jambi University. https://repository.unja.ac.id/
Rohadi, D. (2024). Effect of ensemble feature selection on time series data prediction using gated recurrent unit (gru) and bidirectional long short-term memory (bi-lstm). Faculty of Science and Technology UIN Syarif HIdayatullah Jakarta. https://repository.uinjkt.ac.id/dspace/handle/123456789/80175
Senjawati, M. I., Susanti, L., Zadry, H. R., & Putri, G. R. (2020). The Influence of Psychological and Regulatory Factors on Electric Energy Consumption Behavior of the Household Sector Based on Age. INVENTORY: Industrial Vocational E-Journal on Agroindustry,1 (2), 49-56. http://dx.doi.org/10.52759/inventory.v1i2.23
Sinurat, A. B. N., Arifin, W. A., & Larasati, W. A. (2024). Sea Level Prediction Using Gated Recurrent Unit and Bidirectional Long Short-Term Memory Methods. INOVTEK Polbeng-Series Informatics, 9(2), 753–764. https://doi.org/10.35314/r9bk6j70
Yanti, F., Sari, B. N., & Defiyanti, S. (2024). Implementation of Lstm Algorithm on Forecasting Drug Stock. JATI (Journal of Informatics Engineering Students),8 (4), 6082-6089. https://doi.org/10.36040/jati.v8i4.10068
Copyright (c) 2025 Journal La Multiapp
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
