Application of Support Vector Machine Algorithm for Energy Consumption Prediction
DOI:
https://doi.org/10.30871/jaic.v10i2.11713Keywords:
Energy Consumption, Energy Efficiency, SMOTE, SVM KernelAbstract
Global energy consumption continues to increase due to population growth, urbanization, and rapid technological advancement, creating significant challenges for effective energy management. This study proposes an energy consumption classification model using Support Vector Machine (SVM) to identify consumption levels based on environmental, temporal, and operational features. Data preprocessing includes feature normalization using StandardScaler and class balancing with SMOTE to improve model stability. Experimental results show that the SVM with a linear kernel consistently achieves the best performance on the test data, outperforming more complex kernel configurations. The proposed model attains an average accuracy of 88.15%, precision of 91.08%, recall of 88.16%, and an F1-score of 87.54%. Feature analysis indicates that temperature and HVAC usage are the most influential factors in determining energy consumption levels. These findings demonstrate that selecting a kernel aligned with data characteristics is more critical than increasing model complexity. The proposed SVM-based approach has strong potential as a decision-support tool for building energy management, enabling better identification of consumption conditions and supporting energy efficiency strategies.
Downloads
References
[1] Iea, Irena, UNSD, World Bank, and WHO, Tracking SDG 7: The Energy Progress Report, Washington, DC, USA: World Bank, 2023.
[2] J. S. Puthumana, L. M. Ngaage, M. R. Borrelli, E. M. Rada, J. Caffrey, and Y. Rasko, “Risk factors for cooking-related burn injuries in children: WHO Global Burn Registry,” Bull. World Health Organ., vol. 99, no. 6, pp. 439–445, 2021, doi: 10.2471/BLT.20.279786L.
[3] L. Olatomiwa, H. O. Idakwo, W. S. Olusola, and C. Ezeh, “Global energy consumption trends,” Majlesi J. Electr. Eng., vol. 19, no. 1, art. no. 192509, 2025, doi: 10.57647/j.mjee.2025.1901.09.
[4] H. N. Abraham, “Recent advancement in demand side energy management system for optimal energy utilization,” Energy Rep., vol. 11, pp. 5422–5435, 2024, doi: 10.1016/j.egyr.2024.05.028.24.05.028
[5] R. Qu, R. Kou, and T. Zhang, “The impact of weather variability on renewable energy consumption: Insights from explainable machine learning models,” Sustainability, vol. 17, no. 1, art. no. 87, 2025, doi: 10.3390/su17010087.
[6] M. Mahmood et al., “Impacts of digitalization on smart grids, renewable energy, and demand response: An updated review of current applications,” Energy Convers. Manag.: X, vol. 24, art. no. 100790, 2024, doi: 10.1016/j.ecmx.2024.100790.
[7] T. Shojaei and A. Mokhtar, “Forecasting energy consumption with a novel ensemble deep learning framework,” J. Build. Eng., vol. 96, no. 1, art. no. 110452, 2024, doi: 10.1016/j.jobe.2024.110452.
[8] I. Antonopoulos et al., “Artificial intelligence and machine learning approaches to energy demand-side response: A systematic review,” Renew. Sustain. Energy Rev., vol. 130, art. no. 109899, 2020, doi: 10.1016/j.rser.2020.109899.
[9] M. Shao et al., “Prediction of energy consumption in hotel buildings via support vector machines,” Sustain. Cities Soc., vol. 57, art. no. 102128, 2020, doi: 10.1016/j.scs.2020.102128.
[10] Y. Ali et al., “Advances, challenges, and future research needs in machine learning-based crash prediction models: A systematic review,” Accid. Anal. Prev., vol. 194, art. no. 107378, 2024, doi: 10.1016/j.aap.2023.107378.
[11] W. Sholihah et al., “Revolutionizing healthcare: Comprehensive evaluation and optimization of SVM kernels for precise general health diagnosis,” Sci. J. Informatics, vol. 10, no. 4, pp. 1–12, Nov. 2023, doi: 10.15294/sji.v10i4.46430
[12] L. Xu, L. Hou, Z. Zhu, et al., “Mid-term prediction of electrical energy consumption for crude oil pipelines using a hybrid algorithm of support vector machine and genetic algorithm,” Energy, vol. 222, art. no. 119955, 2021, doi: 10.1016/j.energy.2021.119955.
[13] N. W. Azizah et al., “Analyzing the relationship between meteorological parameters and electric energy consumption using support vector machine and cooling degree days algorithm,” J. Inf. Syst. Informatics, vol. 6, no. 2, pp. 729–750, 2024, doi: 10.51519/journalisi.v6i2.719.
[14] A. F. A. H. Alnuaimi and T. H. K. Albaldawi, “Concepts of statistical learning and classification in machine learning: An overview,” BIO Web Conf., vol. 97, art. no. 00129, 2024, doi: 10.1051/bioconf/20249700129.
[15] A. Tsiamis, I. Ziemann, N. Matni, and G. J. Pappas, “Statistical learning theory for control: A finite-sample perspective,” IEEE Control Syst. Mag., vol. 43, no. 6, pp. 67–97, Dec. 2023, doi: 10.1109/MCS.2023.3310345.
[16] K.-L. Du, B. Jiang, J. Lu, J. Hua, and M. N. S. Swamy, “Exploring kernel machines and support vector machines: Principles, techniques, and future directions,” Mathematics, vol. 12, art. no. 3935, 2024, doi: 10.3390/math12243935.
[17] R. H. Muhammadi et al., “Combination of support vector machine and lexicon-based algorithm in Twitter sentiment analysis,” Khazanah Informatika, vol. 8, no. 1, pp. 59–71, Apr. 2022.
[18] D. Valero-Carreras et al., “Comparing two SVM models through different metrics based on the confusion matrix,” Comput. Oper. Res., vol. 152, art. no. 106131, 2023, doi: 10.1016/j.cor.2022.106131.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Ivani Valentine, Joko Triloka, Ridho Sholehurrohman
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) ) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
