ENERGY DEMAND FORECASTING IN HUILA: A COMPARISON OF PREDICTIVE MODELS
Article Sidebar
Downloads
Section
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Los artículos que se aprueban para publicación en la revista Semestre Económico deben acogerse a las siguientes condiciones:
a) Los autores ceden a la revista Semestre Económico los derechos patrimoniales (copy right), para lo cual debe entregar el formato de originalidad y derechos de autor debidamente diligenciado y con firmas originales.
b) Los artículos que se publican en la revista Semestre Económico se pueden usar, reproducir, transmitir y exponer con fines académicos siempre y cuando se cumplan las siguientes condiciones:
- Se cite la referencia bibliográfica de Semestre Económico (autores, revista, editorial, edición,…)
- No se use con fines comerciales
- El uso con fines diferentes o la publicación en otro sitio electrónico requiere de la autorización por escrito del editor de la revista.
Main Article Content
Abstract
This study analyzes the energy demand of the department of Huila between 2023 and 2025 using statistical and machine learning models, with the aim of evaluating their predictive capacity and providing evidence for understanding the recent dynamics of regional electricity consumption. The database used includes daily and hourly electricity consumption series, which allowed the examination of seasonal patterns, growth trends, and demand variations associated with different temporal behaviors. The analysis implemented ARIMA, SARIMAX, linear regression, Support Vector Regression (SVR), Gaussian Process Regression (GPR), and Random Forest models, and their performance was evaluated using error metrics such as MAE, RMSE, MAPE, MASE, and R². The results show that traditional statistical models, particularly ARIMA and SARIMAX, exhibited more limited performance in dealing with the complexity and nonlinearity of the analyzed series. In contrast, machine learning models achieved better levels of fit, with Random Forest standing out, obtaining an RMSE of 14.137 units and an R² of 0.67, positioning it as the best-performing model among those evaluated for hourly forecasting. In this regard, the findings highlight the potential of machine learning approaches to strengthen regional-scale energy demand forecasting exercises.
Article Details
How to Cite
References
Ahmed, A., Jakir, T., Hossain, N., Fahim, A., Hossain, A., Hoque, A., & Hasan, S. (2025). Predicting energy consumption in hospitals using machine learning: A data-driven approach to energy efficiency in the USA. Journal of Computer Science and Technology Studies. 7,1. DOI: https://doi.org/10.32996/jcsts.2025.7.1.15
Alizamir, M., Wang, M., Adnan-Ikram, R., Kim, S., Ahmed, K., & Heddam, S. (2024). Developing an efficient explainable artificial intelligence approach for accurate reverse osmosis desalination plant performance prediction: Application of SHAP analysis. Engineering Applications of Computational Fluid Mechanics, 18(1), 2422060. https://doi.org/10.1080/19942060.2024.2422060
Al Kez, D., Foley, A., Abdul, Z. K., & Furszyfer Del Rio, D. (2024). Energy poverty prediction in the United Kingdom: A machine learning approach. Energy Policy, 184, 113909. https://doi.org/10.1016/j.enpol.2023.113909
Alshater, M. M., Kampouris, I., Marashdeh, H., Atayah, O. F., & Banna, H. (2025). Early warning system to predict energy prices: The role of artificial intelligence and machine learning. Annals of Operations Research, 345(2), 1297–1333. https://doi.org/10.1007/s10479-022-04908-9
Ansong, M., Nyang'onda, T. N., Musembi, R. J., & Richards, B. S. (2024). Very short-term solar irradiance forecasting for photovoltaic power integration with the grid: Potentials and challenges for Africa. In 2024 IEEE PES/IAS PowerAfrica (pp. 1–5). IEEE. https://doi.org/10.1109/PowerAfrica61624.2024.10759405
Bulungu, D. M., & Kumar, A. (2024). Forecasting the economic growth of Sverdlovsk region: A comparative analysis of machine learning, linear regression and autoregressive models. Journal of Applied Economic Research, 23(3), 674–695. https://doi.org/10.15826/vestnik.2024.23.3.027
Comisión de Regulación de Energía y Gas. (2024). Informe al Congreso: Segundo semestre de 2024. CREG.
Cui, X., Lee, M., Koo, C., & Hong, T. (2024). Energy consumption prediction and household feature analysis for different residential building types using machine learning and SHAP: Toward energy-efficient buildings. Energy and Buildings, 309, 113997. https://doi.org/10.1016/j.enbuild.2024.113997
Hasan, M. S., Tarequzzaman, M., Moznuzzaman, M., & Ahad Juel, M. A. (2025). Prediction of energy consumption in four sectors using support vector regression optimized with genetic algorithm. Heliyon, 11(2), e41765. https://doi.org/10.1016/j.heliyon.2025.e41765
Hicks, J. R., & Allen, R. G. D. (1934). A reconsideration of the theory of value. Part I. Economica, 1(1), 52–76. https://doi.org/10.2307/2548574
Hyndman, R. y Athanasopoulos, G. (2018). Pronóstico: principios y práctica. OTexts.
Hotelling, H. (1931). The economics of exhaustible resources. Journal of Political Economy, 39(2), 137–175. https://doi.org/10.1086/254195
Ibarra, N., Duque, J., Velandia, Y. y Salas, L. (2024). Energías renovables en la caficultura colombiana: Estrategias para la sostenibilidad y la eficiencia energética. Universidad EAN.
Kaloop, M., Ahmad, F., Samui, P., Elbeltagi, E., Hu, J.-W., & Wefki, H. (2025). Predicting energy consumption of residential buildings using metaheuristic-optimized artificial neural network technique in early design stage. Building and Environment. 274, 112749 y DOI: https://doi.org/10.1016/j.buildenv.2025.112749
Kulisz, M., Kujawska, J., Cioch, M., Cel, W., & Pizoń, J. (2024). Comparative analysis of machine learning methods for predicting energy recovery from waste. Applied Sciences, 14(7), 2997. https://doi.org/10.3390/app14072997
Li, Y., Zhang, W., Zhao, B., Sharp, B., & Nie, J. (2026). Does energy poverty affect subjective well-being? Evidence from a cross-country analysis. Applied Economics, 58(1), 141–156. https://doi.org/10.1080/00036846.2024.2449208
López, F., Torre, J., Ríos, L., & Ruvulvaba, L. (2024). Enhancing electricity demand prediction in Mexico: A comparative analysis of forecasting models using conformal prediction. Revista de Gestão Social e Ambiental, 18(12), e010644. https://doi.org/10.24857/rgsa.v18n12-235
Marshall, A. (1890). Principios de economía. Macmillan and Company.
Mohammed, D., Ebrahim Ali, D. M. T., Motuzienė, V., & Džiugaitė-Tumėnienė, R. (2024). AI-driven innovations in building energy management systems: A review of potential applications and energy savings. Energies, 17(17), 4277. https://doi.org/10.3390/en17174277
Molnar, C. (2020). Interpretable machine learning. Lulu.com.
Olivares, F. (2025). Análisis de técnicas en ciencia de datos aplicadas a la matriz energética renovable en Colombia. Repositorio UNAD. https://repository.unad.edu.co/handle/10596/70349
Osorio, W. (2025). Uso del machine learning en la predicción de la demanda de energía en Colombia. Repositorio UNAD. https://repository.unad.edu.co/handle/10596/70599
Pérez-Rosero, D. A., Manrique-Cabezas, D. A., Triana-Martínez, J. C., Álvarez-Meza, A. M., & Castellanos-Domínguez, G. (2025). An explainable framework integrating local biplots and Gaussian processes for unemployment rate prediction in Colombia. Computation, 13(5), 116. https://doi.org/10.3390/computation13050116
Pineda, C., Arrieta, I. y Quitián, M. (2020). Generando oportunidades en la calidad de vida de los habitantes de Villavieja en el departamento del Huila a través de energías renovables. Repositorio UNAD. https://repository.unad.edu.co/handle/10596/35251
Rao, A., Kumar, S., & Karim, S. (2024). Accelerating renewables: Unveiling the role of green energy markets. Applied Energy, 366, 123286. https://doi.org/10.1016/j.apenergy.2024.123286
Reyes, R., Turriago, A., Cárdenas, M. y Buitrago, J. (2023). Análisis de políticas públicas para la adopción de energías renovables no convencionales en Colombia. Cuadernos Latinoamericanos de Administración. 19, 36. DOI: https://doi.org/10.18270/cuaderlam.v19i36.4052
Rocha, A. (2024). Modelo de pronóstico de demanda de energía eléctrica a corto plazo basado en redes neuronales recurrentes [Tesis de grado, Escuela Politécnica Nacional]. https://bibdigital.epn.edu.ec/handle/15000/25750
Rojas, J. (2024). Pronóstico de demanda de energía eléctrica en un mercado de comercialización en Colombia [Tesis de grado, Universidad de Antioquia]. Disponible en: https://hdl.handle.net/10495/40395
Samuelson, P. A. y Nordhaus, W. D. (2010). Macroeconomía con aplicaciones en Latinoamérica. McGraw-Hill.
Torres, C., Rojas, A., Higuera, D., Hernández, J. y Calle, J. (2017). Planeamiento estratégico del sector de las fuentes no convencionales de energía renovable en Colombia. [Tesis de grado, Pontificia Universidad Católica del Perú]. http://hdl.handle.net/20.500.12404/8788
Ubal, C., Di-Giorgi, G., Contreras-Reyes, J. E., & Salas, R. (2023). Predicting the long-term dependencies in time series using recurrent artificial neural networks. Machine Learning and Knowledge Extraction, 5(4), 1340–1358. https://doi.org/10.3390/make5040068
Wang, W. (2025). Theories for analyzing issues of household energy consumption. En Household energy consumption in China. Consumo energético doméstico en China. Cambio climático y transición energética. Springer, Singapur. https://doi.org/10.1007/978-981-96-7941-6_2
XM SA ESP. (s. f.). GitHub. GitHub. Recuperado el 1 de abril de 2026, de https://github.com/XM-SA-ESP
Zhang, Y., Dong, X., Wang, X., Zhang, P., Liu, M., Zhang, Y., & Xiao, R. (2023). The relationship between the low-carbon industrial model and human well-being: A case study of the electric power industry. Energies, 16(3), 1357. https://doi.org/10.3390/en16031357
Zhu, H., Hao, H., & Lu, C. (2024). Enhanced support vector machine-based moving regression strategy for response prediction and reliability estimation of complex structure. Aerospace Science and Technology, 155, 109634. https://doi.org/10.1016/j.ast.2024.109634
Zucaro, A., & Agostinho, F. (2025). Urban sustainability: Challenges and opportunities for resilient and resource-efficient cities. Frontiers in Sustainable Cities, 7, 1556974. https://doi.org/10.3389/frsc.2025.1556974