Hourly electricity consumption forecasting for Antioquia-Colombia using statistical-machine learning models
dc.contributor.advisor | Giraldo Gómez, Norman Diego | |
dc.contributor.author | Restrepo Gil, Adiel Ignacio | |
dc.coverage.region | Antioquia, Colombia | |
dc.date.accessioned | 2024-07-09T12:17:40Z | |
dc.date.available | 2024-07-09T12:17:40Z | |
dc.date.issued | 2024 | |
dc.description | Ilustraciones | spa |
dc.description.abstract | Energy sector plays a fundamental role in encouraging a country's economic growth and social progress due to its functionality as an input for productive processes and as a public service asset that provides greater welfare to the population. Electricity consumption forecasting is a valuable instrument for policy-makers to guide pricing, taxation and investment decisions, as well as energy and operational security planning, helping to ensure a continuous supply of electricity and reducing cost overruns associated with the provision of energy distribution services. The aim of this research is to forecast hourly electricity consumption in Antioquia-Colombia using Statiscal-Machine Learning models with exogenous variables such as day-type and maximum temperature. The results show that LSTM Neural Network can be an efficient model for the operational deployment of electricity distribution since its average electricity supply error for an operational week is estimated to be around 493 MWh, while XM Market Operator's benchmark model obtained an error of 3420 MWh during the evaluated week. (Tomado de la fuente) | eng |
dc.description.abstract | El sector energético desempeña un papel fundamental en el fomento del crecimiento económico y el progreso social de un país debido a su funcionalidad como insumo de los procesos productivos y como activo de servicio público que proporciona mayor bienestar a la población. La previsión del consumo de energía eléctrica es un valioso instrumento para que los hacedores de política orienten las decisiones de tarifas, impuestos e inversión, así como la planificación de la seguridad energética y operativa, contribuyendo a garantizar un suministro continuo de electricidad y reduciendo los sobrecostos asociados a la prestación de los servicios de distribución de energía. El objetivo de esta investigación es pronosticar el consumo de electricidad horario en Antioquia-Colombia utilizando modelos de Statistical-Machine Learning con variables exógenas como el tipo de día y la temperatura máxima. Los resultados muestran que la Red Neuronal LSTM puede ser un modelo eficiente para el despliegue operativo de la distribución eléctrica debido a que su error promedio de suministro de electricidad para una semana operativa se estima en alrededor de 493 MWh, mientras que el modelo de referencia del Operador de Mercado XM obtuvo un error de 3420 MWh durante la semana evaluada. | spa |
dc.description.curriculararea | Estadística.Sede Medellín | spa |
dc.description.degreelevel | Maestría | spa |
dc.description.degreename | Magíster en Ciencias - Estadística | spa |
dc.format.extent | 50 páginas | spa |
dc.format.mimetype | application/pdf | spa |
dc.identifier.instname | Universidad Nacional de Colombia | spa |
dc.identifier.reponame | Repositorio Institucional Universidad Nacional de Colombia | spa |
dc.identifier.repourl | https://repositorio.unal.edu.co/ | spa |
dc.identifier.uri | https://repositorio.unal.edu.co/handle/unal/86415 | |
dc.language.iso | eng | spa |
dc.publisher | Universidad Nacional de Colombia | spa |
dc.publisher.branch | Universidad Nacional de Colombia - Sede Medellín | spa |
dc.publisher.faculty | Facultad de Ciencias | spa |
dc.publisher.place | Medellín, Colombia | spa |
dc.publisher.program | Medellín - Ciencias - Maestría en Ciencias - Estadística | spa |
dc.relation.indexed | LaReferencia | spa |
dc.relation.references | Arora, S. and Taylor, J. W. (2018). Rule-based autoregressive moving average models for forecasting load on special days: A case study for france. European Journal of Operational Research, 266(1):259–268. | spa |
dc.relation.references | Bandara, K., Hyndman, R. J., and Bergmeir, C. (2021). Mstl: A seasonal-trend decomposition algorithm for time series with multiple seasonal patterns. | spa |
dc.relation.references | Barrientos, A. F., Olaya, J., and Gonzalez, V. M. (2007). A spline model for electricity demand forescasting. Revista Colombiana de Estad ́ıstica, 30(2):187. | spa |
dc.relation.references | Barrientos, J., Marquez Marulanda, L., and Villada Duque, F. (2023). Analyzing electricity demand in colombia: A functional time series approach. International Journal of Energy Economics and Policy, 13(1):75–84. | spa |
dc.relation.references | Bartz, E., Bartz-Beielstein, T., Zaefferer, M., and Mersmann, O. (2023). Hyperparameter Tuning for Machine and Deep Learning with R - A Practical Guide. Springer. | spa |
dc.relation.references | Berbesi, L. and Pritchard, G. (2023). Modelling energy data in a generalized additive model: A case study of Colombia. Energies, 16(4). | spa |
dc.relation.references | Bergmeir, C., Hyndman, R. J., and Koo, B. (2018). A note on the validity of cross-validation for evaluating autoregressive time series prediction. Computational Statistics Data Analysis, 120:70–83. | spa |
dc.relation.references | Bontempi, G., Ben Taieb, S., and Le Borgne, Y.-A. (2013). Machine Learning Strategies for Time Series Forecasting, volume 138. | spa |
dc.relation.references | Castaño, E. (2007). Reconstrucción de datos de series de tiempo: una aplicación a la demanda horaria de la electricidad. Revista Colombiana de Estadística, 30:247 – 263. | spa |
dc.relation.references | Chapagain, K. and Kittipiyakul, S. (2018). Performance analysis of short-term electricity demand with atmospheric variables. Energies, 11. | spa |
dc.relation.references | Chen, T. and Guestrin, C. (2016). Xgboost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD ’16, page 785–794, New York, NY, USA. Association for Computing Machinery. | spa |
dc.relation.references | CNO (2021). Consejo nacional de operación: Acuerdo 1303 por el cual se actualizan los procedimientos para la gestión integral de la demanda. Retrieved Dec 10, 2023 from https://bit.ly/3KSCHoI. | spa |
dc.relation.references | CPC (2020). Informe Nacional de Competitividad 2020-2021. Bogotá: Consejo Privado de Competitividad. | spa |
dc.relation.references | Diebold, F. and Mariano, R. (1995). Comparing predictive accuracy. Journal of Business Economic Statistics, 13(3):253–63. | spa |
dc.relation.references | Diebold, F. X. and Rudebusch, G. D. (1999). Business cycles: Durations, dynamics, and forecasting. (6636). | spa |
dc.relation.references | Divina, F., Gilson, A., Goméz-Vela, F., García Torres, M., and Torres, J. F. (2018). Stacking ensemble learning for short-term electricity consumption forecasting. Energies, 11(4). | spa |
dc.relation.references | DNP (2017). Energy Demand Situation in Colombia. Enersinc. | spa |
dc.relation.references | EIA (2023). Energy Information Administration: Electricity explained. Retrieved Dec 1, 2023 from www.eia.gov/energyexplained/electricity. | spa |
dc.relation.references | Engle, R. F. and Granger, C. W. J. (1987). Co-integration and error correction: Representation, estimation, and testing. Econometrica, 55(2):251–276. | spa |
dc.relation.references | Garcia, J., Rey Londoño, F., Arango Restrepo, L. J., and Bohorquez Correa, S. (2023). Sectoral analysis of electricity consumption during the covid-19 pandemic: Evidence for unregulated and regulated markets in colombia. Energy, 268:126614. | spa |
dc.relation.references | Gómez, D. (2001). Análisis espectral: consideraciones teóricas y aplicabilidad. Economía y Sociedad, 6. | spa |
dc.relation.references | Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning. MIT Press. | spa |
dc.relation.references | Hamilton, J. D. (1994). Time series analysis. 10. | spa |
dc.relation.references | Harvey, D., Leybourne, S., and Newbold, P. (1997). Testing the equality of prediction mean squared errors. International Journal of Forecasting, 13(2):281–291. | spa |
dc.relation.references | Hastie, T. and Tibshirani, R. (2017). Generalized Additive Models. Taylor Francis Group., pages 249–307. | spa |
dc.relation.references | Hastie, T., Tibshirani, R., and Friedman, J. (2009). The elements of statistical learning: Data mining, inference, and prediction. Springer Series in Statistics. Springer, 2nd ed. 2009. corr. 3rd printing 5th printing. edition. | spa |
dc.relation.references | Hastie, T., Tibshirani, R., and Wainwright, M. (2015). Statistical Learning with Sparsity: The Lasso and Generalizations. Chapman Hall/CRC Monographs on Statistics Applied Probability. Chapman and Hall/CRC. | spa |
dc.relation.references | Hochreiter, S. and Schmidhuber, J. (1997). Long short-term memory. Neural computation, 9:1735–80. | spa |
dc.relation.references | James, G., Tibshirani, R., Witten, D., and Hastie, T. (2021). An Introduction to Statistical Learning: With Applications in R. Springer Texts in Statistics. Springer, 2 edition. | spa |
dc.relation.references | Jiang, P., Li, R., Lu, H., and Zhang, X. (2020). Modeling of electricity demand forecast for power system. Neural Computing and Applications, 32:1–19. | spa |
dc.relation.references | Jimenez Mares, J., Pertuz, A., Quintero M., C., and Montana, J. (2019). Multivariate statistical analysis based methodology for long-term demand forecasting. IEEE Latin America Transactions, 17:93–101. | spa |
dc.relation.references | Johansen, S. (1991). Estimation and hypothesis testing of cointegration vectors in gaussian vector autoregressive models. Econometrica, 59(6):1551–1580. | spa |
dc.relation.references | Khalil, M., McGough, S. A., Pourmirza, Z., Pazhoohesh, M., and Walker, S. (2022). Machine learning, deep learning and statistical analysis for forecasting building energy consumption — a systematic review. Engineering Applications of Artificial Intelligence, 115:105287. | spa |
dc.relation.references | Khan, A. M. and Osi ́nska, M. (2023). Comparing forecasting accuracy of selected grey and time series models based on energy consumption in brazil and india. Expert Systems with Applications, 212:118840. | spa |
dc.relation.references | Kim, Y.-J. and Gu, C. (2004). Smoothing spline gaussian regression: More scalable computation via efficient approximation. Journal of the Royal Statistical Society. Series B (Statistical Methodology), 66(2):337–356. | spa |
dc.relation.references | Kumar, S., Viral, R., Deep, V., Sharma, P., Kumar, M., Mahmud, M., and Stephan, T. (2021). Forecasting major impacts of covid-19 pandemic on country-driven sectors: challenges, lessons, and future roadmap. Personal and Ubiquitous Computing. | spa |
dc.relation.references | La Tona, G., Luna, M., and Di Piazza, M. (2023). Day-ahead forecasting of residential electric power consumption for energy management using long short-term memory encoder–decoder model. Mathematics and Computers in Simulation. | spa |
dc.relation.references | Li, R., Chen, X., Balezentis, T., Streimikiene, D., and Niu, Z. (2021). Multi-step least squares support vector machine modeling approach for forecasting short-term electricity demand with application. Neural Comput. Appl., 33(1):301–320. | spa |
dc.relation.references | Maltais, L.-G. and Gosselin, L. (2022). Forecasting of short-term lighting and plug load electricity consumption in single residential units: Development and assessment of data-driven models for different horizons. Applied Energy, 307:118229. | spa |
dc.relation.references | Medina, S., Moreno, J., and Gallego, J. P. (2012). Pronóstico de la demanda de energía eléctrica horaria en Colombia mediante redes neuronales artificiales. Revista Facultad de Ingeniería Universidad de Antioquia, (59):98–107. | spa |
dc.relation.references | Meng, Z., Sun, H., and Wang, X. (2022). Forecasting energy consumption based on svr and markov model: A case study of china. Frontiers in Environmental Science, page 363. | spa |
dc.relation.references | Murat, N. (2022). Outlier detection in statistical modeling via multivariate adaptive regression splines. Communications in Statistics - Simulation and Computation, 0(0):1–12. | spa |
dc.relation.references | Murillo, J., Trejos, A., and Carvajal, P. (2003). Estudio del pronostico de la demanda de energía eléctrica, utilizando modelos de series de tiempo. Scientia Et Technica, 3(23). | spa |
dc.relation.references | Peters, J., Janzing, D., and Schlkopf, B. (2017). Elements of Causal Inference: Foundations and Learning Algorithms. The MIT Press. | spa |
dc.relation.references | Ribeiro, A., Carmo, P., Silva, I., Sadok, D., Lynn, T., and Endo, P. (2020). Short-term firm-level energy-consumption forecasting for energy-intensive manufacturing: A comparison of machine learning and deep learning models. Algorithms, 13:274. | spa |
dc.relation.references | Rosero, J., Gonzalez, F. A., Zambrano, A., and Toledo-Cortesa, S. (2023). Short-term forecasting of power demand: A case study with data from colombia. SSNR. | spa |
dc.relation.references | Sadeghian Broujeny, R., Ben Ayed, S., and Matalah, M. (2023). Energy consumption forecasting in a university office by artificial intelligence techniques: An analysis of the exogenous data effect on the modeling. Energies, 16(10). | spa |
dc.relation.references | Safer, A. M. (2004). Multivariate adaptive regression splines and insider trading data for stock prediction. Journal of Interdisciplinary Mathematics, 7(1):79–93. | spa |
dc.relation.references | Santa María, M., Von Der Fehr, N.-H., Millán, J., Benavides, J., and Gracia, O. (2009). El mercado de la energía eléctrica en Colombia: características, evolución e impacto sobre otros sectores. Bogotá: Fedesarrollo, 304 p. | spa |
dc.relation.references | Saranj, A. and Zolfaghari, M. (2022). The electricity consumption forecast: Adopting a hybrid approach by deep learning and arimax-garch models. Energy Reports, 8:7657–7679. | spa |
dc.relation.references | Sarmiento, H. O. and Villa, W. M. (2008). Inteligencia artificial en pronóstico de demanda de energía eléctrica: una aplicación en optimización de recursos energéticos. Revista Colombiana de Tecnologías de Avanzada. | spa |
dc.relation.references | Son, J., Cha, J., Kim, H., and Wi, Y.-M. (2022). Day-ahead short-term load forecasting for holidays based on modification of similar days’ load profiles. IEEE Access, 10:17864– 17880. | spa |
dc.relation.references | Sujan, R. A., Akashdeep, S., Harshvardhan, R., and Sowmya, K. S. (2022). Stacking deep learning and machine learning models for short-term energy consumption forecasting. Advanced Engineering Informatics, 52:101542. | spa |
dc.relation.references | UPME (2021). Proyección de Demanda de Energía Eléctrica, Gas Natural y Combustibles Líquidos 2022-2036. | spa |
dc.relation.references | UPME (2023). Proyecciión de la Demanda de Energía Eléctrica y Potencia Máxima 2023- 2037. | spa |
dc.relation.references | Ushiku, Y. (2020). Long Short-Term Memory, pages 1–7. Springer International Publishing, Cham. | spa |
dc.relation.references | Valencia, A., Moreno, C. A., and Lozano, C. A. (2007). Modelo de promedios móviles para el pronóstico horario de potencia y energía eléctrica. El Hombre y la Máquina | spa |
dc.relation.references | Wasserman, L. (2010). All of Statistics : a concise course in statistical inference. Springer, New York. | spa |
dc.relation.references | Wen, L., Zhou, K., and Yang, S. (2020). Load demand forecasting of residential buildings using a deep learning model. Electric Power Systems Research, 179:106073. | spa |
dc.relation.references | Wood, S. N. (2017). Generalized Additive Models: An Introduction with R, Second Edition. | spa |
dc.relation.references | XM (2023). Mercados. Retrieved Dec 10, 2023 from www.xm.com.co/consumo/mercados. | spa |
dc.relation.references | Young-Min, W., Sung-Kwan, J., and Kyung-Bin, S. (2012). Holiday load forecasting using fuzzy polynomial regression with weather feature selection and adjustment. IEEE Transactions on Power Systems, 27(2):596–603. | spa |
dc.relation.references | Zhou, C., Fang, Z., Xu, X., Zhang, X., Ding, Y., Jiang, X., and ji, Y. (2020). Using long short-term memory networks to predict energy consumption of air-conditioning systems. Sustainable Cities and Society, 55:102000. | spa |
dc.relation.references | Zhou, W., Tao, H., Ding, S., and Li, Y. (2023). Electricity consumption and production forecasting considering seasonal patterns: An investigation based on a novel seasonal discrete grey model. Journal of the Operational Research Society, 74(5):1346–1361. | spa |
dc.relation.references | Zhu, G., Peng, S., Lao, Y., Su, Q., and Sun, Q. (2021a). Short-term electricity consumption forecasting based on the emd-fbprophet-lstm method. Mathematical Problems in Engineering, 2021:1–9. | spa |
dc.relation.references | Zhu, K., Geng, J., and Wang, K. (2021b). A hybrid prediction model based on pattern sequence-based matching method and extreme gradient boosting for holiday load forecasting. Electric Power Systems Research, 190:106841. | spa |
dc.relation.references | Zolfaghari, M. and Sahabi, B. (2019). A hybrid approach to model and forecast the electricity consumption by neurowavelet and arimax-garch models. Energy Efficiency, 12. | spa |
dc.rights.accessrights | info:eu-repo/semantics/openAccess | spa |
dc.rights.license | Atribución-NoComercial-CompartirIgual 4.0 Internacional | spa |
dc.rights.uri | http://creativecommons.org/licenses/by-nc-sa/4.0/ | spa |
dc.subject.ddc | 510 - Matemáticas::519 - Probabilidades y matemáticas aplicadas | spa |
dc.subject.ddc | 330 - Economía::333 - Economía de la tierra y de la energía | spa |
dc.subject.lemb | Estadística - Procesamiento de datos | |
dc.subject.lemb | Pronóstico del tiempo por estadística - Antioquia, Colombia | |
dc.subject.lemb | Consumo de energía - Estadística - Antioquia, Colombia | |
dc.subject.lemb | Rendimiento energético - Estadística - Antioquia, Colombia | |
dc.subject.proposal | Forecast | eng |
dc.subject.proposal | Electricity consumption | eng |
dc.subject.proposal | Machine learning | eng |
dc.subject.proposal | Pronóstico | spa |
dc.subject.proposal | Consumo de electricidad | spa |
dc.title | Hourly electricity consumption forecasting for Antioquia-Colombia using statistical-machine learning models | eng |
dc.title.translated | Pronóstico del consumo de electricidad horario para Antioquia-Colombia utilizando modelos de statistical-machine learning | eng |
dc.type | Trabajo de grado - Maestría | spa |
dc.type.coar | http://purl.org/coar/resource_type/c_bdcc | spa |
dc.type.coarversion | http://purl.org/coar/version/c_ab4af688f83e57aa | spa |
dc.type.content | Text | spa |
dc.type.driver | info:eu-repo/semantics/masterThesis | spa |
dc.type.redcol | http://purl.org/redcol/resource_type/TM | spa |
dc.type.version | info:eu-repo/semantics/acceptedVersion | spa |
dcterms.audience.professionaldevelopment | Administradores | spa |
dcterms.audience.professionaldevelopment | Estudiantes | spa |
dcterms.audience.professionaldevelopment | Investigadores | spa |
dcterms.audience.professionaldevelopment | Público general | spa |
dcterms.audience.professionaldevelopment | Responsables políticos | spa |
oaire.accessrights | http://purl.org/coar/access_right/c_abf2 | spa |
Archivos
Bloque original
1 - 1 de 1
Cargando...
- Nombre:
- 1037664686.2024.pdf
- Tamaño:
- 2.38 MB
- Formato:
- Adobe Portable Document Format
- Descripción:
- Tésis de Maestría en Ciencias - Estadística
Bloque de licencias
1 - 1 de 1
Cargando...
- Nombre:
- license.txt
- Tamaño:
- 5.74 KB
- Formato:
- Item-specific license agreed upon to submission
- Descripción: