EVALUATION OF MACHINE LEARNING MODELS IN SOLAR RADIATION PREDICTION FOR PHOTOVOLTAIC SYSTEM DESIGN
Keywords:
Solar radiation, sizing, costs, EcuadorAbstract
DOI: https://doi.org/10.46296/ig.v8i15.0255
This study evaluates the technical and economic feasibility of a photovoltaic microgenerator in Ecuador, tailored to the residential, commercial, and industrial sectors. A Support Vector Machine (SVM) model was used to predict solar radiation, achieving metrics of precision (0.96), sensitivity (0.96), and accuracy (0.92). In the residential sector, the system requires 11.76 kW and 39 panels to meet a daily demand of 50 kWh, with an initial investment of $4,950 USD and an annual saving of $1,200 USD, reaching the break-even point in 4.12 years. In the commercial sector, 11.76 kW is needed for a similar daily demand, while in the industrial sector, 78.43 kW and 261 panels are required to cover 333.33 kWh/day. The developed tool optimizes system sizing, considering factors such as panel efficiency, battery capacity, inverter power, and days of autonomy. It also analyzes installation costs and return on investment, demonstrating that photovoltaic systems are cost-effective and reduce CO₂ emissions. The results highlight the feasibility of these systems to diversify Ecuador's energy matrix, maximizing economic and environmental benefits.
Keywords: Solar radiation, sizing, costs, Ecuador.
References
Tumbaco K. y Pantaleón K, “Generación de energía eléctrica a través de un sistema fotovoltaico Off Grid en la Zona rural de Guayaquil”, Investigación, Universidad Politécnica Salesiana, Guayaquil, 2024. Consultado: el 15 de febrero de 2025. [En línea]. Disponible en: https://dspace.ups.edu.ec/bitstream/123456789/24665/1/UPS-GT004259.pdf
W. A. Beckman y N. Blair, “Solar Engineering of Thermal Processes, Photovoltaics and Wind Emeritus Professor of Mechanical Engineering”, 2020, Consultado: el 14 de febrero de 2025. [En línea]. Disponible en: www.wiley.com/go/permissions.
Mariela Tapia, Leonard Ramos, Detlev Heinemann, y Edwin Zondervan, “Evaluación del Potencial Fotovoltaico en Tejados en el Cantón Quito.”, Perfiles, vol. 1, núm. 30, pp. 47–56, dic. 2023, doi: 10.47187/PERF.V1I30.240.
CELEC, “Estadística Anual y Multianual 2023 DEL SECTOR ELÉCTRICO ECUATORIANO Agencia de Regulación y Control de Energía y Recursos Naturales No Renovables”, pp. 20–120, mar. 2024, Consultado: el 15 de febrero de 2025. [En línea]. Disponible en: https://www.controlrecursosyenergia.gob.ec/wp-content/uploads/downloads/2024/04/EstadisticaAnual2023-WEB-2.pdf
CONELEC, “ATLAS SOLAR DEL ECUADOR CON FINES DE GENERACIÓN ELÉCTRICA Corporación para la Investigación Energética”, pp. 2–22, ago. 2008.
H. R. L. Altamirano, O. E. Guerra, N. Z. Garay, y J. A. A. Son, “PREPROCESAMIENTO DE DATOS PRELIMINARES PARA CLASIFICADORES EN APRENDIZAJE SUPERVISADO”, TECTZAPIC. Revista Académico-Científica, pp. 80–87, ene. 2022, doi: 10.51896/TECTZAPIC/HWAL1467.
C. Fabara et al., “Predicción de la Generación para un Sistema Fotovoltaico mediante la aplicación de técnicas de Minería de Datos”, Revista Técnica energía, vol. 16, núm. 1, pp. 70–78, ene. 2019, doi: 10.37116/REVISTAENERGIA.V16.N1.2019.337.
B. I. Frauberth Camayo-Lapa, J. I. Eduardo Pomachagua-Paucar, J. I. Raúl Massipe-Hernaández, M. I. Oswaldo Quispe-Flores, y A. Torres-Ten III, “Validación y aplicación del modelo Bristow Campbell para estimar la radiación solar global de la región de Junin”, Tecnología Química, vol. 37, núm. 3, pp. 574–590, 2017, Consultado: el 15 de febrero de 2025. [En línea]. Disponible en: http://scielo.sld.cu/scielo.php?script=sci_arttext&pid=S2224-61852017000300015&lng=pt&nrm=iso&tlng=es
V. N. Vapnik, “The Nature of Statistical Learning Theory”, The Nature of Statistical Learning Theory, 2000, doi: 10.1007/978-1-4757-3264-1.
R. A. Messenger y J. Ventre, “Photovoltaic Systems Engeneering”, Photovoltaic Systems Engeneering, 2005.
J. A. Duffie y W. A. Beckman, “Estimation of Clear-Sky radiation”, Solar Engineering of Thermal Processes, pp. 68–71, 2013, Consultado: el 15 de febrero de 2025. [En línea]. Disponible en: https://www.wiley.com/en-gb/Solar+Engineering+of+Thermal+Processes%2C+4th+Edition-p-9780470873663
J. L. García, F. Jurado, y V. Larco, “Review and resource assessment, solar energy in different region in Ecuador”, E3S Web of Conferences, vol. 80, ene. 2019, doi: 10.1051/E3SCONF/20198001003.
M. Abuella y B. Chowdhury, “Solar power forecasting using artificial neural networks”, 2015 North American Power Symposium, NAPS 2015, nov. 2015, doi: 10.1109/NAPS.2015.7335176.
F. Cucchiella, I. D’Adamo, y M. Gastaldi, “The economic feasibility of residential energy storage combined with PV panels: The role of subsidies in Italy”, Energies (Basel), vol. 10, núm. 9, p. 149, sep. 2017, doi: 10.3390/en10091434.
Kieran Thompson, “Southeast Asia’s pathway to clean energy is all but clean”, pp. 1–4, ago. 2024, Consultado: el 13 de febrero de 2025. [En línea]. Disponible en: https://www.hinrichfoundation.com/research/wp/sustainable/southeast-asia-pathway-to-clean-energy/?utm_source=google&utm_medium=search-retargeting&utm_campaign=wp-thompson-sea-pathway-to-clean-energy&utm_content=20250121-static&utm_term=clean%20energy%20infrastructure&utm_campaign=Search+%7C+Generic+%7C+Kieran:+Clean+Energy&utm_source=adwords&utm_medium=ppc&hsa_acc=8724352572&hsa_cam=22138256118&hsa_grp=174535073460&hsa_ad=729741001407&hsa_src=g&hsa_tgt=kwd-2224713373813&hsa_kw=clean%20energy%20infrastructure&hsa_mt=b&hsa_net=adwords&hsa_ver=3&gad_source=1&gclid=CjwKCAiA8Lu9BhA8EiwAag16by53fmrCzsS4WSpyTW3JBpa_UPJ-6H3quZc2w_6Vjd7siwP1yCjvGxoCNswQAvD_BwE
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Scientific Journal INGENIAR: Engineering, Technology and Research
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
