Herramienta para el diseño de sistemas solares fotovoltaicos basada en redes neuronales artificiales (RNA) para determinar la configuración, selección de equipos y arreglos fotovoltaicos en Colombia
| dc.contributor.advisor | Mendoza Castellanos, Luis Sebastián | spa |
| dc.contributor.advisor | Arizmendi Pereira, Carlos Julio | spa |
| dc.contributor.advisor | Noguera Galindo, Ana Lisbeth | spa |
| dc.contributor.author | Ochoa Buitrago, Harold Oswaldo | spa |
| dc.contributor.author | Ramírez León, Fabian Yesid | spa |
| dc.contributor.cvlac | https://scienti.minciencias.gov.co/cvlac/visualizador/generarCurriculoCv.do?cod_rh=0000115302 | * |
| dc.contributor.googlescholar | https://scholar.google.es/citations?hl=es&user=S5TZbi8AAAAJ | * |
| dc.contributor.orcid | https://orcid.org/0000-0001-8263-2551 | * |
| dc.contributor.researchgate | https://www.researchgate.net/profile/Sebastian_Mendoza6 | * |
| dc.contributor.scopus | https://www.scopus.com/authid/detail.uri?authorId=57193169160 | * |
| dc.coverage.campus | UNAB Campus Bucaramanga | spa |
| dc.coverage.spatial | Colombia | spa |
| dc.date.accessioned | 2020-12-15T15:20:52Z | |
| dc.date.available | 2020-12-15T15:20:52Z | |
| dc.date.issued | 2020-09 | |
| dc.degree.name | Ingeniero en Energía | spa |
| dc.description.abstract | En este proyecto se desarrolló una herramienta que consta de una Red Neuronal Artificial (RNA) que brinda apoyo en el dimensionamiento y proyección de los sistemas fotovoltaicos. Esto fue realizado, mediante una estimación de la configuración eléctrica de algunos proyectos registrados ante la UPME y los datos de ingeniería de detalle que se documentan en la Agencia Nacional de Licencias Ambientales (ANLA). Para la propuesta se implementó una técnica de inteligencia artificial, aprendizaje de máquina supervisado. Para esto, fue implementada una variación del algoritmo K vecinos cercanos, por medio de la función FSCNCA por sus siglas en inglés “Feature Selection for Classification using Neighborhood Component Analysis”. Se usó la técnica de redes neuronales que permitieron el dimensionamiento, diseño y clasificación de los proyectos solares fotovoltaicos. Adicionalmente se implementó un árbol de decisión, que permitió seleccionar más aproximadas a los requerimientos área, potencia de diseño y presupuesto destinado a paneles e inversores. | spa |
| dc.description.abstractenglish | In this project, a tool was developed that consists of an Artificial Neural Network (ANN) that provides support in the dimensioning and projection of photovoltaic systems. This was done by estimating the electrical configuration of some projects registered with the UPME and detailed engineering data that is documented in the National Environmental Licensing Agency (ANLA). For the proposal, an artificial intelligence technique, supervised machine learning, was implemented. For this, a variation of the K near neighbors algorithm was implemented, by means of the FSCNCA function for its acronym in English “Feature Selection for Classification using Neighborhood Component Analysis”. The neural network technique was used that allowed the dimensioning, design and classification of photovoltaic solar projects. Additionally, a decision tree was implemented, which made it possible to select the most approximate requirements for area, design power and budget for panels and inverters. | eng |
| dc.description.degreelevel | Pregrado | spa |
| dc.description.learningmodality | Modalidad Presencial | spa |
| dc.description.tableofcontents | Introducción ........................................................................................................... 3 1. Aspectos generales del proyecto .................................................................... 4 1.1 Planteamiento del problema ...................................................................... 4 1.2 Objetivo principal....................................................................................... 5 1.3 Objetivos específicos ................................................................................ 5 1.4 Alcances ................................................................................................... 5 1.5 Limitaciones .............................................................................................. 5 1.6 Justificación .............................................................................................. 6 2. Marco referencial ............................................................................................ 7 2.1 Antecedentes ............................................................................................ 7 2.2 Marco teórico. ........................................................................................... 8 Movimiento aparente del sol ............................................................... 8 Sistemas fotovoltaicos ........................................................................ 9 Sistemas fotovoltaicos conectados a la red ...................................... 10 Dimensionamiento de sistemas fotovoltaicos conectados a la red .... 10 Inteligencia artificial .......................................................................... 14 Tratamiento de datos ........................................................................ 16 Selección de características ............................................................. 19 Generación de datos ........................................................................ 22 Aprendizaje de maquina ................................................................... 24 Algoritmos de aprendizaje supervisado ......................................... 24 3. Metodología. ................................................................................................. 34 4. Recolección de datos .................................................................................... 34 4.1 Desarrollo de la herramienta auxiliar ....................................................... 35 4.2 Tratamiento de datos .............................................................................. 37 Visualización de datos ...................................................................... 37 Limpieza de datos ............................................................................ 40 Imputación de datos utilizando interpolación lineal ........................... 40 5. Selección de características.......................................................................... 42 Selección de características para clasificación ................................. 43 Generación de datos sintéticos ......................................................... 46 II Selección de características para la regresión .................................. 47 6. Redes neuronales ......................................................................................... 54 Redes neuronales para clasificación ................................................ 55 Redes neuronales para regresión ..................................................... 58 7. Resultados .................................................................................................... 62 7.1 Base de datos de los proyectos .............................................................. 62 7.2 Variables más relevantes para la clasificación ........................................ 63 7.3 Variables más relevantes para la regresión............................................. 64 7.4 Arquitecturas seleccionadas ................................................................... 65 7.5 Herramienta ............................................................................................ 67 7.6 Ensayo de la herramienta ....................................................................... 68 8. Conclusiones ................................................................................................ 69 9. Recomendaciones ........................................................................................ 70 10. Biografía ..................................................................................................... 71 Anexo A : Datos recolectados de la ANLA ...................................................... 75 Anexo B : Tabla de dimensionamiento de la herramienta auxiliar ................... 77 Anexo C : Explicación del script del proceso ................................................... 81 | spa |
| dc.format.mimetype | application/pdf | spa |
| dc.identifier.instname | instname:Universidad Autónoma de Bucaramanga - UNAB | spa |
| dc.identifier.reponame | reponame:Repositorio Institucional UNAB | spa |
| dc.identifier.repourl | repourl:https://repository.unab.edu.co | spa |
| dc.identifier.uri | http://hdl.handle.net/20.500.12749/11930 | |
| dc.language.iso | spa | spa |
| dc.publisher.grantor | Universidad Autónoma de Bucaramanga UNAB | spa |
| dc.publisher.program | Pregrado Ingeniería en Energía | spa |
| dc.relation.references | [1] UPME, “Circular Externa No 046-2019,” 2019. | spa |
| dc.relation.references | [2] “Microsoft Power B .” [ nline]. Available: https://app.powerbi.com/view?r=eyJrIjoiNzBhN2Q4YmMtN2IxMy00Mjg2LWJhZTctMjRkNWE2NDdlMzI0IiwidCI6IjgxNTAwZjZkLWJjZTktNDgzNC1iNDQ2LTc0YjVmYjljZjEwZSIsImMiOjh9. [Accessed: 15-Jun-2020]. | spa |
| dc.relation.references | [3] “PV Performance Modeling Collaborative | PV_ B Toolbox,” PV Lib, 2018. [Online]. Available: https://pvpmc.sandia.gov/applications/pv_lib-toolbox/. [Accessed: 02-Jun-2020]. | spa |
| dc.relation.references | [4] A. Mellita and M. Benghanem, “Sizing of stand-alone photovoltaic systems using neural network adaptive model,” Desalination, vol. 209, no. 1-3 SPEC. ISS., pp. 64–72, 2007, doi: 10.1016/j.desal.2007.04.010 | spa |
| dc.relation.references | [5] L. ontoria, J. Aguilera, and P. Zufiria, “A new approach for sizing stand alone photovoltaic systems based in neural networks,” Sol. Energy, vol. 78, no. 2, pp. 313–319, 2005, doi: 10.1016/j.solener.2004.08.018. | spa |
| dc.relation.references | [6] M. H. Alomari, J. Adeeb, and O. Younis, “Solar photovoltaic power forecasting in Jordan using artificial neural networks,” Int. J. Electr. Comput. Eng., vol. 8, no. 1, pp. 497–504, 2018, doi: 10.11591/ijece.v8i1.pp497-504 | spa |
| dc.relation.references | [7] A. K. Yadav and S. S. Chandel, “Solar radiation prediction using Artificial Neural Network techniques: A review,” Renew. Sustain. Energy Rev., vol. 33, pp. 772–781, 2014, doi: 10.1016/j.rser.2013.08.055. | spa |
| dc.relation.references | [8] F. Rodríguez, A. Fleetwood, A. Galarza, and L. Fontán, “Predicting solar energy generation through artificial neural networks using weather forecasts for microgrid control,” Renew. Energy, vol. 126, pp. 855–864, 2018, doi: 10.1016/j.renene.2018.03.070 | spa |
| dc.relation.references | [9] X. Luo et al., Solar water heating system. 2018 | spa |
| dc.relation.references | [10] R. D. Prasad and R. C. Bansal, “Photovoltaic systems,” Handb. Renew. Energy Technol., pp. 205–224, 2011, doi: 10.1142/9789814289078_0009 | spa |
| dc.relation.references | [11] M. C. MER N , “Escuela Técnica Superior de ngeniería del Diseño Grado en Ingeniería Electrónica Industrial y Automática,” 2019 | spa |
| dc.relation.references | [12] meteorología y estudios ambientales (IDEAM) Instituto de hidrología, “ RRAD AC ÓN G BA R Z NTA MED D AR ANUA ,” 2014. [Online]. Available: http://atlas.ideam.gov.co/basefiles/RadiacionSolar13.pdf. [Accessed: 03-Jun-2020]. | spa |
| dc.relation.references | [13] Subdirección de Meteorología and DEAM, “Clasificaciones Climaticas Colombia,” 05-Jun-2020. [Online]. Available: http://www.ideam.gov.co/documents/21021/418894/Clasificaciones+Climáticas.pdf/15d8c5c8-a850-43f9-a954-2ce98d927f98. [Accessed: 04-Jul-2020]. | spa |
| dc.relation.references | [14] K. A. ERNÁNDEZ and J. S. CARR CRUZ, “ANÁ S S DE A CURVA DE DEMANDA ELÉCTRICA PARA USUARIOS RESIDENCIALES ESTRATO 4 EN LA CIUDAD DE BOGOTÁ ANTE DIFERENTES ESCENARIOS DE LOS ÁB T S DE C NSUM ,” Univ. Dist. Fr. JOSÉ CALDAS, vol. 01, pp. 1–163, 2017. | spa |
| dc.relation.references | [15] O. Perpiñan Lamigueiro, E S Fotovoltaica. 2012. | spa |
| dc.relation.references | [16] A. Smets, K. Jäger, O. Isabella, R. A. C. M. M. Van Swaaij, and M. Zeman, Solar Energy - The physics and engineering of photovoltaic conversion, technologies and systems. 2016. | spa |
| dc.relation.references | [17] E. M. Knowles, Oxford Dictionary of Phrase and Fable. Oxford University Press, 2005 | spa |
| dc.relation.references | [18] S. Rusell and P. Norvig, Inteligencia Artificial. Un Enfoque Moderno. 2004. | spa |
| dc.relation.references | [19] V. Novák, . Perfilieva, and J. Močkoř, Mathematical Principles of Fuzzy Logic, no. January. 1999 | spa |
| dc.relation.references | [20] F. Behrooz, N. Mariun, M. H. Marhaban, M. A. M. Radzi, and A. R. Ramli, “Review of control techniques for VAC systems-nonlinearity approaches based on fuzzy cognitive maps,” Energies, vol. 11, no. 3, 2018, doi: 10.3390/en11030495 | spa |
| dc.relation.references | [21] B. G. BUC ANAN, “Expert systems: working systems and the research literature,” Expert Syst., vol. 3, no. 1, pp. 32–50, 1986, doi: 10.1111/j.1468-0394.1986.tb00192.x. | spa |
| dc.relation.references | [22] D. uttenlocher, “Computer vision,” Comput. Sci. Handbook, Second Ed., pp. 43-1-43–23, 2004, doi: 10.4324/9780429042522-10. | spa |
| dc.relation.references | [23] E. Gharibkhani and R. C. Akdeniz, “Advantages and Disadvantages of Machine Vision Applications for Automatic Sorting of Aflatoxin Contaminated Dried Figs,” vol. 10, pp. 7–10, 2014. | spa |
| dc.relation.references | [24] A. Cortez, H. Vega, and J. Pariona, “Procesamiento de lenguaje natural robusto,” Prim. encuentro Grup. Investig. sobre Proces. del Leng., vol. 2013, no. 3, p. 147, 2011. | spa |
| dc.relation.references | [25] A. Geron, Hands-On Machine Learing With Scikit-Learn & Tensor Flow. ’Reilly Media, 2017 | spa |
| dc.relation.references | [26] T. Yang, Q. Zhao, X. Wang, and Q. Zhou, “Sub-pixel chessboard corner localization for camera calibration and pose estimation,” Appl. Sci., vol. 8, no. 11, 2018, doi: 10.3390/app8112118 | spa |
| dc.relation.references | [27] F. errera, “Big Data: Preprocesamiento y calidad de datos,” Novática, no. 237, p. 17, 2016. | spa |
| dc.relation.references | [28] R. Goyena and A. . Fallis, Data mining concepts and techniques, vol. 53, no. 9. 2019 | spa |
| dc.relation.references | [29] A. linsky, S. Chen, and . arlow, “The comparative efficacy of imputation methods for missing data in structural equation modeling,” Eur. J. Oper. Res., vol. 151, no. 1, pp. 53–79, 2003, doi: 10.1016/S0377-2217(02)00578-7. | spa |
| dc.relation.references | [30] H. Junninen, H. Niska, K. Tuppurainen, J. Ruuskanen, and M. Kolehmainen, “Methods for imputation of missing values in air quality data sets,” Atmos. Environ., vol. 38, no. 18, pp. 2895–2907, 2004, doi: 10.1016/j.atmosenv.2004.02.026. | spa |
| dc.relation.references | [31] D. Berrar, “Cross-validation,” Encycl. Bioinforma. Comput. Biol. ABC Bioinforma., vol. 1–3, no. April, pp. 542–545, 2018, doi: 10.1016/B978-0-12-809633-8.20349-X. | spa |
| dc.relation.references | [32] T. Hastie, R. Tibshirani, and J. H. Friedman, The Elements of Statistical Learning: Data Mining, Inference, and Prediction. Springer, 2009. | spa |
| dc.relation.references | [33] W. Yang, K. Wang, and W. Zuo, “Neighborhood component feature selection for high-dimensional data,” J. Comput., vol. 7, no. 1, pp. 162–168, 2012, doi: 10.4304/jcp.7.1.161-168 | spa |
| dc.relation.references | [34] H. H. Hsu, C. Y. Chang, and C. H. Hsu, Big Data Analytics for Sensor-Network Collected Intelligence. 2017. | spa |
| dc.relation.references | [35] H. e, Y. Bai, E. A. Garcia, and S. i, “ADASYN: Adaptive synthetic sampling approach for imbalanced learning,” Proc. Int. Jt. Conf. Neural Networks, no. 3, pp. 1322–1328, 2008, doi: 10.1109/IJCNN.2008.4633969 | spa |
| dc.relation.references | [36] W. J. Murdoch, C. Singh, K. Kumbier, R. Abbasi-Asl, and B. Yu, “Definitions, methods, and applications in interpretable machine learning,” Proc. Natl. Acad. Sci. U. S. A., vol. 116, no. 44, pp. 22071–22080, 2019, doi: 10.1073/pnas.1900654116. | spa |
| dc.relation.references | [37] N. K. K, “Naive Bayes : Text Classifier for Spam Detection. - Naveen Kumar K - Medium,” 2019. [ nline]. Available: https://medium.com/@naveeen.kumar.k/naive-bayes-spam-detection-7d087cc96d9d. [Accessed: 03-Jun-2020]. | spa |
| dc.relation.references | [38] . . W. and E. Fran, “ ntroducción a Data Mining,” SAS Train. courses, vol. (2thEd.), no. Dm, p. 34, 2007. | spa |
| dc.relation.references | [39] K. A. Gaurav and L. Patel, Machine Learning With R. 2020. | spa |
| dc.relation.references | [40] “ ow to Bulid a Neural Network in Python | Blog | Dimensionless.” [ nline]. Available: https://dimensionless.in/building-a-neural-network-in-python-language-modeling-task/. [Accessed: 03-Jun-2020]. | spa |
| dc.relation.references | [41] David Kriesel, “A Brief ntoduction to Neural Networks,” Nonlinear Syst. Identif., pp. 239–297, 2001, doi: 10.1007/978-3-662-04323-3_10. | spa |
| dc.relation.references | [42] C. Bircano and T. Çizge, “Yapay Sinir A ˘ glarında Aktivasyon Fonksiyonlarının Kar ¸ sıla ¸ stırılması A Comparison of Activation Functions in Artificial Neural Networks,” 2018 26th Signal Process. Commun. Appl. Conf., pp. 1–4. | spa |
| dc.relation.references | [43] P. Marius-Constantin, V. E. Balas, L. Perescu-Popescu, and N. Mastorakis, “Multilayer perceptron and neural networks,” WSEAS Trans. Circuits Syst., vol. 8, no. 7, pp. 579–588, 2009. | spa |
| dc.relation.references | [44] M. N. Noor, A. S. Yahaya, N. A. Ramli, and A. M. M. Al Bakri, “Filling missing data using interpolation methods: Study on the effect of fitting distribution,” Key Eng. Mater., vol. 594–595, pp. 889–895, 2014, doi: 10.4028/www.scientific.net/KEM.594-595.889. | spa |
| dc.rights.accessrights | info:eu-repo/semantics/openAccess | spa |
| dc.rights.accessrights | http://purl.org/coar/access_right/c_abf2 | spa |
| dc.rights.creativecommons | Atribución-NoComercial-SinDerivadas 2.5 Colombia | * |
| dc.rights.local | Abierto (Texto Completo) | spa |
| dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/2.5/co/ | * |
| dc.subject.keywords | Energy engineering | eng |
| dc.subject.keywords | Technological innovations | eng |
| dc.subject.keywords | Energy | eng |
| dc.subject.keywords | Neural networks | eng |
| dc.subject.keywords | Decision tree | eng |
| dc.subject.keywords | Artificial intelligence | eng |
| dc.subject.keywords | Flexible computing | eng |
| dc.subject.keywords | Grid-connected system | eng |
| dc.subject.lemb | Ingeniería en energía | spa |
| dc.subject.lemb | Innovaciones tecnológicas | spa |
| dc.subject.lemb | Energía | spa |
| dc.subject.lemb | Inteligencia artificial | spa |
| dc.subject.lemb | Computación flexible | spa |
| dc.subject.proposal | Redes neuronales | spa |
| dc.subject.proposal | Árbol de decisión | spa |
| dc.subject.proposal | Grid tie | spa |
| dc.subject.proposal | Sistema fotovoltaico conectado a la red | spa |
| dc.title | Herramienta para el diseño de sistemas solares fotovoltaicos basada en redes neuronales artificiales (RNA) para determinar la configuración, selección de equipos y arreglos fotovoltaicos en Colombia | spa |
| dc.title.translated | Tool for the design of photovoltaic solar systems based on artificial neural networks (ANN) to determine the configuration, selection of equipment and photovoltaic arrangements in Colombia | spa |
| dc.type.coar | http://purl.org/coar/resource_type/c_7a1f | |
| dc.type.driver | info:eu-repo/semantics/bachelorThesis | |
| dc.type.hasversion | info:eu-repo/semantics/acceptedVersion | |
| dc.type.local | Trabajo de Grado | spa |
| dc.type.redcol | http://purl.org/redcol/resource_type/TP |
Archivos
Bloque de licencias
1 - 1 de 1
Cargando...
- Nombre:
- license.txt
- Tamaño:
- 1.71 KB
- Formato:
- Item-specific license agreed upon to submission
- Descripción:
