Physics-informed neural networks-based optimization for gas-powered energy systems

dc.contributor.advisorÁlvarez Meza, Andrés Marino
dc.contributor.advisorCastellanos Domínguez, César Germán
dc.contributor.authorPérez Rosero, Diego Armando
dc.contributor.cvlacPérez Rosero, Diego Armando [https://scienti.minciencias.gov.co/cvlac/visualizador/generarCurriculoCv.do?cod_rh=0001779699]spa
dc.contributor.googlescholarPérez Rosero, Diego Armando [https://scholar.google.com/citations?user=IF9Bxe0AAAAJ&hl=es&oi=ao]spa
dc.contributor.orcidPérez Rosero, Diego Armando [0000-0001-9258-7088]spa
dc.contributor.researchgroupGrupo de Control y Procesamiento Digital de Señalesspa
dc.date.accessioned2024-10-29T16:40:24Z
dc.date.available2024-10-29T16:40:24Z
dc.date.issued2024
dc.descriptiongraficas, tablasspa
dc.description.abstractLa transición global hacia un paradigma energético sostenible destaca tanto la persistencia de los combustibles fósiles como el auge de las fuentes de energía renovable. En este contexto, la adopción de tecnologías basadas en turbinas de gas surge como una opción viable que minimiza el impacto ambiental al reducir las emisiones y los costos operativos. Aunque se espera que la demanda de combustibles fósiles para la generación de electricidad aumente hasta 2030, paralelamente a este evento, se prevé una inversión considerable en energía renovable, especialmente en los sectores solar y eólico. América Latina, con una notable capacidad hidroeléctrica de 340,332 MW, está a la vanguardia de los esfuerzos de mitigación de emisiones de carbono. Sin embargo, la región enfrenta desafíos, incluida la dependencia de combustibles importados y la fragilidad de su infraestructura energética. En Colombia, la variabilidad climática impulsa la diversificación energética. La Comisión de Regulación de Energía y Gas (CREG) tiene como objetivo optimizar el transporte de gas, consciente de la limitación temporal de las reservas actuales, estimadas en solo siete años. El modelo lineal utilizado tradicionalmente por CREG, aunque efectivo para ciertos propósitos, no considera factores críticos como las variaciones de presión y el papel de las estaciones de compresión, revelando la necesidad de un modelo de optimización no lineal (NOPT). Sin embargo, los desafíos de NOPT incluyen la gestión de datos variables y mediciones ruidosas, lo que puede llevar a soluciones erróneas o subóptimas. Este documento presenta un nuevo enfoque: la Red Neuronal Informada por la Física Regularizada (RPINN), diseñada para abordar tanto tareas de optimización supervisada como no supervisada. RPINN combina funciones de activación personalizadas y penalizaciones de regularización dentro de una arquitectura de red neuronal artificial (ANN), lo que le permite manejar la variabilidad de los datos y entradas inexactas. Incorpora principios físicos en el diseño de la red, calculando variables de optimización a partir de los pesos de la red y las características aprendidas. Además, emplea técnicas de diferenciación automática para optimizar la escalabilidad del sistema y reducir el tiempo de cálculo mediante la retropropagación por lotes. Los resultados experimentales demuestran que RPINNes competitivo con los solucionadores de última generación para tareas de optimización supervisada y no supervisada, mostrando robustez frente a mediciones ruidosas. Este avance lo posiciona como una solución prometedora para entornos con información fluctuante, como se evidencia en los modelos de mezcla uniforme y sistemas alimentados por gas. La base ANN de RPINN no solo asegura flexibilidad y escalabilidad, sino que también destaca su potencial como una metodología robusta y efectiva en comparación con la tradicional (Texto tomado de la fuente)spa
dc.description.abstractThe global transition towards a sustainable energy paradigm highlights both the persistence of fossil fuels and the rise of renewable energy sources. In this context, the adoption of gas turbine-based technologies emerges as a viable option that minimizes environmental impact by reducing emissions and operational costs. While the demand for fossil fuels for electricity generation is expected to increase until 2030, parallel to this event a considerable investment in renewable energy, especially in the solar and wind sectors, is expected. Latin America, with a notable hydroelectric capacity of 340,332 MW, is at the forefront of carbon emission mitigation efforts. However, the region faces challenges, including dependence on imported fuels and the fragility of its energy infrastructure. In Colombia, climatic variability drives energy diversification. The Energy and Gas Regulatory Commission (CREG) aims to optimize gas transportation, aware of the temporary limitation of current reserves, estimated at only seven years. The linear model traditionally used by CREG, though effective for certain purposes, does not consider critical factors such as pressure variations and the role of compression stations, revealing the need for a nonlinear optimization (NOPT}) model. However, NOPT challenges include managing variable data and noisy measurements, which can lead to erroneous or suboptimal solutions. This document presents a new approach: the Regularized Physics-Informed Neural Network (RPINN), designed to address both supervised and unsupervised optimization tasks.RPINNcombines custom activation functions and regularization penalties within an artificial neural network (ANN) architecture, enabling it to handle data variability and inaccurate inputs. It incorporates physical principles into the network design, calculating optimization variables from network weights and learned features. Additionally, it employs automatic differentiation techniques to optimize system scalability and reduce computation time through batch-based backpropagation. Experimental results demonstrate that RPINNis competitive with state-of-the-art solvers for both supervised and unsupervised optimization tasks, exhibiting robustness against noisy measurements. This advancement positions it as a promising solution for environments with fluctuating information, as evidenced in uniform mixture models and gas-fed systems. The ANN foundation of RPINN not only ensures flexibility and scalability but also highlights its potential as a robust and effective methodology when compared to traditional approaches.eng
dc.description.degreelevelMaestríaspa
dc.description.degreenameMagíster en Ingeniería - Automatización Industrialspa
dc.description.researchareaInteligencia Artificialspa
dc.description.sponsorshipDesarrollo de una herramienta para la planeación a largo plazo de la operación del sistema de transporte de gas natural de Colombia’", soportado por MINCIENCIAS (Code 111085269982).spa
dc.format.extentxiii, 94 páginasspa
dc.format.mimetypeapplication/pdfspa
dc.identifier.instnameUniversidad Nacional de Colombiaspa
dc.identifier.reponameRepositorio Institucional Universidad Nacional de Colombiaspa
dc.identifier.repourlhttps://repositorio.unal.edu.co/spa
dc.identifier.urihttps://repositorio.unal.edu.co/handle/unal/87099
dc.language.isoengspa
dc.publisherUniversidad Nacional de Colombiaspa
dc.publisher.branchUniversidad Nacional de Colombia - Sede Manizalesspa
dc.publisher.facultyFacultad de Ingeniería y Arquitecturaspa
dc.publisher.placeManizales, Colombiaspa
dc.publisher.programManizales - Ingeniería y Arquitectura - Maestría en Ingeniería - Automatización Industrialspa
dc.relation.references[CRE, 2023] , 2023; Creg; https://creg.gov.co/; Último acceso en 2024.spa
dc.relation.references[Cor, 2023] , 2023; Actualidad del sector energético colom- biano; https://investigaciones.corficolombiana.com/ analisis-sectorial-y-sostenibilidad/perspectiva-sectorial-energia/ actualidad-del-sector-energetico-colombiano/informe_1290865; Último acceso en 2024.spa
dc.relation.references[Ene, 2023] , 2023; Cómo se genera la electricidad; https://www.enel.com.co/es/ empresas/enel-generacion/como-se-genera-la-electricidad.html; Último ac- ceso en 2024.spa
dc.relation.references[REA, 2023] , 2023; Renewable energy association; https://www.r-e-a.net; Último acceso en 2024.spa
dc.relation.references[Uni, 2023] , 2023; Colombia puede liderar la transición energética que ex- ige el planeta; https://uniandes.edu.co/es/noticias/ingenieria/ colombia-puede-liderar-la-transicion-energetica-que-exige-el-planeta; Último acceso en 2024.spa
dc.relation.references[FIC, 2024] , 2024; Xpress optimization; https://www.fico.com/en/products/ fico-xpress-optimization; Último acceso en 2024.spa
dc.relation.references[Gur, 2024] , 2024; Gurobi optimization; https://www.gurobi.com/; Último acceso en 2024.spa
dc.relation.references[Ipo, 2024] , 2024; Ipopt deprecated features; https://coin-or.github.io/Ipopt/ deprecated.html; Último acceso en 2024.spa
dc.relation.references[Mos, 2024] , 2024; Mosek; https://www.mosek.com/; Último acceso en 2024.spa
dc.relation.references[Ab Wahab et al., 2020] Ab Wahab, M. N.; Nefti-Meziani, S. & Atyabi, A.: , 2020; A comparative review on mobile robot path planning: Classical or meta-heuristic methods?; Annual Reviews in Control ; 50: 233–252.spa
dc.relation.references[Abubakar & Kumam, 2019] Abubakar, A. B. & Kumam, P.: , 2019; A descent dai- liao conjugate gradient method for nonlinear equations; Numerical Algorithms; 81: 197–210.spa
dc.relation.references[Agrawal & Boyd, 2020] Agrawal, A. & Boyd, S.: , 2020; Disciplined quasiconvex pro- gramming; Optimization Letters; to appear.spa
dc.relation.references[Agrawal et al., 2019] Agrawal, A.; Amos, B.; Barratt, S.; Boyd, S.; Diamond, S. & Kolter, J. Z.: , 2019; Differentiable convex optimization layers; Advances in neural information processing systems; 32.spa
dc.relation.references[Andrei et al., 2020] Andrei, N. et al.: , 2020; Nonlinear conjugate gradient methods for unconstrained optimization; Springer.spa
dc.relation.references[ANH, 2022] ANH: , 2022; Informe de reservas y recursos contingentes de hidrocar- buros 2022; https://www.anh.gov.co/documents/21617/Informe_de_Reservas_ _y_Recursos_Contingentes_de_Hidrocarburos_2022_pfMyhzQ.pdf; Último acceso en 2024.spa
dc.relation.references[Applegate et al., 2021] Applegate, D.; Diaz, M.; Hinder, O.; Lu, H.; Lubin, M.; O' Donoghue, B. & Schudy, W.: , 2021; Practical large-scale linear pro- gramming using primal-dual hybrid gradient; en Advances in Neural Information Processing Systems, tomo 34 (Editado por Ranzato, M.; Beygelzimer, A.; Dauphin, Y.; Liang, P. & Vaughan, J. W.); Curran Associates, Inc.; págs. 20243–20257; URL https://proceedings.neurips.cc/paper_files/paper/2021/ file/a8fbbd3b11424ce032ba813493d95ad7-Paper.pdf.spa
dc.relation.references[Arya, 2022] Arya, A. K.: , 2022; A critical review on optimization parameters and techniques for gas pipeline operation profitability; Journal of Petroleum Exploration and Production Technology; 12 (11): 3033–3057.spa
dc.relation.references[Arya et al., 2022] Arya, A. K.; Jain, R.; Yadav, S.; Bisht, S. & Gautam, S.: , 2022; Recent trends in gas pipeline optimization; Materials Today: Proceedings; 57: 1455–1461.spa
dc.relation.references[Asgharieh Ahari & Kocuk, 2023] Asgharieh Ahari, S. & Kocuk, B.: , 2023; A mixed- integer exponential cone programming formulation for feature subset selection in logistic regression; EURO Journal on Computational Optimization; 11: 100069; doi: https://doi.org/10.1016/j.ejco.2023.100069; URL https://www.sciencedirect.com/ science/article/pii/S2192440623000138.spa
dc.relation.references[Attari & Torkayesh, 2018] Attari, M. Y. N. & Torkayesh, A. E.: , 2018; Developing benders decomposition algorithm for a green supply chain network of mine industry: Case of iranian mine industry; Operations Research Perspectives; 5: 371–382.spa
dc.relation.references[Awwal et al., 2019] Awwal, A. M.; Kumam, P. & Abubakar, A. B.: , 2019; A modified conjugate gradient method for monotone nonlinear equations with convex constraints; Applied Numerical Mathematics; 145: 507–520.spa
dc.relation.references[Azad et al., 2020] Azad, A. S.; Rahaman, M. S. A.; Watada, J.; Vasant, P. & Vintaned, J. A. G.: , 2020; Optimization of the hydropower energy generation using meta-heuristic approaches: A review; Energy Reports; 6: 2230–2248.spa
dc.relation.references[Bahrami & Mohammadi, 2019] Bahrami, S. & Mohammadi, A.: , 2019; Smart micro- grids; Springer.spa
dc.relation.references[Baker, 2020] Baker, K.: , 2020; A learning-boosted quasi-newton method for ac optimal power flow; arXiv preprint arXiv:2007.06074.spa
dc.relation.references[Bayat & Bagheri, 2019] Bayat, A. & Bagheri, A.: , 2019; Optimal active and reactive power allocation in distribution networks using a novel heuristic approach; Applied Energy; 233: 71–85.spa
dc.relation.references[Baydin et al., 2018] Baydin, A. G.; Pearlmutter, B. A.; Radul, A. A. & Siskind, J. M.: , 2018; Automatic differentiation in machine learning: a survey; Journal of Marchine Learning Research; 18: 1–43.spa
dc.relation.references[Beal et al., 2018] Beal, L.; Hill, D.; Martin, R. & Hedengren, J.: , 2018; Gekko optimization suite; Processes; 6 (8): 106; doi:10.3390/pr6080106.spa
dc.relation.references[Beyza et al., 2020] Beyza, J.; Bravo, V. M.; Garcia-Paricio, E.; Yusta, J. M. & Artal-Sevil, J. S.: , 2020; Vulnerability and resilience assessment of power systems: From deterioration to recovery via a topological model based on graph theory; en 2020 IEEE International Autumn Meeting on Power, Electronics and Computing (ROPEC), tomo 4; págs. 1–6; doi:10.1109/ROPEC50909.2020.9258709.spa
dc.relation.references[Bolte & Pauwels, 2021] Bolte, J. & Pauwels, E.: , 2021; Conservative set valued fields, automatic differentiation, stochastic gradient methods and deep learning; Mathematical Programming; 188: 19–51.spa
dc.relation.references[Böttcher et al., 2023] Böttcher, L.; Wolf, H.; Jung, B.; Lutat, P.; Trageser, M.; Pohl, O.; Tao, X.; Ulbig, A. & Grohe, M.: , 2023; Solving ac power flow with graph neural networks under realistic constraints; en 2023 IEEE Belgrade PowerTech; IEEE; págs. 1–7.spa
dc.relation.references[Buitrago-Villada et al., 2021] Buitrago-Villada, M. d. P.; García-Marín, S.; Zuluaga- Orozco, J. E. & Murillo-Sánchez, C. E.: , 2021; On the importance of using an ac or dc network model in the multi-period secure stochastic optimal power flow for settling a multidimensional day-ahead market; IEEE Latin America Transactions; 19 (12): 2003–2010; doi:10.1109/TLA.2021.9480141.spa
dc.relation.references[Casacio et al., 2019] Casacio, L.; Lyra, C. & Oliveira, A. R.: , 2019; Interior point methods for power flow optimization with security constraints; International Transac- tions in Operational Research; 26 (1): 364–378.spa
dc.relation.references[CEOWORLD, 2022] CEOWORLD: , 2022; The power of optimization; https:// ceoworld.biz/2022/12/05/the-power-of-optimization/; Último acceso en 2024.spa
dc.relation.references[Chang et al., 2022] Chang, H.; Chen, Q.; Lin, R.; Shi, Y.; Xie, L. & Su, H.: , 2022; Controlling pressure of gas pipeline network based on mixed proximal policy optimization; en 2022 China Automation Congress (CAC); IEEE; págs. 4642–4647.spa
dc.relation.references[Chen et al., 2020a] Chen, C.; Liu, S.; Lin, Z.; Yang, L.; Wu, X.; Qiu, W.; Gao, Q.; Zhu, T.; Xing, F. & Zhang, J.: , 2020a; Optimal coordinative operation strategy of the electric–thermal–gas integrated energy system considering csp plant; IET Energy Systems Integration; 2 (3): 187–195.spa
dc.relation.references[Chen et al., 2021] Chen, J.; Wang, L.; Wang, C.; Yao, B.; Tian, Y. & Wu, Y.-S.: , 2021; Automatic fracture optimization for shale gas reservoirs based on gradient descent method and reservoir simulation; Advances in Geo-Energy Research; 5 (2): 191–201.spa
dc.relation.references[Chen et al., 2022] Chen, M.; Lu, H. & Zheng, C.: , 2022; An integrated energy system optimization model coupled with power-to-gas and carbon capture; en 2022 Interna- tional Conference on Renewable Energies and Smart Technologies (REST), tomo 1; IEEE; págs. 1–5.spa
dc.relation.references[Chen et al., 2020b] Chen, Q.; Zuo, L.; Wu, C.; Bu, Y.; Lu, Y.; Huang, Y. & Chen, F.: , 2020b; Short-term supply reliability assessment of a gas pipeline system under demand variations; Reliability Engineering & System Safety; 202: 107004.spa
dc.relation.references[Chen et al., 2023] Chen, T.-C.; Alvarez, J. R. N.; Dwijendra, N. K. A.; Kadhim, Z. J.; Alayi, R.; Kumar, R.; PraveenKumar, S. & Velkin, V. I.: , 2023; Modeling and optimization of combined heating, power, and gas production system based on renewable energies; Sustainability; 15 (10): 7888.spa
dc.relation.references[Chevalier & Chatzivasileiadis, 2023] Chevalier, S. & Chatzivasileiadis, S.: , 2023; Global performance guarantees for neural network models of ac power flowspa
dc.relation.references[Chowdhury & Kamalasadan, 2021] Chowdhury, M. M.-U.-T. & Kamalasadan, S.: , 2021; A new second-order cone programming model for voltage control of power distribution system with inverter-based distributed generation; IEEE Transactions on Industry Applications; 57 (6): 6559–6567.spa
dc.relation.references[Cotter et al., 2019] Cotter, A.; Jiang, H.; Gupta, M.; Wang, S.; Narayan, T.; You, S. & Sridharan, K.: , 2019; Optimization with non-differentiable constraints with applications to fairness, recall, churn, and other goals; Journal of Machine Learning Research; 20 (172): 1–59.spa
dc.relation.references[CREG, 2022a] CREG: , 2022a; Anexo 7; https://gestornormativo. creg.gov.co/Publicac.nsf/52188526a7290f8505256eee0072eba7/ efe89a093559fe0b052589b9007d308b/$FILE/Anexo7.pdf; Último acceso en 2024.spa
dc.relation.references[CREG, 2022b] CREG: , 2022b; Regulación de la creg sobre energías renovables comprende seis grandes temas; https://creg.gov.co/publicaciones/8625/regulacion-de-la-creg-sobre-energias-renovables-comprende-seis-grandes-temas/; Último acceso en 2024.spa
dc.relation.references[CREG, 2022c] CREG: , 2022c; Reglamento Único de la comisión de regulación de energía y gas (creg); https://gestornormativo.creg.gov.co/gestor/entorno/docs/ru_ creg_gn.htm; Último acceso en 2024.spa
dc.relation.references[Delgado et al., 2022] Delgado, J. A.; Baptista, E. C.; Balbo, A. R.; Soler, E. M.; Silva, D. N.; Martins, A. C. & Nepomuceno, L.: , 2022; A primal–dual penalty- interior-point method for solving the reactive optimal power flow problem with discrete control variables; International Journal of Electrical Power & Energy Systems; 138: 107917.spa
dc.relation.references[Diamond & Boyd, 2016] Diamond, S. & Boyd, S.: , 2016; CVXPY: A Python-embedded modeling language for convex optimization; Journal of Machine Learning Research; 17 (83): 1–5spa
dc.relation.references[Diehl, 2019] Diehl, F.: , 2019; Warm-starting ac optimal power flow with graph neural networks; en 33rd Conference on Neural Information Processing Systems (NeurIPS 2019); págs. 1–6.spa
dc.relation.references[EIA, 2022] EIA: , 2022; Natural gas explained; https://www.eia.gov/energyexplained/ natural-gas/; Último acceso en 2024.spa
dc.relation.references[Eleftheriadis et al., 2023] Eleftheriadis, P.; Leva, S. & Ogliari, E.: , 2023; Bayesian hyperparameter optimization of stacked bidirectional long short-term memory neural network for the state of charge estimation; Sustainable Energy, Grids and Networks; 36: 101160.spa
dc.relation.references[Energy Master, 2023] Energy Master: , 2023; Consumo de energía; https:// energymaster.co/consumo-de-energia-2/; Último acceso en 2024.spa
dc.relation.references[Energy5, 2024] Energy5: , 2024; Optimización de las redes de gasoductos de gas natural para mejorar la gestión de la cadena de suministro; https://energy5.com/es/ optimizacion-de-las-redes-de-gasoductos-de-gas-natural-para-mejorar-la-gestion-de- Último acceso en 2024.spa
dc.relation.references[Falconer & Mones, 2022] Falconer, T. & Mones, L.: , 2022; Leveraging power grid topology in machine learning assisted optimal power flow; IEEE Transactions on Power Systems; 38 (3): 2234–2246.spa
dc.relation.references[Falconer & Mones, 2023] Falconer, T. & Mones, L.: , 2023; Leveraging power grid topology in machine learning assisted optimal power flow; IEEE Transactions on Power Systems; 38 (3): 2234–2246; doi:10.1109/TPWRS.2022.3187218.spa
dc.relation.references[Fallahi & Maghouli, 2020] Fallahi, F. & Maghouli, P.: , 2020; Integrated unit com- mitment and natural gas network operational planning under renewable generation uncertainty; International Journal of Electrical Power & Energy Systems; 117: 105647.spa
dc.relation.references[Falsone et al., 2020] Falsone, A.; Notarnicola, I.; Notarstefano, G. & Prandini, M.: , 2020; Tracking-admm for distributed constraint-coupled optimization; Automatica; 117: 108962.spa
dc.relation.references[Fan et al., 2023] Fan, Y.; Chen, Y. & Cui, M.: , 2023; Electric-hydrogen integrated energy system optimization considering ladder-type carbon trading mechanism and user-side flexible load; en 2023 IEEE 6th International Electrical and Energy Conference (CIEEC); IEEE; págs. 1780–1784.spa
dc.relation.references[Farrokhifar et al., 2020] Farrokhifar, M.; Nie, Y. & Pozo, D.: , 2020; Energy sys- tems planning: A survey on models for integrated power and natural gas networks coordination; Applied Energy; 262: 114567.spa
dc.relation.references[Füllner & Rebennack, 2022] Füllner, C. & Rebennack, S.: , 2022; Non-convex nested benders decomposition; Mathematical Programming; 196 (1-2): 987–1024.spa
dc.relation.references[Gao et al., 2022] Gao, G.; Wang, Y.; Vink, J. C.; Wells, T. J. & Saaf, F. J.: , 2022; Distributed quasi-newton derivative-free optimization method for optimization problems with multiple local optima; Computational Geosciences; 26 (4): 847–863.spa
dc.relation.references[Gao & Li, 2021] Gao, H. & Li, Z.: , 2021; A benders decomposition based algorithm for steady-state dispatch problem in an integrated electricity-gas system; IEEE Transac- tions on Power Systems; 36 (4): 3817–3820.spa
dc.relation.references[Gao et al., 2019] Gao, S.; Yu, Y.; Wang, Y.; Wang, J.; Cheng, J. & Zhou, M.: , 2019; Chaotic local search-based differential evolution algorithms for optimization; IEEE Transactions on Systems, Man, and Cybernetics: Systems; 51 (6): 3954–3967.spa
dc.relation.references[García-Marín et al., 2019] García-Marín, S.; González-Vanegas, W. & Murillo- Sánchez, C.: , 2019; MPNG: MATPOWER-Natural Gas; https://github.com/ MATPOWER/mpng; [Online; accessed (fecha de acceso)].spa
dc.relation.references[García-Marín et al., 2022] García-Marín, S.; González-Vanegas, W. & Murillo- Sánchez, C.: , 2022; Mpng: A matpower-based tool for optimal power and natural gas flow analyses; IEEE Transactions on Power Systems: 1–9; doi:10.1109/TPWRS. 2022.3195684.spa
dc.relation.references[Gholizadeh et al., 2020] Gholizadeh, S.; Danesh, M. & Gheyratmand, C.: , 2020; A new newton metaheuristic algorithm for discrete performance-based design optimization of steel moment frames; Computers & Structures; 234: 106250.spa
dc.relation.references[González et al., 2021] González, A. B. P.; Silva, B. D. J. & Macia, Y. M.: , 2021; Transición energética en américa latina y el caribe: diálogos inter y transdisciplinarios en tiempos de pandemia por covid-19; Revista LIDER: 33–61.spa
dc.relation.references[Gonzalez & Peña-Vinces, 2023] Gonzalez, C. C. & Peña-Vinces, J.: , 2023; A frame- work for a green accounting system-exploratory study in a developing country context, colombia; Environment, Development and Sustainability; 25 (9): 9517–9541.spa
dc.relation.references[González-Vanegas et al., 2019] González-Vanegas, W.; Álvarez Meza, A.; Hernández-Muriel, J. & Orozco-Gutiérrez, : , 2019; Akl-abc: An automatic ap- proximate bayesian computation approach based on kernel learning; Entropy; 21 (10); doi:10.3390/e21100932; URL https://www.mdpi.com/1099-4300/21/10/932.spa
dc.relation.references[Goulart & Chen, 2024] Goulart, P. & Chen, Y.: , 2024; Clarabel documentation; https: //oxfordcontrol.github.io/ClarabelDocs/stable/; Último acceso en 2024.spa
dc.relation.references[Greyson, 2021] Greyson, K. A.: , 2021; Vehicles power consumption measurements: Case study of dart in tanzania; en 2021 IEEE AFRICON ; págs. 1–7; doi:10.1109/ AFRICON51333.2021.9570955.spa
dc.relation.references[Habib & Yildirim, 2022] Habib, A. & Yildirim, U.: , 2022; Developing a physics-informed and physics-penalized neural network model for preliminary design of multi-stage friction pendulum bearings; Engineering Applications of Artificial Intelligence; 113: 104953.spa
dc.relation.references[Haghighat et al., 2021] Haghighat, E.; Raissi, M.; Moure, A.; Gomez, H. & Juanes, R.: , 2021; A physics-informed deep learning framework for inversion and surro- gate modeling in solid mechanics; Computer Methods in Applied Mechanics and Engineering; 379: 113741; doi:https://doi.org/10.1016/j.cma.2021.113741; URL https://www.sciencedirect.com/science/article/pii/S0045782521000773.spa
dc.relation.references[Haji & Abdulazeez, 2021] Haji, S. H. & Abdulazeez, A. M.: , 2021; Comparison of optimization techniques based on gradient descent algorithm: A review; PalArch’s Journal of Archaeology of Egypt/Egyptology; 18 (4): 2715–2743.spa
dc.relation.references[Han et al., 2024] Han, M.; Du, Z.; Yuen, K. F.; Zhu, H.; Li, Y. & Yuan, Q.: , 2024; Walrus optimizer: A novel nature-inspired metaheuristic algorithm; Expert Systems with Applications; 239: 122413.spa
dc.relation.references[Harrington, 2018] Harrington, K. R.: , 2018; Panorama actual sobre eficiencia energética en américa latina; Revista VIRTUALPRO; 200.spa
dc.relation.references[Hasanzadeh et al., 2021] Hasanzadeh, A.; Chitsaz, A.; Mojaver, P. & Ghasemi, A.: , 2021; Stand-alone gas turbine and hybrid mcfc and sofc-gas turbine systems: Comparative life cycle cost, environmental, and energy assessments; Energy Reports; 7: 4659–4680.spa
dc.relation.references[Heipcke & Colombani, 2020] Heipcke, S. & Colombani, Y.: , 2020; Xpress mosel: Mod- eling and programming features for optimization projects; en Operations Research Proceedings 2019: Selected Papers of the Annual International Conference of the Ger- man Operations Research Society (GOR), Dresden, Germany, September 4-6, 2019 ; Springer; págs. 677–683.spa
dc.relation.references[Hu & Jiang, 2024] Hu, J. & Jiang, Y.: , 2024; Accelerating benders decomposition approach for shared parking spaces allocation considering parking unpunctuality and no-shows; Expert Systems with Applications; 240: 122346.spa
dc.relation.references[Hu & Zhang, 2023] Hu, Z. & Zhang, H.: , 2023; Optimal power flow based on physical- model-integrated neural network with worth-learning data generation.spa
dc.relation.references[Huang & Wang, 2023] Huang, B. & Wang, J.: , 2023; Applications of physics-informed neural networks in power systems - a review; IEEE Transactions on Power Systems; 38 (1): 572–588; doi:10.1109/TPWRS.2022.3162473.spa
dc.relation.references[Huang et al., 2023] Huang, W.; Zhang, X.; Cheng, H.; Xie, J. et al.: , 2023; Metamodel-based optimization method for traffic network signal design under stochastic demand; Journal of Advanced Transportation; 2023spa
dc.relation.references[Ibrahim & Hossain, 2021] Ibrahim, I. A. & Hossain, M. J.: , 2021; Low voltage distri- bution networks modeling and unbalanced (optimal) power flow: A comprehensive review; IEEE Access; 9: 143026–143084.spa
dc.relation.references[Impacto TIC, 2023] Impacto TIC: , 2023; Energías renovables en colombia: Situación, retos y proyectos; https://impactotic.co/innovacion/sostenibilidad/ energias-renovables-en-colombia-situacion-retos-y-proyectos/; Último ac- ceso en 2024.spa
dc.relation.references[International Energy Agency (IEA), 2022] International Energy Agency (IEA): , 2022; World energy investment 2022; https://www.iea.org/reports/ world-energy-investment-2022; license: CC BY 4.0.spa
dc.relation.references[International Energy Agency (IEA), 2023] International Energy Agency (IEA): , 2023; Global energy and climate model; https://www.iea.org/reports/ global-energy-and-climate-model; license: CC BY 4.0.spa
dc.relation.references[Jakovetić et al., 2020] Jakovetić, D.; Bajović, D.; Xavier, J. & Moura, J. M.: , 2020; Primal–dual methods for large-scale and distributed convex optimization and data analytics; Proceedings of the IEEE ; 108 (11): 1923–1938.spa
dc.relation.references[Jamii et al., 2022] Jamii, J.; Trabelsi, M.; Mansouri, M.; Mimouni, M. F. & Shatanawi, W.: , 2022; Non-linear programming-based energy management for a wind farm coupled with pumped hydro storage system; Sustainability; 14 (18); doi:10.3390/su141811287; URL https://www.mdpi.com/2071-1050/14/18/11287.spa
dc.relation.references[Jeon & Van Roy, 2022] Jeon, H. J. & Van Roy, B.: , 2022; An information-theoretic framework for deep learning; Advances in Neural Information Processing Systems; 35: 3279–3291.spa
dc.relation.references[Kardoš et al., 2022] Kardoš, J.; Kourounis, D.; Schenk, O. & Zimmerman, R.: , 2022; Beltistos: A robust interior point method for large-scale optimal power flow problems; Electric Power Systems Research; 212: 108613.spa
dc.relation.references[Karimi et al., 2019] Karimi, M.; Shahriari, A.; Aghamohammadi, M.; Marzooghi, H. & Terzija, V.: , 2019; Application of newton-based load flow methods for determining steady-state condition of well and ill-conditioned power systems: A review; International Journal of Electrical Power & Energy Systems; 113: 298–309.spa
dc.relation.references[Khan et al., 2020] Khan, I. U.; Javaid, N.; Gamage, K. A.; Taylor, C. J.; Baig, S. & Ma, X.: , 2020; Heuristic algorithm based optimal power flow model incorporating stochastic renewable energy sources; IEEE Access; 8: 148622–148643.spa
dc.relation.references[KILIÇARSLAN et al., 2021] KILIÇARSLAN, S.; Kemal, A. & Çelik, M.: , 2021; An overview of the activation functions used in deep learning algorithms; Journal of New Results in Science; 10 (3): 75–88.spa
dc.relation.references[Kim et al., 2023] Kim, H. et al.: , 2023; Self-supervised equality embedded deep lagrange dual for approximate constrained optimization; arXiv preprint arXiv:2306.06674.spa
dc.relation.references[Klatzer et al., 2022] Klatzer, T.; Bachhiesl, U. & Wogrin, S.: , 2022; State-of-the-art expansion planning of integrated power, natural gas, and hydrogen systems; Interna- tional Journal of Hydrogen Energy; 47 (47): 20585–20603.spa
dc.relation.references[Kohjitani et al., 2022] Kohjitani, H.; Koda, S.; Himeno, Y.; Makiyama, T.; Ya- mamoto, Y.; Yoshinaga, D.; Wuriyanghai, Y.; Kashiwa, A.; Toyoda, F.; Zhang, Y. et al.: , 2022; Gradient-based parameter optimization method to determine membrane ionic current composition in human induced pluripotent stem cell-derived cardiomyocytes; Scientific Reports; 12 (1): 19110.spa
dc.relation.references[Koksal & Aydin, 2023] Koksal, E. S. & Aydin, E.: , 2023; Physics informed piecewise linear neural networks for process optimization; Computers Chemical Engineering; 174: 108244; doi:https://doi.org/10.1016/j.compchemeng.2023.108244; URL https: //www.sciencedirect.com/science/article/pii/S009813542300114X.spa
dc.relation.references[Kuhns & Shaw, 2018] Kuhns, R. J. & Shaw, G. H.: , 2018; Coal and Natural Gas; Springer International Publishing, Cham; ISBN 978-3-319-22783-2; págs. 65–69; doi:10. 1007/978-3-319-22783-2_8; URL https://doi.org/10.1007/978-3-319-22783-2_ 8.spa
dc.relation.references[Kumar & Rahaman, 2020] Kumar, J. & Rahaman, O.: , 2020; Lower bound limit analysis using power cone programming for solving stability problems in rock mechanics for generalized hoek–brown criterion; Rock Mechanics and Rock Engineering; 53 (7): 3237–3252.spa
dc.relation.references[Laue, 2022] Laue, S.: , 2022; On the equivalence of automatic and symbolic differentiation.spa
dc.relation.references[Lee et al., 2023] Lee, M.; Kim, K. T. & Park, J.: , 2023; A numerically efficient output- only system-identification framework for stochastically forced self-sustained oscillators; arXiv preprint arXiv:2305.02801.spa
dc.relation.references[Leon et al., 2020] Leon, L. M.; Bretas, A. S. & Rivera, S.: , 2020; Quadratically constrained quadratic programming formulation of contingency constrained optimal power flow with photovoltaic generation; Energies; 13 (13): 3310.spa
dc.relation.references[Li et al., 2022] Li, S.; Ding, T.; Jia, W.; Huang, C.; Catalão, J. P. S. & Li, F.: , 2022; A machine learning-based vulnerability analysis for cascading failures of integrated power-gas systems; IEEE Transactions on Power Systems; 37 (3): 2259–2270; doi: 10.1109/TPWRS.2021.3119237.spa
dc.relation.references[Li et al., 2017] Li, X.; Tomasgard, A. & Barton, P. I.: , 2017; Natural gas production network infrastructure development under uncertainty; Optimization and Engineering; 18: 35–62.spa
dc.relation.references[Liang & Zhao, 2023] Liang, H. & Zhao, C.: , 2023; Deepopf-u: A unified deep neural network to solve ac optimal power flow in multiple networks.spa
dc.relation.references[Lin et al., 2022a] Lin, Y.; Zhang, X.; Wang, J.; Shi, D. & Bian, D.: , 2022a; Voltage stability constrained optimal power flow for unbalanced distribution system based on semidefinite programming; Journal of Modern Power Systems and Clean Energy; 10 (6): 1614–1624; doi:10.35833/MPCE.2021.000220.spa
dc.relation.references[Lin et al., 2022b] Lin, Y.; Zhang, X.; Wang, J.; Shi, D. & Bian, D.: , 2022b; Voltage stability constrained optimal power flow for unbalanced distribution system based on semidefinite programming; Journal of Modern Power Systems and Clean Energy; 10 (6): 1614–1624.spa
dc.relation.references[Liu et al., 2021] Liu, B.; Yang, Q.; Zhang, H. & Wu, H.: , 2021; An interior-point solver for ac optimal power flow considering variable impedance-based facts devices; IEEE Access; 9: 154460–154470.spa
dc.relation.references[Lopez-Garcia & Domínguez-Navarro, 2023] Lopez-Garcia, T. B. & Domínguez- Navarro, J. A.: , 2023; Power flow analysis via typed graph neural networks; Engineering Applications of Artificial Intelligence; 117: 105567.spa
dc.relation.references[Ma et al., 2020a] Ma, M.; Fan, L.; Miao, Z.; Zeng, B. & Ghassempour, H.: , 2020a; A sparse convex ac opf solver and convex iteration implementation based on 3-node cycles; Electric Power Systems Research; 180: 106169; doi:https://doi.org/10.1016/ j.epsr.2019.106169; URL https://www.sciencedirect.com/science/article/pii/ S0378779619304882.spa
dc.relation.references[Ma et al., 2020b] Ma, X.; Huang, H.; Wang, Y.; Romano, S.; Erfani, S. & Bailey, J.: , 2020b; Normalized loss functions for deep learning with noisy labels; en International conference on machine learning; PMLR; págs. 6543–6553.spa
dc.relation.references[Mahapatra & Rajan, 2020] Mahapatra, D. & Rajan, V.: , 2020; Multi-task learning with user preferences: Gradient descent with controlled ascent in pareto optimization; en International Conference on Machine Learning; PMLR; págs. 6597–6607.spa
dc.relation.references[Mai & Mortari, 2022] Mai, T. & Mortari, D.: , 2022; Theory of functional connections applied to quadratic and nonlinear programming under equality constraints; Journal of Computational and Applied Mathematics; 406: 113912.spa
dc.relation.references[Mannel & Rund, 2021] Mannel, F. & Rund, A.: , 2021; A hybrid semismooth quasi- newton method for nonsmooth optimal control with pdes; Optimization and Engineer- ing; 22 (4): 2087–2125.spa
dc.relation.references[McKinsey & Company, 2023] McKinsey & Company: , 2023; Global energy perspec- tive 2023; https://www.mckinsey.com/industries/oil-and-gas/our-insights/ global-energy-perspective-2023; accedido el [fecha de acceso].spa
dc.relation.references[Meng et al., 2020a] Meng, L.; Zhang, C.; Ren, Y.; Zhang, B. & Lv, C.: , 2020a; Mixed-integer linear programming and constraint programming formulations for solving distributed flexible job shop scheduling problem; Computers & industrial engineering; 142: 106347.spa
dc.relation.references[Meng et al., 2020b] Meng, Z.; Zhao, Z.; Mei, D. & Zhou, Y.: , 2020b; Numerical differentiation for two-dimensional functions by a fourier extension method; Inverse Problems in Science and Engineering; 28 (1): 126–143.spa
dc.relation.references[Mhanna & Mancarella, 2021] Mhanna, S. & Mancarella, P.: , 2021; An exact sequential linear programming algorithm for the optimal power flow problem; IEEE Transactions on Power Systems; 37 (1): 666–679.spa
dc.relation.references[Ministerio de Minas y Energía, 2020] Ministerio de Minas y Energía: , 2020; Res- olución 40311 de 2020; https://gestornormativo.creg.gov.co/gestor/entorno/ docs/resolucion_minminas_40311_2020.htm; Último acceso en 2024.spa
dc.relation.references[Ministerio de Minas y Energía, 2021] Ministerio de Minas y Energía: , 2021; Res- olución 40279 de 2021; https://gestornormativo.creg.gov.co/gestor/entorno/ docs/resolucion_minminas_40279_2021.htm; Último acceso en 2024.spa
dc.relation.references[Misra, 1908] Misra, D.: , 1908; Mish: A self regularized non-monotonic activation function. arxiv 2019; arXiv preprint arXiv:1908.08681.spa
dc.relation.references[Misyris et al., 2020] Misyris, G. S.; Venzke, A. & Chatzivasileiadis, S.: , 2020; Physics-informed neural networks for power systems; en 2020 IEEE power & energy society general meeting (PESGM); IEEE; págs. 1–5.spa
dc.relation.references[Misyris et al., 2021] Misyris, G. S.; Stiasny, J. & Chatzivasileiadis, S.: , 2021; Captur- ing power system dynamics by physics-informed neural networks and optimization; en 2021 60th IEEE Conference on Decision and Control (CDC); IEEE; págs. 4418–4423.spa
dc.relation.references[Moehle et al., 2017] Moehle, N.; Mattingley, J. & Boyd, S.: , 2017; Embedded convex optimization with cvxpy; url= https://github. com/moehle/cvxpy codegen.spa
dc.relation.references[Mokhtari & Ribeiro, 2020] Mokhtari, A. & Ribeiro, A.: , 2020; Stochastic quasi-newton methods; Proceedings of the IEEE ; 108 (11): 1906–1922.spa
dc.relation.references[Montoya et al., 2020a] Montoya, O.; Gil-González, W.; Hernández, J. C.; Giral- Ramírez, D. A. & Medina-Quesada, A.: , 2020a; A mixed-integer nonlinear programming model for optimal reconfiguration of dc distribution feeders; Energies; 13 (17): 4440.spa
dc.relation.references[Montoya et al., 2020b] Montoya, O. D.; Gil-González, W. & Grisales-Noreña, L.: , 2020b; Relaxed convex model for optimal location and sizing of dgs in dc grids using sequential quadratic programming and random hyperplane approaches; International Journal of Electrical Power & Energy Systems; 115: 105442.spa
dc.relation.references[Mora-Camino & Nunes Cosenza, 2018] Mora-Camino, F. & Nunes Cosenza, C. A.: , 2018; Fuzzy Dual Numbers; Springer International Publishing, Cham; ISBN 978-3-319- 65418-8; págs. 11–16; doi:10.1007/978-3-319-65418-8_3; URL https://doi.org/10. 1007/978-3-319-65418-8_3.spa
dc.relation.references[Mugel et al., 2022] Mugel, S.; Kuchkovsky, C.; Sanchez, E.; Fernandez-Lorenzo, S.; Luis-Hita, J.; Lizaso, E. & Orus, R.: , 2022; Dynamic portfolio optimization with real datasets using quantum processors and quantum-inspired tensor networks; Physical Review Research; 4 (1): 013006.spa
dc.relation.references[Muñoz et al., 2022] Muñoz, P.; Franceschini, E. A.; Levitan, D.; Rodriguez, C. R.; Humana, T. & Perelmuter, G. C.: , 2022; Comparative analysis of cost, emissions and fuel consumption of diesel, natural gas, electric and hydrogen urban buses; Energy Conversion and Management; 257: 115412.spa
dc.relation.references[Murphy, 2022] Murphy, K. P.: , 2022; Probabilistic machine learning: an introduction; MIT press.spa
dc.relation.references[Naderi et al., 2021] Naderi, E.; Pourakbari-Kasmaei, M.; Cerna, F. V. & Lehtonen, M.: , 2021; A novel hybrid self-adaptive heuristic algorithm to handle single-and multi-objective optimal power flow problems; International Journal of Electrical Power & Energy Systems; 125: 106492.spa
dc.relation.references[Nellikkath & Chatzivasileiadis, 2022a] Nellikkath, R. & Chatzivasileiadis, S.: , 2022a; Physics-informed neural networks for ac optimal power flow; Electric Power Systems Research; 212: 108412; doi:https://doi.org/10.1016/j.epsr.2022.108412; URL https: //www.sciencedirect.com/science/article/pii/S0378779622005636.spa
dc.relation.references[Nellikkath & Chatzivasileiadis, 2022b] Nellikkath, R. & Chatzivasileiadis, S.: , 2022b; Minimizing worst-case violations of neural networks; arXiv preprint arXiv:2212.10930.spa
dc.relation.references[Nellikkath & Chatzivasileiadis, 2022c] Nellikkath, R. & Chatzivasileiadis, S.: , 2022c; Physics-informed neural networks for ac optimal power flow; Electric Power Systems Research; 212: 108412.spa
dc.relation.references[Notarnicola & Notarstefano, 2019] Notarnicola, I. & Notarstefano, G.: , 2019; Constraint-coupled distributed optimization: A relaxation and duality approach; IEEE Transactions on Control of Network Systems; 7 (1): 483–492.spa
dc.relation.references[O’Donoghue, 2021] O’Donoghue, B.: , 2021; Operator splitting for a homogeneous em- bedding of the linear complementarity problem; SIAM Journal on Optimization; 31: 1999–2023.spa
dc.relation.references[O’Donoghue et al., 2016] O’Donoghue, B.; Chu, E.; Parikh, N. & Boyd, S.: , 2016; Conic optimization via operator splitting and homogeneous self-dual embed- ding; Journal of Optimization Theory and Applications; 169 (3): 1042–1068; URL http://stanford.edu/~boyd/papers/scs.html.spa
dc.relation.references[Oliva et al., 2019] Oliva, D.; Abd Elaziz, M.; Elsheikh, A. H. & Ewees, A. A.: , 2019; A review on meta-heuristics methods for estimating parameters of solar cells; Journal of Power Sources; 435: 126683.spa
dc.relation.references[Owerko et al., 2020] Owerko, D.; Gama, F. & Ribeiro, A.: , 2020; Optimal power flow using graph neural networks; en ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP); IEEE; págs. 5930–5934.spa
dc.relation.references[Owerko et al., 2022] Owerko, D.; Gama, F. & Ribeiro, A.: , 2022; Unsupervised optimal power flow using graph neural networks; arXiv preprint arXiv:2210.09277.spa
dc.relation.references[Pan et al., 2021] Pan, X.; Zhao, T.; Chen, M. & Zhang, S.: , 2021; Deepopf: A deep neural network approach for security-constrained dc optimal power flow; IEEE Transactions on Power Systems; 36 (3): 1725–1735; doi:10.1109/TPWRS.2020.3026379.spa
dc.relation.references[Pan et al., 2022] Pan, X.; Chen, M.; Zhao, T. & Low, S. H.: , 2022; Deepopf: A feasibility-optimized deep neural network approach for ac optimal power flow problems; IEEE Systems Journal ; 17 (1): 673–683.spa
dc.relation.references[Pan et al., 2023] Pan, X.; Chen, M.; Zhao, T. & Low, S. H.: , 2023; Deepopf: A feasibility-optimized deep neural network approach for ac optimal power flow problems; IEEE Systems Journal ; 17 (1): 673–683; doi:10.1109/JSYST.2022.3201041.spa
dc.relation.references[Park et al., 2023] Park, S.; Chen, W.; Mak, T. W. K. & Hentenryck, P. V.: , 2023; Compact optimization learning for ac optimal power flow.spa
dc.relation.references[Pas et al., 2022] Pas, P.; Schuurmans, M. & Patrinos, P.: , 2022; Alpaqa: A matrix- free solver for nonlinear mpc and large-scale nonconvex optimization; en 2022 European Control Conference (ECC); págs. 417–422; doi:10.23919/ECC55457.2022.9838172.spa
dc.relation.references[Paszke et al., 2017] Paszke, A.; Gross, S.; Chintala, S.; Chanan, G.; Yang, E.; DeVito, Z.; Lin, Z.; Desmaison, A.; Antiga, L. & Lerer, A.: , 2017; Automatic differentiation in pytorch.spa
dc.relation.references[Pérez-Cedeño et al., 2022] Pérez-Cedeño, R. O.; Stanescu, C. L. V. et al.: , 2022; Relación entre el consumo energético y las emisiones de co2 con el índice de desarrollo humano en países americanos: un análisis de eficiencia usando dea; Publicaciones en Ciencias y Tecnología; 16 (1): 3–15.spa
dc.relation.references[Pillutla et al., 2023] Pillutla, K.; Roulet, V.; Kakade, S. M. & Harchaoui, Z.: , 2023; Modified gauss-newton algorithms under noise; en 2023 IEEE Statistical Signal Processing Workshop (SSP); págs. 51–55; doi:10.1109/SSP53291.2023.10207977spa
dc.relation.references[Pinheiro et al., 2022] Pinheiro, R. B.; Balbo, A. R.; Cabana, T. G. & Nepomuceno, L.: , 2022; Solving nonsmooth and discontinuous optimal power flow problems via interior-point p-penalty approach; Computers & Operations Research; 138: 105607.spa
dc.relation.references[Pritchard et al., 1999] Pritchard, J. K.; Seielstad, M. T.; Perez-Lezaun, A. & Feld- man, M. W.: , 1999; Population growth of human y chromosomes: a study of y chromosome microsatellites.; Molecular biology and evolution; 16 (12): 1791–1798.spa
dc.relation.references[Qi et al., 2020] Qi, J.; Du, J.; Siniscalchi, S. M.; Ma, X. & Lee, C.-H.: , 2020; On mean absolute error for deep neural network based vector-to-vector regression; IEEE Signal Processing Letters; 27: 1485–1489.spa
dc.relation.references[Qiu et al., 2020] Qiu, B.; Huang, Z.; Liu, X.; Meng, X.; You, Y.; Liu, G.; Yang, K.; Maier, A.; Ren, Q. & Lu, Y.: , 2020; Noise reduction in optical coherence tomography images using a deep neural network with perceptually-sensitive loss function; Biomed. Opt. Express; 11 (2): 817–830; doi:10.1364/BOE.379551; URL https://opg.optica.org/boe/abstract.cfm?URI=boe-11-2-817.spa
dc.relation.references[Rasamoelina et al., 2020] Rasamoelina, A. D.; Adjailia, F. & Sinčák, P.: , 2020; A review of activation function for artificial neural network; en 2020 IEEE 18th World Symposium on Applied Machine Intelligence and Informatics (SAMI); IEEE; págs. 281–286.spa
dc.relation.references[Raynaud et al., 2022] Raynaud, G.; Houde, S. & Gosselin, F. P.: , 2022; Modalpinn: An extension of physics-informed neural networks with enforced truncated fourier decomposition for periodic flow reconstruction using a limited number of imperfect sensors; Journal of Computational Physics; 464: 111271.spa
dc.relation.references[Ríos-Mercado & Borraz-Sánchez, 2015] Ríos-Mercado, R. Z. & Borraz-Sánchez, C.: , 2015; Optimization problems in natural gas transportation systems: A state-of-the-art review; Applied Energy; 147: 536–555.spa
dc.relation.references[Ritchie & Rosado, 2020] Ritchie, H. & Rosado, P.: , 2020; Energy mix; Our World in Data; https://ourworldindata.org/energy-mix.spa
dc.relation.references[Robuschi et al., 2021] Robuschi, N.; Zeile, C.; Sager, S. & Braghin, F.: , 2021; Multi- phase mixed-integer nonlinear optimal control of hybrid electric vehicles; Automatica; 123: 109325spa
dc.relation.references[Rumelhart et al., 1986] Rumelhart, D. E.; Hinton, G. E. & Williams, R. J.: , 1986; Learning representations by back-propagating errors; nature; 323 (6088): 533–536.spa
dc.relation.references[Sadat & Sahraei-Ardakani, 2021] Sadat, S. A. & Sahraei-Ardakani, M.: , 2021; Cus- tomized sequential quadratic programming for solving large-scale ac optimal power flow; en 2021 North American Power Symposium (NAPS); IEEE; págs. 1–6.spa
dc.relation.references[Sadat & Sahraei-Ardakani, 2022] Sadat, S. A. & Sahraei-Ardakani, M.: , 2022; Tuning successive linear programming to solve ac optimal power flow problem for large networks; International Journal of Electrical Power & Energy Systems; 137: 107807.spa
dc.relation.references[Sakketou & Ampazis, 2019] Sakketou, F. & Ampazis, N.: , 2019; On the invariance of the selu activation function on algorithm and hyperparameter selection in neural network recommenders; en Artificial Intelligence Applications and Innovations: 15th IFIP WG 12.5 International Conference, AIAI 2019, Hersonissos, Crete, Greece, May 24–26, 2019, Proceedings 15 ; Springer; págs. 673–685.spa
dc.relation.references[Saldarriaga-Cortés et al., 2019] Saldarriaga-Cortés, C.; Salazar, H.; Moreno, R. & Jiménez-Estévez, G.: , 2019; Stochastic planning of electricity and gas networks: An asynchronous column generation approach; Applied energy; 233: 1065–1077.spa
dc.relation.references[Sangaiah et al., 2020] Sangaiah, A. K.; Tirkolaee, E. B.; Goli, A. & Dehnavi-Arani, S.: , 2020; Robust optimization and mixed-integer linear programming model for lng supply chain planning problem; Soft computing; 24: 7885–7905spa
dc.relation.references[Schiassi et al., 2021] Schiassi, E.; De Florio, M.; D’Ambrosio, A.; Mortari, D. & Furfaro, R.: , 2021; Physics-informed neural networks and functional interpola- tion for data-driven parameters discovery of epidemiological compartmental models; Mathematics; 9 (17): 2069.spa
dc.relation.references[Schreider et al., 2015] Schreider, S.; Plummer, J.; McInnes, D. & Miller, B.: , 2015; Sensitivity analysis of gas supply optimization models; Annals of Operations Research; 226: 565–588.spa
dc.relation.references[Schuster et al., 2020] Schuster, R.; Hanson, J. O.; Strimas-Mackey, M. & Bennett, J. R.: , 2020; Exact integer linear programming solvers outperform simulated annealing for solving conservation planning problems; PeerJ ; 8: e9258.spa
dc.relation.references[Shi & Hong, 2020] Shi, Q. & Hong, M.: , 2020; Penalty dual decomposition method for nonsmooth nonconvex optimization—part i: Algorithms and convergence analysis; IEEE Transactions on Signal Processing; 68: 4108–4122.spa
dc.relation.references[Sosa & Navarro, 2020] Sosa, P. V. & Navarro, D. M.: , 2020; Crecimiento, complejidad económica y emisiones de co2: un análisis para colombia; Revista CIFE: Lecturas de Economía Social ; 22 (37): 21–41.spa
dc.relation.references[Stiasny et al., 2021] Stiasny, J.; Chevalier, S. & Chatzivasileiadis, S.: , 2021; Learning without data: Physics-informed neural networks for fast time-domain simulation; en 2021 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm); IEEE; págs. 438–443.spa
dc.relation.references[Street, 1988] Street, J. H.: , 1988; The contribution of simon s. kuznets to institutionalist development theory; Journal of Economic Issues; 22 (2): 499–509.spa
dc.relation.references[Strelow et al., 2023] Strelow, E. L.; Gerisch, A.; Lang, J. & Pfetsch, M. E.: , 2023; Physics informed neural networks: A case study for gas transport problems; Journal of Computational Physics; 481: 112041.spa
dc.relation.references[Sun et al., 2022] Sun, X.; Zhang, Y.; Zhang, Y.; Xie, J. & Sun, B.: , 2022; Operation optimization of integrated energy system considering power-to-gas technology and carbon trading; International Transactions on Electrical Energy Systems; 2022: 1–12spa
dc.relation.references[Sun et al., 2020] Sun, Y.; Zhang, B.; Ge, L.; Sidorov, D.; Wang, J. & Xu, Z.: , 2020; Day-ahead optimization schedule for gas-electric integrated energy system based on second-order cone programming; CSEE Journal of Power and Energy Systems; 6 (1): 142–151.spa
dc.relation.references[Thangamuthu et al., 2022] Thangamuthu, A.; Kumar, G.; Bishnoi, S.; Bhattoo, R.; Krishnan, N. & Ranu, S.: , 2022; Unravelling the performance of physics- informed graph neural networks for dynamical systems; Advances in Neural Information Processing Systems; 35: 3691–3702.spa
dc.relation.references[Unigas, 2023] Unigas: , 2023; Panorama energético en colombia: re- tos del segundo semestre de 2023; https://www.unigas.com.co/blog/ panorama-energetico-en-colombia-retos-del-segundo-semestre-de-2023/; Último acceso en 2024spa
dc.relation.references[UPME, 2019] UPME: , 2019; Informe final del plan energético nacional: Indicadores de eficiencia energética; URL https://www1.upme.gov.co/DemandayEficiencia/ Documents/Informe_PEVI_final.pdf; accessed: 2024-07-15.spa
dc.relation.references[UPME, 2021a] UPME: , 2021a; Resolución 0283 de 2021; https://gestornormativo. creg.gov.co/gestor/entorno/docs/resolucion_upme_0283_2021.htm; Último ac- ceso en 2024spa
dc.relation.references[UPME, 2021b] UPME: , 2021b; Resolución 0330 de 2021; https://normas.cra.gov.co/ gestor/docs/resolucion_upme_0330_2021.htm; Último acceso en 2024.spa
dc.relation.references[UPME, 2022a] UPME: , 2022a; Proyectos de eficiencia energética; https://www1.upme. gov.co/DemandayEficiencia/Paginas/Proyectos-de-eficiencia-energetica. aspx; Último acceso en 2024.spa
dc.relation.references[UPME, 2022b] UPME: , 2022b; Resolución 0289 de 2022; https://gestornormativo. creg.gov.co/gestor/entorno/docs/resolucion_upme_0289_2022.htm; Último ac- ceso en 2024.spa
dc.relation.references[UPME, 2022c] UPME: , 2022c; Resolución 0468 de 2022; https://gestornormativo. creg.gov.co/gestor/entorno/docs/resolucion_upme_0468_2022.htm; Último ac- ceso en 2024.spa
dc.relation.references[Van de Graaf & Colgan, 2016] Van de Graaf, T. & Colgan, J.: , 2016; Global energy governance: a review and research agenda; Palgrave Communications; 2 (1): 1–12.spa
dc.relation.references[Vo et al., 2023] Vo, T. Q. T.; Baiou, M.; Nguyen, V. H. & Weng, P.: , 2023; Improving subtour elimination constraint generation in branch-and-cut algorithms for the tsp with machine learning; en Learning and Intelligent Optimization (Editado por Sellmann, M. & Tierney, K.); Springer International Publishing, Cham; ISBN 978-3-031-44505-7; págs. 537–551.spa
dc.relation.references[Vásquez Cordano & Zellou, 2020] Vásquez Cordano, A. L. & Zellou, A. M.: , 2020; Super cycles in natural gas prices and their impact on latin american energy and environmental policies; Resources Policy; 65: 101513; doi:https://doi.org/10.1016/ j.resourpol.2019.101513; URL https://www.sciencedirect.com/science/article/ pii/S0301420718302034.spa
dc.relation.references[Wang et al., 2023] Wang, G.; Zhao, W.; Qiu, R.; Liao, Q.; Lin, Z.; Wang, C. & Zhang, H.: , 2023; Operational optimization of large-scale thermal constrained natural gas pipeline networks: A novel iterative decomposition approach; Energy; 282: 128856spa
dc.relation.references[Wang et al., 2007] Wang, H.; Murillo-Sanchez, C. E.; Zimmerman, R. D. & Thomas, R. J.: , 2007; On computational issues of market-based optimal power flow; IEEE Transactions on Power Systems; 22 (3): 1185–1193; doi:10.1109/TPWRS.2007. 901301spa
dc.relation.references[Wang & Zhou, 2023] Wang, L. & Zhou, B.: , 2023; Optimal planning of electric vehi- cle fast-charging stations considering uncertain charging demands via dantzig–wolfe decomposition; Sustainability; 15 (8): 6588.spa
dc.relation.references[Wang et al., 2020a] Wang, Q.; Ma, Y.; Zhao, K. & Tian, Y.: , 2020a; A comprehensive survey of loss functions in machine learning; Annals of Data Science: 1–26spa
dc.relation.references[Wang et al., 2020b] Wang, Y.; Gao, S.; Zhou, M. & Yu, Y.: , 2020b; A multi-layered gravitational search algorithm for function optimization and real-world problems; IEEE/CAA Journal of Automatica Sinica; 8 (1): 94–109spa
dc.relation.references[Wolpert & Macready, 1997] Wolpert, D. H. & Macready, W. G.: , 1997; No free lunch theorems for optimization; IEEE transactions on evolutionary computation; 1 (1): 67–82.spa
dc.relation.references[Wu et al., 2018] Wu, X.; Li, C.; He, Y. & Jia, W.: , 2018; Operation optimization of natural gas transmission pipelines based on stochastic optimization algorithms: a review; Mathematical Problems in Engineering; 2018spa
dc.relation.referencesXM, 2023] XM: , 2023; Informes mensuales de análisis del mercado; https://www.xm. com.co/nuestra-empresa/informes/informes-de-la-operacion-y-el-mercado/ informes-mensuales-de-analisis-del-mercado; Último acceso en 2024.spa
dc.relation.references[Yang et al., 2021] Yang, L.; Meng, X. & Karniadakis, G. E.: , 2021; B-pinns: Bayesian physics-informed neural networks for forward and inverse pde problems with noisy data; Journal of Computational Physics; 425: 109913spa
dc.relation.references[Yang et al., 2019] Yang, W.; Wang, J.; Niu, T. & Du, P.: , 2019; A hybrid forecasting system based on a dual decomposition strategy and multi-objective optimization for electricity price forecasting; Applied energy; 235: 1205–1225.spa
dc.relation.references[Yu et al., 2023] Yu, H.; Ma, W.; Li, R.; Qiu, Z.; Li, H.; Zhou, J. & Wu, K.: , 2023; Optimization of electric-gas integrated energy system based on reversible solid oxide cell considering gas composition; en 2023 International Conference on Smart Electrical Grid and Renewable Energy (SEGRE); IEEE; págs. 214–220.spa
dc.relation.references[Yu et al., 2021] Yu, W.; Huang, W.; Wen, Y.; Li, Y.; Liu, H.; Wen, K.; Gong, J. & Lu, Y.: , 2021; An integrated gas supply reliability evaluation method of the large-scale and complex natural gas pipeline network based on demand-side analysis; Reliability Engineering & System Safety; 212: 107651.spa
dc.relation.references[Zhang et al., 2023] Zhang, Z.; Sun, M.; Deng, R.; Kang, C. & Chow, M.-Y.: , 2023; Physics-constrained robustness evaluation of intelligent security assessment for power systems; IEEE Transactions on Power Systems; 38 (1): 872–884; doi: 10.1109/TPWRS.2022.3169139.spa
dc.relation.references[Zhao et al., 2020] Zhao, Z.; Liu, S.; Zhou, M. & Abusorrah, A.: , 2020; Dual-objective mixed integer linear program and memetic algorithm for an industrial group scheduling problem; IEEE/CAA Journal of Automatica Sinica; 8 (6): 1199–1209.spa
dc.relation.references[Zhou et al., 2023] Zhou, M.; Chen, M. & Low, S. H.: , 2023; Deepopf-ft: One deep neural network for multiple ac-opf problems with flexible topology; IEEE Transactions on Power Systems; 38 (1): 964–967; doi:10.1109/TPWRS.2022.3217407.spa
dc.relation.references[Zimmerman & Murillo-Sánchez, 2020] Zimmerman, R. D. & Murillo-Sánchez, C. E.: , 2020; MATPOWER User’s Manual ; Zenodo; doi:10.5281/zenodo.4074122.spa
dc.rights.accessrightsinfo:eu-repo/semantics/openAccessspa
dc.rights.licenseAtribución-NoComercial-CompartirIgual 4.0 Internacionalspa
dc.rights.urihttp://creativecommons.org/licenses/by-nc-sa/4.0/spa
dc.subject.ddc620 - Ingeniería y operaciones afines::629 - Otras ramas de la ingenieríaspa
dc.subject.proposalOptimizaciónspa
dc.subject.proposalSistemas de Gasspa
dc.subject.proposalRedes Neuronalesspa
dc.subject.proposalProgramación No Linealspa
dc.subject.proposalTiempo de Cómputospa
dc.subject.proposalRedes Informadas Físicamentespa
dc.subject.proposalOptimizationeng
dc.subject.proposalGas Systemseng
dc.subject.proposalNeural Networkseng
dc.subject.proposalNonlinear Programmingeng
dc.subject.proposalConvergenceeng
dc.subject.proposalComputation timeeng
dc.subject.proposalPhysic-informed networkseng
dc.subject.unescoModelos matemáticos
dc.subject.unescoSistemas de energía
dc.subject.unescoTecnologías sostenibles
dc.titlePhysics-informed neural networks-based optimization for gas-powered energy systemseng
dc.title.translatedOptimización basada en redes neuronales informadas por la física para sistemas de energía a gasspa
dc.typeTrabajo de grado - Maestríaspa
dc.type.coarhttp://purl.org/coar/resource_type/c_bdccspa
dc.type.coarversionhttp://purl.org/coar/version/c_ab4af688f83e57aaspa
dc.type.contentTextspa
dc.type.driverinfo:eu-repo/semantics/masterThesisspa
dc.type.versioninfo:eu-repo/semantics/acceptedVersionspa
dcterms.audience.professionaldevelopmentBibliotecariosspa
dcterms.audience.professionaldevelopmentEstudiantesspa
dcterms.audience.professionaldevelopmentInvestigadoresspa
dcterms.audience.professionaldevelopmentPúblico generalspa
oaire.accessrightshttp://purl.org/coar/access_right/c_abf2spa
oaire.awardtitleDesarrollo de una herramienta para la planeación a largo plazo de la operación del sistema de transporte de gas natural de Colombiaspa
oaire.fundernameMincienciasspa

Archivos

Bloque original

Mostrando 1 - 1 de 1
Cargando...
Miniatura
Nombre:
1081595697.2024.pdf
Tamaño:
2.53 MB
Formato:
Adobe Portable Document Format
Descripción:
Tesis de Maestría en Ingeniería - Automatización Industrial

Bloque de licencias

Mostrando 1 - 1 de 1
Cargando...
Miniatura
Nombre:
license.txt
Tamaño:
5.74 KB
Formato:
Item-specific license agreed upon to submission
Descripción: