Enfoque del empleo de las redes neuronales de base radial en las redes eléctricas inteligentes en la UTM.

  • Ney Balderramo Velez Universidad Técnica de Manabí
  • Lenin Cuenca Alava Universidad Técnica de Manabí
  • Yolanda Llosas Albuerne
  • Julio Cesar Mera Maciás Universidad Técnica de Manabí

Resumen

In the presented work, an analysis of the use of artificial intelligence is proposed, as a way to solve the problems that arise in the daily work of electrical networks. By implementing the distributed generation with contributions from generating elements with the incorporation of renewable energy sources in them, as well as connection of consumer elements in different points of the network, conflicts are established regarding the transmission of electrical energy in the different scenarios. It is therefore essential to manage the direction in which energy is transmitted in the network, as well as the organized connection and disconnection of each of the elements, the creation of intelligent decision-making elements, to what is called Intelligent Electrical Network (Smart Grids). For the decision making it is proposed to use artificial intelligence techniques, and according to the experience in the work of transmission lines it has been selected to work with the topology of radial-based neural networks to undertake the different tasks regarding the intelligent decision.


Index Terms electrical networks, smart grids, distributed generation, transmission line, renewable energy

Citas

[1] S. M. Ochoa, “Smart grids: presente y futuro del sistema eléctrico,” 2012.
[2] A. G. Peralta Sevilla and F. Amata Fernández, “Evolución de las Redes Eléctricas hacia Smart Grid en Países de la Región Andina,” Rev. Educ. en Ing., vol. 8, pp. 1–14, 2013.
[3] K. Akira et al., “A study on estimation method of reactive power control of DGs in distribution systems with a large amount of PVs,” Power Plants Power Syst. Control, pp. 387–392, 2012.
[4] A. A. Álvarez, Sistema de agentes para control de stock de almacén basado en identificación por radiofrecuencia. 2011.
[5] J. A. Iglesias Martínez, “Modelado automático del comportamiento de agentes inteligentes,” Jan. 2010.
[6] S. Montelier, A. Borroto, M. De Armas, J. Gomez, C. Perez, and O. Goza, “Estimación de cargas térmicas de climatización de hoteles mediante simulación y redes neuronales artificiales,” Energética, vol. XXXI, no. 3, pp. 13–18, 2010.
[7] H. Galán Asencio and A. Martínez Bowen, “Inteligencia artificial . Redes neuronales y Aplicaciones,” p. 8, 2010.
[8] S. P. Daza, “Redes Neuronales Artificiales. Fundamentos, modelos y aplicaciones,” p. 390, 2000.
[9] F. Villada, D. R. Cadavid, and J. D. Molina, “Pronóstico del precio de la energía eléctrica usando redes neuronales artificiales Electricity price forecasting using artificial neural networks,” pp. 111–118, 2008.
[10] E. Barrero, B. Fernández, and O. Llanes, “‘ Propuesta de procedimiento para configurar una red neuronal artificial de Base Radial con aplicaciones en el diagnóstico de fallos ,’” no. December 2014, pp. 60–75, 2014.
[11] B. Martín, D. Brío, A. Sanz Molina, T. Pollán Santamaría, and Y. N. Medrano Marqués, “REDES NEURONALES Y SISTEMAS BORROSOS: UN LIBRO DE TEXTO EN ESPAÑOL,” 1997.
[12] A. Muñoz San Roque, “Aplicación de técnicas de redes neuronales artificiales al diagnostico de procesos industriales,” p. 1, 1996.
Publicado
2017-12-15
Sección
Artículos