{"title":"Diseño de redes neuronales inteligentes para la realización de pronósticos en microrredes eléctricas","authors":"Juan Pablo Fossati","doi":"10.36561/ing.17.2","DOIUrl":null,"url":null,"abstract":"espanolConocer de antemano los perfiles de demanda y de potencia generada por las fuentes renovables constituye un aspecto esencial para la optimizacion de la operacion de las redes electricas. En el caso particular de las microrredes dicho aspecto cobra aun mas importancia ya que en general un alto porcentaje de la energia generada proviene de fuentes renovables. A esto debe sumarsele el hecho de que debido a un efecto de escala los parametros a pronosticar estan sometidos a una gran variabilidad. En este articulo se propone una metodologia para el diseno de sistemas de pronosticos basados en redes neuronales artificiales (RNA) y algoritmos geneticos. EnglishBeing able to predict power demand and output from renewable energy sources is an essential asset for the optimization of the performance of electric networks. In the particular case of microgrids the importance of that ability is enhanced even more so, since in general a great percentage of the energy generated comes from renewable sources. These parameters fluctuate substantially due to the scale in which they operate, so the need to predict their values acquires further significance. In this article we propose a methodology for the design of forecasting systems based on artificial neural networks (ANN)","PeriodicalId":42925,"journal":{"name":"Memoria Investigaciones en Ingenieria","volume":null,"pages":null},"PeriodicalIF":0.4000,"publicationDate":"2019-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Memoria Investigaciones en Ingenieria","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.36561/ing.17.2","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"ENGINEERING, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0
Abstract
espanolConocer de antemano los perfiles de demanda y de potencia generada por las fuentes renovables constituye un aspecto esencial para la optimizacion de la operacion de las redes electricas. En el caso particular de las microrredes dicho aspecto cobra aun mas importancia ya que en general un alto porcentaje de la energia generada proviene de fuentes renovables. A esto debe sumarsele el hecho de que debido a un efecto de escala los parametros a pronosticar estan sometidos a una gran variabilidad. En este articulo se propone una metodologia para el diseno de sistemas de pronosticos basados en redes neuronales artificiales (RNA) y algoritmos geneticos. EnglishBeing able to predict power demand and output from renewable energy sources is an essential asset for the optimization of the performance of electric networks. In the particular case of microgrids the importance of that ability is enhanced even more so, since in general a great percentage of the energy generated comes from renewable sources. These parameters fluctuate substantially due to the scale in which they operate, so the need to predict their values acquires further significance. In this article we propose a methodology for the design of forecasting systems based on artificial neural networks (ANN)