• JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
 
  Bookmark and Share
 
 
Master's Dissertation
DOI
https://doi.org/10.11606/D.18.1999.tde-06062024-153224
Document
Author
Full name
Patrícia Teixeira Leite Asano
Institute/School/College
Knowledge Area
Date of Defense
Published
São Carlos, 1999
Supervisor
Committee
Carneiro, Adriano Alber de Franca Mendes (President)
Carvalho, André Carlos Ponce de Leon Ferreira de
Ohishi, Takaaki
Title in Portuguese
Um algoritmo genético para o planejamento de sistemas hidroelétricos
Keywords in Portuguese
algoritmos genéticos
inteligência artificial
otimização
planejamento da operação
sistemas hidrotérmicos
Abstract in Portuguese
O Planejamento da Operação dos Sistemas Hidrotérmicos de Potência vem sendo formulado através de modelos de otimização e simulação. Estes métodos apresentam imperfeições enerentes, susceptíveis de aperfeiçoamento, uma vez que lidam com problemas não-lineares bastante complexos e de difíceis soluções. Algumas abordagens baseiam-se na programação dinâmica ou em técnicas de programação não-linear, que apresentam deficiências de convergência, simplificação da formulação original do problema, ou dificuldades devido à complexidade da função objetivo. Com a finalidade de encontrar métodos mais eficazes para solução do problema, este trabalho propõem métodos de Inteligência Artificial que possam superar as deficiências encontradas nas abordagens tradicionais. A abordagem proposta, utilizando técnicas de Algoritmos Genéticos, foi aplicada em vários testes com usinas hidroelétricas pertencentes ao Sistema Brasileiro. Os testes procuram reproduzir as mesmas situações encontradas nos estudos e ações do Planejamento da Operação de Sistemas Hidrotérmicos de Potência, visando determinar o cronograma ótimo de operação. Os resultados foram comparados com outros obtidos através da técnica tradicional de programação não-linear, já exaustivamente testada
Title in English
A genetíc algorithm applied to hydroelectric system planning
Keywords in English
artificial intelligence
geneíic aigorithms
hydrothermical systems
operation planning
optimization
Abstract in English
The Power Systems Hydrothermal Operation Plamng is nowadays formulaíed through optimizaíion models and simulations. These approaches show inherení imperfections, susceptible to improvement, since they deal with complex non-linear problems with difficult solution. Some approaches are based on dynamic programming or in nou-linear programming tecbniques, which also present some drawbacks, such as hard convergence, simplification of the origmal problem formulation, or difficulty due to complex object function. In order to find more efficient methods to solve this problem, the present study uses Artificial Inteligent Techniques to overcome the inaccuracies found in the traditional approaches. The proposed approach, using Genetic Algorithms techniques, was applied m various tests with hydroelectric plants belonging to the Brazílian System. The tests reproduces the same situations found in the studies and procedures of the Hydrothermal System Planning, aiming to determine the optimal operation scheduling. The results achieved were compared to those obtained by an algorithm using the traditional Non-linear Programming, which has been extensively investigated and tested.
 
WARNING - Viewing this document is conditioned on your acceptance of the following terms of use:
This document is only for private use for research and teaching activities. Reproduction for commercial use is forbidden. This rights cover the whole data about this document as well as its contents. Any uses or copies of this document in whole or in part must include the author's name.
Publishing Date
2024-06-07
 
WARNING: Learn what derived works are clicking here.
All rights of the thesis/dissertation are from the authors
CeTI-SC/STI
Digital Library of Theses and Dissertations of USP. Copyright © 2001-2024. All rights reserved.