Tournament Selection for Global Guide on Multiobjective Particle Swarm Optimization
碩士 === 國立東華大學 === 電機工程學系 === 99 === In recent years, multiobjective particle swarm optimization (MOSPO) has been used to solve multiobjective optimization problems widely. The selection of the global best solution is a critical issue in MOPSO since it can be leading the whole population to move....
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
2011
|
Online Access: | http://ndltd.ncl.edu.tw/handle/66429133456724323182 |
id |
ndltd-TW-099NDHU5442014 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-099NDHU54420142015-10-16T04:05:34Z http://ndltd.ncl.edu.tw/handle/66429133456724323182 Tournament Selection for Global Guide on Multiobjective Particle Swarm Optimization 競賽選擇的多目標粒子群最佳化演算法 Chih-Nien Lin 林至年 碩士 國立東華大學 電機工程學系 99 In recent years, multiobjective particle swarm optimization (MOSPO) has been used to solve multiobjective optimization problems widely. The selection of the global best solution is a critical issue in MOPSO since it can be leading the whole population to move. This thesis proposes a tournament selection mechanism to select the global best solution by comparing the distance between the particles in the external repository and the particles in the evolution. The global best solution leads the population to move toward better position so it can promote the convergence and enhance the diversity of the solutions. This thesis uses seven common benchmarks to evaluate the performance. The proposed method compared with three other algorithms which are NSGA-II, MODE and PDJI-MOPSO. The experiment results showed that the proposed method not only can find the solutions closer to the Pareto front but also the convergence and the diversity of the solutions are better. Tsung-Ying Sun 孫宗瀛 2011 學位論文 ; thesis 123 zh-TW |
collection |
NDLTD |
language |
zh-TW |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立東華大學 === 電機工程學系 === 99 === In recent years, multiobjective particle swarm optimization (MOSPO) has been used to solve multiobjective optimization problems widely. The selection of the global best solution is a critical issue in MOPSO since it can be leading the whole population to move. This thesis proposes a tournament selection mechanism to select the global best solution by comparing the distance between the particles in the external repository and the particles in the evolution. The global best solution leads the population to move toward better position so it can promote the convergence and enhance the diversity of the solutions.
This thesis uses seven common benchmarks to evaluate the performance. The proposed method compared with three other algorithms which are NSGA-II, MODE and PDJI-MOPSO. The experiment results showed that the proposed method not only can find the solutions closer to the Pareto front but also the convergence and the diversity of the solutions are better.
|
author2 |
Tsung-Ying Sun |
author_facet |
Tsung-Ying Sun Chih-Nien Lin 林至年 |
author |
Chih-Nien Lin 林至年 |
spellingShingle |
Chih-Nien Lin 林至年 Tournament Selection for Global Guide on Multiobjective Particle Swarm Optimization |
author_sort |
Chih-Nien Lin |
title |
Tournament Selection for Global Guide on Multiobjective Particle Swarm Optimization |
title_short |
Tournament Selection for Global Guide on Multiobjective Particle Swarm Optimization |
title_full |
Tournament Selection for Global Guide on Multiobjective Particle Swarm Optimization |
title_fullStr |
Tournament Selection for Global Guide on Multiobjective Particle Swarm Optimization |
title_full_unstemmed |
Tournament Selection for Global Guide on Multiobjective Particle Swarm Optimization |
title_sort |
tournament selection for global guide on multiobjective particle swarm optimization |
publishDate |
2011 |
url |
http://ndltd.ncl.edu.tw/handle/66429133456724323182 |
work_keys_str_mv |
AT chihnienlin tournamentselectionforglobalguideonmultiobjectiveparticleswarmoptimization AT línzhìnián tournamentselectionforglobalguideonmultiobjectiveparticleswarmoptimization AT chihnienlin jìngsàixuǎnzédeduōmùbiāolìziqúnzuìjiāhuàyǎnsuànfǎ AT línzhìnián jìngsàixuǎnzédeduōmùbiāolìziqúnzuìjiāhuàyǎnsuànfǎ |
_version_ |
1718093232711139328 |