Using Cluster based Global Search Strategy on Multi-Objective Particle Swarm Optimization
碩士 === 國立東華大學 === 電機工程學系 === 94 === Recently, there have been several studies to extend Particle Swarm Optimization (PSO) algorithm to handle multi-objective problems (MOPs). In this thesis, we incorporate cluster based global search into a Multi-Objective Particle Swarm Optimization (MOPSO) algorit...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
2006
|
Online Access: | http://ndltd.ncl.edu.tw/handle/61453521648208032181 |
id |
ndltd-TW-094NDHU5442009 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-094NDHU54420092015-12-16T04:39:01Z http://ndltd.ncl.edu.tw/handle/61453521648208032181 Using Cluster based Global Search Strategy on Multi-Objective Particle Swarm Optimization 以聚類為基礎的全域最佳解搜尋法應用於多目標粒子群聚最佳化的研究 Cheng-Wei Lin 林政緯 碩士 國立東華大學 電機工程學系 94 Recently, there have been several studies to extend Particle Swarm Optimization (PSO) algorithm to handle multi-objective problems (MOPs). In this thesis, we incorporate cluster based global search into a Multi-Objective Particle Swarm Optimization (MOPSO) algorithm. We call it CGS-MOPSO. By using the clustering mechanism, we obtain better spread between the non-dominated solutions we found. Then we use the center of a circle method for selecting the appropriate global best solution for each particle of the population. This approach is validated by using five benchmarks and compare with the Sigma method. Experiments adopted three performance measurement methods including the general distance, diversity metric, and maximum spread for comparing CGS-MOPSO with Sigma method. CGS-MOPSO shows the smaller difference with real Pareto front and better spread than Sigma method. Tsung-Ying Sun 孫宗瀛 2006 學位論文 ; thesis 70 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 === 94 === Recently, there have been several studies to extend Particle Swarm Optimization (PSO) algorithm to handle multi-objective problems (MOPs). In this thesis, we incorporate cluster based global search into a Multi-Objective Particle Swarm Optimization (MOPSO) algorithm. We call it CGS-MOPSO. By using the clustering mechanism, we obtain better spread between the non-dominated solutions we found. Then we use the center of a circle method for selecting the appropriate global best solution for each particle of the population. This approach is validated by using five benchmarks and compare with the Sigma method. Experiments adopted three performance measurement methods including the general distance, diversity metric, and maximum spread for comparing CGS-MOPSO with Sigma method. CGS-MOPSO shows the smaller difference with real Pareto front and better spread than Sigma method.
|
author2 |
Tsung-Ying Sun |
author_facet |
Tsung-Ying Sun Cheng-Wei Lin 林政緯 |
author |
Cheng-Wei Lin 林政緯 |
spellingShingle |
Cheng-Wei Lin 林政緯 Using Cluster based Global Search Strategy on Multi-Objective Particle Swarm Optimization |
author_sort |
Cheng-Wei Lin |
title |
Using Cluster based Global Search Strategy on Multi-Objective Particle Swarm Optimization |
title_short |
Using Cluster based Global Search Strategy on Multi-Objective Particle Swarm Optimization |
title_full |
Using Cluster based Global Search Strategy on Multi-Objective Particle Swarm Optimization |
title_fullStr |
Using Cluster based Global Search Strategy on Multi-Objective Particle Swarm Optimization |
title_full_unstemmed |
Using Cluster based Global Search Strategy on Multi-Objective Particle Swarm Optimization |
title_sort |
using cluster based global search strategy on multi-objective particle swarm optimization |
publishDate |
2006 |
url |
http://ndltd.ncl.edu.tw/handle/61453521648208032181 |
work_keys_str_mv |
AT chengweilin usingclusterbasedglobalsearchstrategyonmultiobjectiveparticleswarmoptimization AT línzhèngwěi usingclusterbasedglobalsearchstrategyonmultiobjectiveparticleswarmoptimization AT chengweilin yǐjùlèiwèijīchǔdequányùzuìjiājiěsōuxúnfǎyīngyòngyúduōmùbiāolìziqúnjùzuìjiāhuàdeyánjiū AT línzhèngwěi yǐjùlèiwèijīchǔdequányùzuìjiājiěsōuxúnfǎyīngyòngyúduōmùbiāolìziqúnjùzuìjiāhuàdeyánjiū |
_version_ |
1718150757981618176 |