An epidemic model-based particle swarm optimizer
碩士 === 國立高雄第一科技大學 === 電腦與通訊工程研究所 === 99 === Optimization inspired by the collective behavior of social animals has been unexpectedly successful and has been known as particle swarm optimization (PSO) in recent years. To improve the performance of a PSO-based algorithm, one of the most important fact...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Others |
| Language: | zh-TW |
| Published: |
2011
|
| Online Access: | http://ndltd.ncl.edu.tw/handle/35261347845859758091 |
| Summary: | 碩士 === 國立高雄第一科技大學 === 電腦與通訊工程研究所 === 99 === Optimization inspired by the collective behavior of social animals has been unexpectedly successful and has been known as particle swarm optimization (PSO) in recent years. To improve the performance of a PSO-based algorithm, one of the most important factors is the trade-off between exploitation and exploration. An epidemic model-based particle swarm optimizer, namely EMPSO, is therefore proposed in this thesis to solve global numerical optimization problems with continuous variables. Several control policies based on the epidemic model are developed to explicitly balance the exploration and exploitation abilities of EMPSO. The proposed EMPSO is effectively applied to solve 16 benchmark problems of global optimization with 30 dimensions. Computational experiments demonstrate the effectiveness of the proposed approach.
|
|---|