A Method For Solving Mult-Objective Optimization Problem: Vector Evaluated Genetic Algorithm (Vega)
Solving Multi-Objective Optimization Problem (MOOP) is significant as it finds solutions that satisfy two or more objectives simultaneously which are always related to the real world situation. However, it is impractical to solve MOOP by using classical methods due to its complexity. Genetic Algorit...
Saved in:
| Main Author: | |
|---|---|
| Format: | Final Year Project Report / IMRAD |
| Language: | en |
| Published: |
Universiti Malaysia Sarawak, (UNIMAS)
2009
|
| Subjects: | |
| Online Access: | http://ir.unimas.my/id/eprint/47511/1/Tan%20Tun%20Tai%20FT.pdf http://ir.unimas.my/id/eprint/47511/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Solving Multi-Objective Optimization Problem (MOOP) is significant as it finds solutions that satisfy two or more objectives simultaneously which are always related to the real world situation. However, it is impractical to solve MOOP by using classical methods due to its complexity. Genetic Algorithms (GAs) are a powerful stochastic search in solving optimization problems. Nonetheless, GAs which always deal with single objective cannot be used to solve MOOP.
Consequently, some components of GAs had been modified to produce Vector Evaluated Genetic Algorithm (VEGA) in order to adapt the nature of MOOP. Simulation runs on GAs and VEGA are developed to demonstrate their capability in solving optimization problems. Series of experiment are done on VEGA in order to find out its performance under various parameter input. The results are
later compared. |
|---|