The review of multiple evolutionary searches and multi-objective evolutionary algorithms
Over the past decade, subdividing evolutionary search into multiple local evolutionary searches has been identified as an effective method to search for optimal solutions of multi-objective optimization problems (MOPs). The existing multi-objective evolutionary algorithms that benefit from the multi...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Published: |
Kluwer Academic Publishers
2015
|
| Subjects: | |
| Online Access: | http://eprints.utm.my/id/eprint/58988/ http://dx.doi.org/10.1007/s10462-012-9378-3 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Universiti Teknologi Malaysia |
| Summary: | Over the past decade, subdividing evolutionary search into multiple local evolutionary searches has been identified as an effective method to search for optimal solutions of multi-objective optimization problems (MOPs). The existing multi-objective evolutionary algorithms that benefit from the multiple local searches (multiple-MOEAs, or MMOEAs) use different dividing methods and/or collaborations (information sharing) strategies between the created divisions. Their local evolutionary searches are implicitly or explicitly guided toward a part of global optimal solutions instead of converging to local ones in some divisions. In this reviewed paper, the dividing methods and the collaborations strategies are reviewed, while their advantage and disadvantage are mentioned. |
|---|