MO-TRIBES, an adaptive multiobjective particle swarm optimization algorithm

This paper presents MO-TRIBES, an adaptive multiobjective Particle Swarm Optimization (PSO) algorithm. Metaheuristics have the drawback of being very dependent on their parameter values. Then, performances are strongly related to the fitting of parameters. Usually, such tuning is a lengthy, time con...

Full description

Saved in:
Bibliographic Details
Published in:Computational optimization and applications Vol. 49; no. 2; pp. 379 - 400
Main Authors: Cooren, Yann, Clerc, Maurice, Siarry, Patrick
Format: Journal Article
Language:English
Published: Boston Springer US 01.06.2011
Springer Nature B.V
Springer Verlag
Subjects:
Adaptation
Computer Science
Convex and Discrete Geometry
Design
Genetic algorithms
Heuristic
Management Science
Mathematics
Mathematics and Statistics
Operations Research
Operations Research/Decision Theory
Optimization
Optimization algorithms
Particle physics
Statistics
Studies
Crowding distance
Adaptive
Particle swarm optimization
Parameter-free
Pareto dominance
ISSN:0926-6003, 1573-2894
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper presents MO-TRIBES, an adaptive multiobjective Particle Swarm Optimization (PSO) algorithm. Metaheuristics have the drawback of being very dependent on their parameter values. Then, performances are strongly related to the fitting of parameters. Usually, such tuning is a lengthy, time consuming and delicate process. The aim of this paper is to present and to evaluate MO-TRIBES, which is an adaptive algorithm, designed for multiobjective optimization, allowing to avoid the parameter fitting step. A global description of TRIBES and a comparison with other algorithms are provided. Using an adaptive algorithm means that adaptation rules must be defined. Swarm’s structure and strategies of displacement of the particles are modified during the process according to the tribes behaviors. The choice of the final solutions is made using the Pareto dominance criterion. Rules based on crowding distance have been incorporated in order to maintain diversity along the Pareto Front. Preliminary simulations are provided and compared with the best known algorithms. These results show that MO-TRIBES is a promising alternative to tackle multiobjective problems without the constraint of parameter fitting.
Bibliography:SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 14
ISSN:0926-6003
1573-2894
DOI:10.1007/s10589-009-9284-z