Interactive particle swarm: A Pareto-adaptive metaheuristic to multiobjective optimization

Shubham Agrawal, Yogest Dashora, Manoj Tiwari, Young-Jun Son

Research output: Contribution to journalArticle

81 Citations (Scopus)

Abstract

This paper proposes an interactive particle-swarm metaheuristic for multiobjective optimization (MOO) that seeks to encapsulate the positive aspects of the widely used approaches, namely, Pareto dominance and interactive decision making in its solution mechanism. Pareto dominance is adopted as the criterion to evaluate the particles found along the search process. Nondominated particles are stored in an external repository which updates continuously through the adaptive-grid mechanism proposed. The approach is further strengthened by the incorporation of a self-adaptive mutation operator. A decision maker (DM) is provided with the knowledge of an approximate Pareto optimal front, and his/her preference articulations are used to derive a utility function intended to calculate the utility of the existing and upcoming solutions. The incubation of particle-swarm mechanism for the MOO by incorporating an adaptive-grid mechanism, a self-adaptive mutation operator, and a novel decision-making strategy makes it a novel and efficient approach. Simulation results on various test functions indicate that the proposed metaheuristic identifies not only the best preferred solution with a greater accuracy but also presents a uniformly diverse high utility Pareto front without putting excessive cognitive load on the DM. The practical relevance of the proposed strategy is very high in the cases that involve the simultaneous use of decision making and availability of highly favored alternatives.

Original languageEnglish (US)
Pages (from-to)258-277
Number of pages20
JournalIEEE Transactions on Systems, Man, and Cybernetics Part A:Systems and Humans
Volume38
Issue number2
DOIs
StatePublished - Mar 2008

Fingerprint

Particle Swarm
Multiobjective optimization
Pareto
Metaheuristics
Multi-objective Optimization
Decision making
Adaptive Grid
Decision Making
Mutation
Cognitive Load
Pareto Front
Operator
Test function
Utility Function
Availability
Repository
Update
Calculate
Evaluate
Alternatives

Keywords

  • Metaheuristic
  • Multiobjective optimization (MOO)
  • Pareto dominance
  • Particle-swarm optimization (PSO)

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Human-Computer Interaction
  • Theoretical Computer Science
  • Computational Theory and Mathematics

Cite this

Interactive particle swarm : A Pareto-adaptive metaheuristic to multiobjective optimization. / Agrawal, Shubham; Dashora, Yogest; Tiwari, Manoj; Son, Young-Jun.

In: IEEE Transactions on Systems, Man, and Cybernetics Part A:Systems and Humans, Vol. 38, No. 2, 03.2008, p. 258-277.

Research output: Contribution to journalArticle

@article{9bcd84de26d944e3b5c158764cae3cc1,
title = "Interactive particle swarm: A Pareto-adaptive metaheuristic to multiobjective optimization",
abstract = "This paper proposes an interactive particle-swarm metaheuristic for multiobjective optimization (MOO) that seeks to encapsulate the positive aspects of the widely used approaches, namely, Pareto dominance and interactive decision making in its solution mechanism. Pareto dominance is adopted as the criterion to evaluate the particles found along the search process. Nondominated particles are stored in an external repository which updates continuously through the adaptive-grid mechanism proposed. The approach is further strengthened by the incorporation of a self-adaptive mutation operator. A decision maker (DM) is provided with the knowledge of an approximate Pareto optimal front, and his/her preference articulations are used to derive a utility function intended to calculate the utility of the existing and upcoming solutions. The incubation of particle-swarm mechanism for the MOO by incorporating an adaptive-grid mechanism, a self-adaptive mutation operator, and a novel decision-making strategy makes it a novel and efficient approach. Simulation results on various test functions indicate that the proposed metaheuristic identifies not only the best preferred solution with a greater accuracy but also presents a uniformly diverse high utility Pareto front without putting excessive cognitive load on the DM. The practical relevance of the proposed strategy is very high in the cases that involve the simultaneous use of decision making and availability of highly favored alternatives.",
keywords = "Metaheuristic, Multiobjective optimization (MOO), Pareto dominance, Particle-swarm optimization (PSO)",
author = "Shubham Agrawal and Yogest Dashora and Manoj Tiwari and Young-Jun Son",
year = "2008",
month = "3",
doi = "10.1109/TSMCA.2007.914767",
language = "English (US)",
volume = "38",
pages = "258--277",
journal = "IEEE Transactions on Systems, Man, and Cybernetics Part A:Systems and Humans.",
issn = "1083-4427",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "2",

}

TY - JOUR

T1 - Interactive particle swarm

T2 - A Pareto-adaptive metaheuristic to multiobjective optimization

AU - Agrawal, Shubham

AU - Dashora, Yogest

AU - Tiwari, Manoj

AU - Son, Young-Jun

PY - 2008/3

Y1 - 2008/3

N2 - This paper proposes an interactive particle-swarm metaheuristic for multiobjective optimization (MOO) that seeks to encapsulate the positive aspects of the widely used approaches, namely, Pareto dominance and interactive decision making in its solution mechanism. Pareto dominance is adopted as the criterion to evaluate the particles found along the search process. Nondominated particles are stored in an external repository which updates continuously through the adaptive-grid mechanism proposed. The approach is further strengthened by the incorporation of a self-adaptive mutation operator. A decision maker (DM) is provided with the knowledge of an approximate Pareto optimal front, and his/her preference articulations are used to derive a utility function intended to calculate the utility of the existing and upcoming solutions. The incubation of particle-swarm mechanism for the MOO by incorporating an adaptive-grid mechanism, a self-adaptive mutation operator, and a novel decision-making strategy makes it a novel and efficient approach. Simulation results on various test functions indicate that the proposed metaheuristic identifies not only the best preferred solution with a greater accuracy but also presents a uniformly diverse high utility Pareto front without putting excessive cognitive load on the DM. The practical relevance of the proposed strategy is very high in the cases that involve the simultaneous use of decision making and availability of highly favored alternatives.

AB - This paper proposes an interactive particle-swarm metaheuristic for multiobjective optimization (MOO) that seeks to encapsulate the positive aspects of the widely used approaches, namely, Pareto dominance and interactive decision making in its solution mechanism. Pareto dominance is adopted as the criterion to evaluate the particles found along the search process. Nondominated particles are stored in an external repository which updates continuously through the adaptive-grid mechanism proposed. The approach is further strengthened by the incorporation of a self-adaptive mutation operator. A decision maker (DM) is provided with the knowledge of an approximate Pareto optimal front, and his/her preference articulations are used to derive a utility function intended to calculate the utility of the existing and upcoming solutions. The incubation of particle-swarm mechanism for the MOO by incorporating an adaptive-grid mechanism, a self-adaptive mutation operator, and a novel decision-making strategy makes it a novel and efficient approach. Simulation results on various test functions indicate that the proposed metaheuristic identifies not only the best preferred solution with a greater accuracy but also presents a uniformly diverse high utility Pareto front without putting excessive cognitive load on the DM. The practical relevance of the proposed strategy is very high in the cases that involve the simultaneous use of decision making and availability of highly favored alternatives.

KW - Metaheuristic

KW - Multiobjective optimization (MOO)

KW - Pareto dominance

KW - Particle-swarm optimization (PSO)

UR - http://www.scopus.com/inward/record.url?scp=41149153821&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=41149153821&partnerID=8YFLogxK

U2 - 10.1109/TSMCA.2007.914767

DO - 10.1109/TSMCA.2007.914767

M3 - Article

AN - SCOPUS:41149153821

VL - 38

SP - 258

EP - 277

JO - IEEE Transactions on Systems, Man, and Cybernetics Part A:Systems and Humans.

JF - IEEE Transactions on Systems, Man, and Cybernetics Part A:Systems and Humans.

SN - 1083-4427

IS - 2

ER -