The effect of elite pool in hybrid population-based meta-heuristics for solving combinatorial optimization problems

Ghaith Jaradat, Masri Ayob, Ibrahim Almarashdeh

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

This work investigates the effect of elite pool that has high-quality and diverse solutions in three hybrid population-based meta-heuristics with an elite pool of a hybrid Elitist-Ant System, a hybrid Big Bang-Big Crunch optimization, and a hybrid scatter search. The purpose of incorporating an elite pool in population-based meta-heuristics is to maintain the diversity of the search while exploiting the solution space as in the reference set of the scatter search. This may guarantee the effectiveness and efficiency of the search, which could enhance the performance of the algorithms and generalized well across different datasets. To test the generality of these meta-heuristics via their consistency and efficiency, we use three classes of well-known combinatorial optimization problems as follows: symmetric traveling salesman problem, 0-1 multidimensional knapsack problem, and capacitated vehicle routing problem. Experimental results showed that the performance of our hybrid population-based meta-heuristics, compared to the best known results, is competitive in many instances. This finding indicates the effectiveness of utilizing an elite pool in our hybrid meta-heuristics in diversifying the search and subsequently enhances their performance over different instances and problems.

Original languageEnglish
Pages (from-to)45-56
Number of pages12
JournalApplied Soft Computing Journal
Volume44
DOIs
Publication statusPublished - 1 Jul 2016

Fingerprint

Combinatorial optimization
Vehicle routing
Traveling salesman problem

Keywords

  • Big Bang-Big Crunch
  • Combinatorial optimization problems
  • Elite pool
  • Elitist-Ant System
  • Hybrid meta-heuristics
  • Scatter search

ASJC Scopus subject areas

  • Software

Cite this

The effect of elite pool in hybrid population-based meta-heuristics for solving combinatorial optimization problems. / Jaradat, Ghaith; Ayob, Masri; Almarashdeh, Ibrahim.

In: Applied Soft Computing Journal, Vol. 44, 01.07.2016, p. 45-56.

Research output: Contribution to journalArticle

@article{efe4cc3db5e14c3c969e6bd4fc2480c6,
title = "The effect of elite pool in hybrid population-based meta-heuristics for solving combinatorial optimization problems",
abstract = "This work investigates the effect of elite pool that has high-quality and diverse solutions in three hybrid population-based meta-heuristics with an elite pool of a hybrid Elitist-Ant System, a hybrid Big Bang-Big Crunch optimization, and a hybrid scatter search. The purpose of incorporating an elite pool in population-based meta-heuristics is to maintain the diversity of the search while exploiting the solution space as in the reference set of the scatter search. This may guarantee the effectiveness and efficiency of the search, which could enhance the performance of the algorithms and generalized well across different datasets. To test the generality of these meta-heuristics via their consistency and efficiency, we use three classes of well-known combinatorial optimization problems as follows: symmetric traveling salesman problem, 0-1 multidimensional knapsack problem, and capacitated vehicle routing problem. Experimental results showed that the performance of our hybrid population-based meta-heuristics, compared to the best known results, is competitive in many instances. This finding indicates the effectiveness of utilizing an elite pool in our hybrid meta-heuristics in diversifying the search and subsequently enhances their performance over different instances and problems.",
keywords = "Big Bang-Big Crunch, Combinatorial optimization problems, Elite pool, Elitist-Ant System, Hybrid meta-heuristics, Scatter search",
author = "Ghaith Jaradat and Masri Ayob and Ibrahim Almarashdeh",
year = "2016",
month = "7",
day = "1",
doi = "10.1016/j.asoc.2016.01.002",
language = "English",
volume = "44",
pages = "45--56",
journal = "Applied Soft Computing",
issn = "1568-4946",
publisher = "Elsevier BV",

}

TY - JOUR

T1 - The effect of elite pool in hybrid population-based meta-heuristics for solving combinatorial optimization problems

AU - Jaradat, Ghaith

AU - Ayob, Masri

AU - Almarashdeh, Ibrahim

PY - 2016/7/1

Y1 - 2016/7/1

N2 - This work investigates the effect of elite pool that has high-quality and diverse solutions in three hybrid population-based meta-heuristics with an elite pool of a hybrid Elitist-Ant System, a hybrid Big Bang-Big Crunch optimization, and a hybrid scatter search. The purpose of incorporating an elite pool in population-based meta-heuristics is to maintain the diversity of the search while exploiting the solution space as in the reference set of the scatter search. This may guarantee the effectiveness and efficiency of the search, which could enhance the performance of the algorithms and generalized well across different datasets. To test the generality of these meta-heuristics via their consistency and efficiency, we use three classes of well-known combinatorial optimization problems as follows: symmetric traveling salesman problem, 0-1 multidimensional knapsack problem, and capacitated vehicle routing problem. Experimental results showed that the performance of our hybrid population-based meta-heuristics, compared to the best known results, is competitive in many instances. This finding indicates the effectiveness of utilizing an elite pool in our hybrid meta-heuristics in diversifying the search and subsequently enhances their performance over different instances and problems.

AB - This work investigates the effect of elite pool that has high-quality and diverse solutions in three hybrid population-based meta-heuristics with an elite pool of a hybrid Elitist-Ant System, a hybrid Big Bang-Big Crunch optimization, and a hybrid scatter search. The purpose of incorporating an elite pool in population-based meta-heuristics is to maintain the diversity of the search while exploiting the solution space as in the reference set of the scatter search. This may guarantee the effectiveness and efficiency of the search, which could enhance the performance of the algorithms and generalized well across different datasets. To test the generality of these meta-heuristics via their consistency and efficiency, we use three classes of well-known combinatorial optimization problems as follows: symmetric traveling salesman problem, 0-1 multidimensional knapsack problem, and capacitated vehicle routing problem. Experimental results showed that the performance of our hybrid population-based meta-heuristics, compared to the best known results, is competitive in many instances. This finding indicates the effectiveness of utilizing an elite pool in our hybrid meta-heuristics in diversifying the search and subsequently enhances their performance over different instances and problems.

KW - Big Bang-Big Crunch

KW - Combinatorial optimization problems

KW - Elite pool

KW - Elitist-Ant System

KW - Hybrid meta-heuristics

KW - Scatter search

UR - http://www.scopus.com/inward/record.url?scp=84962679689&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84962679689&partnerID=8YFLogxK

U2 - 10.1016/j.asoc.2016.01.002

DO - 10.1016/j.asoc.2016.01.002

M3 - Article

AN - SCOPUS:84962679689

VL - 44

SP - 45

EP - 56

JO - Applied Soft Computing

JF - Applied Soft Computing

SN - 1568-4946

ER -