Impact of Boundary Control Methods on Bound-constrained Optimization Benchmarking

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F70883521%3A28140%2F22%3A63549578" target="_blank" >RIV/70883521:28140/22:63549578 - isvavai.cz</a>

Výsledek na webu

<a href="https://ieeexplore.ieee.org/abstract/document/9878135" target="_blank" >https://ieeexplore.ieee.org/abstract/document/9878135</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/TEVC.2022.3204412" target="_blank" >10.1109/TEVC.2022.3204412</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Impact of Boundary Control Methods on Bound-constrained Optimization Benchmarking

Popis výsledku v původním jazyce

Benchmarking various metaheuristics and their new enhancements, strategies, and adaptation mechanisms has become standard in computational intelligence research. Recently, many challenges and issues regarding fair comparisons and recommendations towards good practices for benchmarking of metaheuristic algorithms, have been identified. This paper is aimed at an important issues in metaheuristics design and benchmarking, which are boundary strategies or boundary control methods (BCM). This work aims to investigate whether the choice of a BCM could significantly influence the performance of competitive algorithms. The experiments encompass the top three performing algorithms from IEEE CEC competitions 2017 and 2020 with six different boundary control methods. We provide extensive statistical analysis and rankings resulting in conclusions and recommendations for metaheuristics researchers and possibly also for the future direction of benchmark definitions. We conclude that the BCM should be considered another vital metaheuristics input variable for unambiguous reproducibility of results in benchmarking and for a better understanding of population dynamics, since the BCM setting could impact the optimization method performance.

Název v anglickém jazyce

Impact of Boundary Control Methods on Bound-constrained Optimization Benchmarking

Popis výsledku anglicky

Benchmarking various metaheuristics and their new enhancements, strategies, and adaptation mechanisms has become standard in computational intelligence research. Recently, many challenges and issues regarding fair comparisons and recommendations towards good practices for benchmarking of metaheuristic algorithms, have been identified. This paper is aimed at an important issues in metaheuristics design and benchmarking, which are boundary strategies or boundary control methods (BCM). This work aims to investigate whether the choice of a BCM could significantly influence the performance of competitive algorithms. The experiments encompass the top three performing algorithms from IEEE CEC competitions 2017 and 2020 with six different boundary control methods. We provide extensive statistical analysis and rankings resulting in conclusions and recommendations for metaheuristics researchers and possibly also for the future direction of benchmark definitions. We conclude that the BCM should be considered another vital metaheuristics input variable for unambiguous reproducibility of results in benchmarking and for a better understanding of population dynamics, since the BCM setting could impact the optimization method performance.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2022

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

IEEE Transactions on Evolutionary Computation

ISSN

1089-778X

e-ISSN

1941-0026

Svazek periodika

26

Číslo periodika v rámci svazku

6

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

10

Strana od-do

1271-1280

Kód UT WoS článku

000892933300008

EID výsledku v databázi Scopus

2-s2.0-85137939631