Testing different evolution strategy selection strategies

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23210%2F18%3A43952644" target="_blank" >RIV/49777513:23210/18:43952644 - isvavai.cz</a>

Výsledek na webu

<a href="http://www.mmscience.eu/content/file/archives/MM_Science_2017110.pdf" target="_blank" >http://www.mmscience.eu/content/file/archives/MM_Science_2017110.pdf</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.17973/MMSJ.2018_03_2017110" target="_blank" >10.17973/MMSJ.2018_03_2017110</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Testing different evolution strategy selection strategies

Popis výsledku v původním jazyce

The paper deals with testing different selection strategies of Evolution Strategy on different discrete event simulation models. The models reflect real production systems in industrial companies. We specified different objective functions of models considering the simulated system. All possible solutions and their objective function values were mapped to find the global optimum in the search space. We tested different settings of selection strategies and other Evolution Strategy parameters using a simulation optimizer we developed for simulation optimization. We evaluated these settings by the success of finding the optimum by the optimization algorithms. We also used another evaluation criterion - the difference between the objective function value of the best solution found in the series (replication of optimization experiments with a concrete optimization method setting) and the optimum objective function value.

Název v anglickém jazyce

Testing different evolution strategy selection strategies

Popis výsledku anglicky

The paper deals with testing different selection strategies of Evolution Strategy on different discrete event simulation models. The models reflect real production systems in industrial companies. We specified different objective functions of models considering the simulated system. All possible solutions and their objective function values were mapped to find the global optimum in the search space. We tested different settings of selection strategies and other Evolution Strategy parameters using a simulation optimizer we developed for simulation optimization. We evaluated these settings by the success of finding the optimum by the optimization algorithms. We also used another evaluation criterion - the difference between the objective function value of the best solution found in the series (replication of optimization experiments with a concrete optimization method setting) and the optimum objective function value.

Druh

J_SC - Článek v periodiku v databázi SCOPUS

CEP obor

—

OECD FORD obor

20301 - Mechanical engineering

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2018

Kód důvěrnosti údajů

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

Název periodika

MM Science Journal

ISSN

1803-1269

e-ISSN

—

Svazek periodika

Neuveden

Číslo periodika v rámci svazku

March

Stát vydavatele periodika

CZ - Česká republika

Počet stran výsledku

10

Strana od-do

2290-2299

Kód UT WoS článku

—

EID výsledku v databázi Scopus

2-s2.0-85043400468