| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

Show document Help

Title:Uporaba paralelnih evolucijskih algoritmov za reševanje več-kriterijskih optimizacijskih problemov : magistrsko delo
Authors:ID Gartner, Aleš (Author)
ID Fister, Iztok (Mentor) More about this mentor... New window
Files:.pdf MAG_Gartner_Ales_2024.pdf (1,73 MB)
MD5: BABC4692A025154032397966AAE52D83
 
Language:Slovenian
Work type:Master's thesis/paper
Typology:2.09 - Master's Thesis
Organization:FERI - Faculty of Electrical Engineering and Computer Science
Abstract:V sklopu magistrskega dela predstavimo in implementiramo nov paralelni evolucijski algoritem z otoškim paralelnim modelom I-DEMO, ki algoritem diferencialne evolucije za več-kriterijsko optimizacijo (angl. Differential Evolution Multiobjective Optimization, krajše DEMO) razširi s koncepti paralelnih več-kriterijskih evolucijskih algoritmov. Učinkovitost algoritma I-DEMO nato primerjamo z originalnim algoritmom DEMO na testnih več-kriterijskih problemih. S statistično analizo dobljenih rezultatov smo pokazali, da je algoritem I-DEMO boljši od algoritma DEMO, če oba uporabljata selekcijsko strategijo, ki temelji na indikatorjih kakovosti. Z dodatnimi testi in analizo njihovih rezultatov smo pokazali tudi, da različica algoritma I-DEMO, ki uporablja selekcijsko strategijo, ki temelji na indikatorjih kakovosti, dosega boljše rezultate kot ostale selekcijske strategije, in da večje število otokov v splošnem poslabša učinkovitost algoritma.
Keywords:več-kriterijska optimizacija, evolucijsko računanje, paralelni evolucijski algoritmi, diferencialna evolucija
Place of publishing:Maribor
Place of performance:Maribor
Publisher:[A. Gartner]
Year of publishing:2024
Number of pages:1 spletni vir (1 datoteka PDF (IX, 50 str.))
PID:20.500.12556/DKUM-91392 New window
UDC:004.8.021(043.2)
COBISS.SI-ID:227270659 New window
Publication date in DKUM:06.02.2025
Views:222
Downloads:31
Metadata:XML DC-XML DC-RDF
Categories:KTFMB - FERI
:
Copy citation
  
Average score:(0 votes)
Your score:Voting is allowed only for logged in users.
Share:Bookmark and Share



Hover the mouse pointer over a document title to show the abstract or click on the title to get all document metadata.

Licences

License:CC BY-NC-ND 4.0, Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International
Link:http://creativecommons.org/licenses/by-nc-nd/4.0/
Description:The most restrictive Creative Commons license. This only allows people to download and share the work for no commercial gain and for no other purposes.
Licensing start date:18.12.2024

Secondary language

Language:English
Title:Using Parallel Evolutionary Algorithms for solving Multi-Objective Optimization problems
Abstract:As part of our thesis, we have presented and implemented a new parallel evolutionary algorithm I-DEMO using the island parallel model, which extends the Differential Evolution for Multi-Objective Optimization algorithm with concepts of Parallel Multi-Objective Evolutionary Algorithms. The performance of the I-DEMO algorithm is then compared with the original DEMO algorithm on multi-objective test problems. By statistically analysing the results obtained, we show that the I-DEMO algorithm outperforms the DEMO algorithm when both use a selection strategy based on quality indicators. By running additional tests and analysing their results, we have also shown that the version of the I-DEMO algorithm that uses a selection strategy based on quality indicators performs better than other selection strategies and that a larger number of islands tends to degrade the performance of the algorithm.
Keywords:multi-objective optimization, evolutionary computing, parallel evolutionary algorithms, differential evolution


Comments

Leave comment

You must log in to leave a comment.

Comments (0)
0 - 0 / 0
 
There are no comments!

Back
Logos of partners University of Maribor University of Ljubljana University of Primorska University of Nova Gorica