magistrsko delo
Abstract
Implementirali in analizirali smo moderni evolucijski algoritem po znanstvenem članku »The Whale Optimization Algorithm« avtorjev Seyedali Mirjalili in Andrew Lewis. Naredili smo primerjavo s podobnim algoritmom GWO istih avtorjev, opisanim v članku »Gray Wolf Optimizer«, in drugimi evolucijskimi algoritmi. Algoritem smo implementirali v programskem jeziku Java v sistemu za ocenjevanje evolucijskih algoritmov (angl. »evolutionary algorithm rating system«), znan tudi kot EARS [3]. Pri implementaciji smo se zgledovali po podani izvorni kodi avtorjev, napisani v Matlab-u [4]. Implementirali smo dva realna optimizacijska problema in algoritem na njima tudi preizkusili. Rezultate optimizacije problemov smo primerjali z rešitvami drugih algoritmov. Nenazadnje smo preverili pravilnost in točnost delovanja naše implementacije v primerjavi z izvorno kodo.
Keywords
evolucijski algoritmi;vzorci iz narave;optimizacijski algoritmi;optimizacija;magistrske naloge;
Data
Language: |
Slovenian |
Year of publishing: |
2020 |
Typology: |
2.09 - Master's Thesis |
Organization: |
UM FERI - Faculty of Electrical Engineering and Computer Science |
Publisher: |
[J. Krnc] |
UDC: |
004.8.021(043.2) |
COBISS: |
38011907
|
Views: |
332 |
Downloads: |
49 |
Average score: |
0 (0 votes) |
Metadata: |
|
Other data
Secondary language: |
English |
Secondary title: |
Analysis of the evolutionary Whale Optimization Algorithm |
Secondary abstract: |
In this thesis, the modern evolutionary algorithm described in Seyedali Mirjalili's and Andrew Lewis' article »The Whale Optimization Algorithm« was analysed and implemented. A detailed comparison was made with similar evolutionary algorithms, including the GWO algorithm presented by the same authors. The WOA algorithm was implemented in the Java programming language, in EARS (Evolutionary Algorithm Rating System) framework. Two real-world optimisation problems were implemented and solved with our WOA algorithm implementation. The results were compared with the results of other evolutionary algorithms. Finally, the results were compared to the authors’ Matlab source code. |
Secondary keywords: |
evolutionary algorithms;nature-inspired patterns;optimisation algorithms;optimisation; |
Type (COBISS): |
Master's thesis/paper |
Thesis comment: |
Univ. v Mariboru, Fak. za elektrotehniko, računalništvo in informatiko, Računalništvo in informacijske tehnologije |
Pages: |
90 f. |
ID: |
11991798 |