Usporedba sinkronog i asinkronog obnavljanja populacije u algoritmu diferencijalne evolucije

Veselčić, Valentin

prikaz prve stranice dokumenta Usporedba sinkronog i asinkronog obnavljanja populacije u algoritmu diferencijalne evolucije

Download
PDF 1.33 MB

undergraduate thesis

Usporedba sinkronog i asinkronog obnavljanja populacije u algoritmu diferencijalne evolucije

2024. urn:nbn:hr:200:370484

Veselčić, Valentin

Josip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Department of Software Engineering
Chair of Programming Languages and Systems

Cite this document

APA 6th Edition

Veselčić, V. (2024). Usporedba sinkronog i asinkronog obnavljanja populacije u algoritmu diferencijalne evolucije (Undergraduate thesis). Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek. Retrieved from https://urn.nsk.hr/urn:nbn:hr:200:370484

MLA 8th Edition

Veselčić, Valentin. "Usporedba sinkronog i asinkronog obnavljanja populacije u algoritmu diferencijalne evolucije." Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2024. https://urn.nsk.hr/urn:nbn:hr:200:370484

Chicago 17th Edition

Harvard

Veselčić, V. (2024). 'Usporedba sinkronog i asinkronog obnavljanja populacije u algoritmu diferencijalne evolucije', Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 01 January 2025, https://urn.nsk.hr/urn:nbn:hr:200:370484

Vancouver

Veselčić V. Usporedba sinkronog i asinkronog obnavljanja populacije u algoritmu diferencijalne evolucije [Undergraduate thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2024 [cited 2025 January 01] Available at: https://urn.nsk.hr/urn:nbn:hr:200:370484

IEEE

V. Veselčić, "Usporedba sinkronog i asinkronog obnavljanja populacije u algoritmu diferencijalne evolucije", Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Osijek, 2024. Available at: https://urn.nsk.hr/urn:nbn:hr:200:370484

Cite this item: https://urn.nsk.hr/urn:nbn:hr:200:370484

Please login to the repository to save this object to your list.

Metadata

Title	Usporedba sinkronog i asinkronog obnavljanja populacije u algoritmu diferencijalne evolucije
Title (english)	Comparison of synchronous and asynchronous population update in differential evolution
Author	Valentin Veselčić
Mentor	Dražen Bajer (mentor)
Committee member	Dražen Bajer (predsjednik povjerenstva)
Committee member	Goran Knežević (član povjerenstva)
Committee member	Ivica Lukić (član povjerenstva)
Granter	Josip Juraj Strossmayer University of Osijek Faculty of Electrical Engineering, Computer Science and Information Technology Osijek (Department of Software Engineering) (Chair of Programming Languages and Systems) Osijek
Defense date and country	2024-09-26, Croatia
Scientific / art field, discipline and subdiscipline	TECHNICAL SCIENCES Computing Artificial Intelligence
Abstract	U radu su razmotrene dvije inačice algoritma diferencijalne evolucije, jednog od najpopularnijih evolucijskih algoritama koji se pokazao vrlo učinkovit za probleme kontinuirane optimizacije. Inačice se razlikuju samo u načinu obnavljanja populacije, jedna sa sinkronim gdje se populacija obnavlja generaciju po generaciju, a druga sa asinkronim gdje se populacija obnavlja odmah kada su nova kvalitetnija rješenja dostupna. Upotrebom ostvarenog programskog rješenja provedena je eksperimentalna analiza u kojoj su dvije inačice algoritma primijenjene na deset često korištenih testnih funkcija pri dvije različite dimenzionalnosti. Također je razmotren utjecaj parametra veličine populacije korištenjem tri različite vrijednosti istog. Ostvareni rezultati daju uvid u to kako način obnavljanja populacije direktno utječe na performanse algoritma. Daljnjom usporedbom dvije inačice primijećeno je da ona sa asinkronom implementacijom obnavljanja populacije ostvaruje bolje performanse u usporedbi sa standardnom, sinkronom inačicom u većini slučajeva.
Abstract (english)	The thesis discusses two implementations of the differential evolution algorithm, one of the most popular evolutionary algorithms, which has proven to be highly effective in problems of continuous optimization. The implementations differ only in the method of population updating: one using a synchronous method, where the population is updated generation by generation, and the other using an asynchronous method, where the population is updated immediately when new, better solutions become available. Using the implemented software solution, an experimental analysis was conducted in which the two implementations of the algorithm were applied to ten commonly used benchmark functions at two different dimensionalities. The impact of the population size parameter was also examined by using three different values of it. The obtained results provide insight into how the method of population updating directly affects the algorithm's performance. Further comparison of the two variants revealed that the asynchronous implementation achieves better performance compared to the standard synchronous implementations in most cases.
Keywords
Keywords (english)
Language	croatian
URN:NBN	urn:nbn:hr:200:370484
Study programme	Title: Undergraduate University Study Programme in Computer Engineering Study programme type: university Study level: undergraduate Academic / professional title: sveučilišni/sveučilišna provostupnik/prvostupnica (baccalaureus/baccalaurea) inženjerka računarstva (sveučilišni/sveučilišna provostupnik/prvostupnica (baccalaureus/baccalaurea) inženjerka računarstva)
Type of resource	Text
File origin	Born digital
Access conditions	Open access
Terms of use
Created on	2024-09-30 08:26:36