Optimizacija parametrov simuliranega socialno-ekonomskega sistema z genetskim algoritmom

diplomsko delo

Aljaž Borko (Author), Damjan Strnad (Mentor), Nikola Guid (Co-mentor)

Abstract

V diplomskem delu je predstavljen genetski algoritem in njegova implementacija za optimiziranje parametrov v simuliranem socialno-ekonomskem sistemu, v katerem nastopajo entitete, kot so agenti, drevesa, hrana itd. Vsak tip entitete ima svoje lastnosti in omejitve. Delovanje sistema je predpisano z implicitnimi pravili, ki določajo medsebojne vplive entitet. Parametri, ki jih optimiziramo, vplivajo na obnašanje agentov, ki so glavni skrbniki sistema. S tem želimo vzpostaviti stabilen sistem, ki bi preživel čim dlje. V diplomskem delu pokažemo, da lahko ta cilj dosežemo s pomočjo genetskega algoritma, ki poišče optimalne vrednosti omenjenih parametrov.

Keywords

genetski algoritmi;evolucijski algoritmi;simulacija;optimizacija parametrov;

Data

Language:	Slovenian
Year of publishing:	2014
Typology:	2.11 - Undergraduate Thesis
Organization:	UM FERI - Faculty of Electrical Engineering and Computer Science
Publisher:	[A. Borko]
UDC:	004.986(043.2)
COBISS:	18287126
Views:	1129
Downloads:	71
Average score:	0 (0 votes)
Metadata:

Other data

Secondary language:	English
Secondary title:	OPTIMIZATION OF PARAMETERS OF SIMULATED SOCIAL-ECONOMIC SYSTEM WITH GENETIC ALGORITHM
Secondary abstract:	This diploma paper discusses genetic algorithm and its implementation in order to optimize parameters in a simulated socio-economic system, including entities such as agents, trees, food, etc. Each type of entity has its own characteristics and limitations. Activity of the system is in accordance to rules and regulations of implicit standards that determine interacting influences of entities. When parameters are optimised, they influence the behaviour of agents that are the systems main administrators. Thus, this enables us to establish a stable system with the longest survival time possible. As shown in this paper, this can be achieved by using genetic algorithm that establishes optimal values of mentioned parameters.
Secondary keywords:	genetic algorithm;evolution algorithm;stsimulation;parameter optimization;
URN:	URN:SI:UM:
Type (COBISS):	Bachelor thesis/paper
Thesis comment:	Univ. v Mariboru, Fak. za elektrotehniko, računalništvo in informatiko
Pages:	VIII, 25 f.
ID:	8730252