Optimizacija prometnih semafora evolucijskim algoritmom

undergraduate thesis

• Title (english): Traffic lights optimization with a evolutionary algorithm
• Author: Marko Varga
• Mentor: Marin Golub (mentor)
• Committee member: Marin Golub (predsjednik povjerenstva)
• Committee member: Marin Kačan (član povjerenstva)
• Committee member: Ivan Grubišić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2024-07-04, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Opisano je modeliranje prometnih sustava simulacijskim paketom SUMO (Simulation of Urban Mobility). Definiran je problem optimizacije faza i intervala u ciklusu prometnog semafora. Predstavljene su dosadašnje prakse u programiranju semafora i razlozi uporabe evolucijskih algoritama u istom. Implementiran je genetski algoritam u Pythonu koristeći knjižicu PyGAD. Provedeni su eksperimenti na dva različita prometna opterećenja dionice Ulice grada Vukovara u Zagrebu i analizirani rezultati. Određeno je najbolje dobiveno rješenje i donesen zaključak da je najbolje koristiti znatno opterećeni sustav u optimizacijskom postupku.

Abstract (english)

The design of traffic systems in the simulation package SUMO (Simulation of Urban Mobility) is described. Optimization problem of phases and intervals of traffic light cycle is defined. Current practices in traffic light programming and reasons for using evolutionary algorithms are presented. The genetic algorithm was implemented in Python using PyGAD library. Two types of traffic flow on Grada Vukovara Street in Zagreb are used to optimize traffic lights and then the results are analyzed. The best solution is shown and it is discussed what type of traffic is needed to get the best possible results.

• Keywords: prometni semafor; problem optimizacije ciklusa semafora; SUMO; evolucijski algoritam; genetski algoritam
• Keywords (english): traffic light; optimization problem of traffic light cycle; SUMO; evolutionary algorithm; genetic algorithm
• Language: croatian
• URN:NBN: urn:nbn:hr:168:736394
• Study programme: Title: Computing; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2024-10-12 22:24:16