Koordinirano upravljanje mrežom raskrižja sa semaforima primjenom umjetne inteligencije

master's thesis

• Title (english): Coordinated Traffic Signal Control of Signalized Intersection Network Using Artificial Intelligence
• Author: Josip Miloš
• Mentor: Edouard Ivanjko (mentor)
• Committee member: Luka Novačko (predsjednik povjerenstva)
• Committee member: Martin Gregurić (član povjerenstva)
• Committee member: Miroslav Vujić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Transport and Traffic Sciences; (Division of Intelligent Transport Systems and Logistics); (Department of Intelligent Transport Systems); Zagreb
• Defense date and country: 2022-09-22, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Traffic and Transport Technology; Intelligent Transport Systems and Logistics

Abstract

Razvojem industrije transporta i svakodnevnim povećanjem broja vozila javlja se sve veći problem zagušenja u gradovima. Nastala zagušenja karakterizirana su malim brzinama i velikom gustoćom prometnog toka što značajno utječe na smanjenje razine uslužnosti (engl. Level of Service - LoS). Kako bi se smanjio utjecaj zagušenja prometnog toka razvijeni su različiti sustavi upravljanja iz domene inteligentnih transportnih sustava (engl. Intelligent Transport Systems - ITS). Najčešće korišteni sustavi upravljanja raskrižjima sa semaforima u gradovima zasnivaju se na implementaciji ustaljenih (engl. Fixed-Time) ili prometno ovisnih (engl. Traffic Actuated) sustava upravljanja. Napredniji sustavi upravljanja zasnivaju se na adaptivnom upravljanju (engl. Adaptive Traffic Control Systems - ATCS). Tako današnji ATCS sustavi primjenjuju napredne tehnologije umjetne inteligencije (engl. Artificial Intelligence) za rješavanje problema zagušenja na raskrižjima sa semaforima. Unutar ovog rada uspješno je implementiran upravlja čki algoritam zasnovan na umjetnoj inteligenciji primjernom PTV Vissim simulacijskog alata i objektno orijentiranog programskog jezika C#. Implementirani algoritam upravljanja koristi genetski algoritam (engl. Genetic Algorithm) i umjetne neuronske mreže (engl. Artificial Neural Networks). Analizom dobivenih rezultata postignuto je znatno poboljšanje ukupnog vremena putovanja (engl. Total Travel Time), kašnjenja (engl. Delay) i broja stajanja (engl. Number of stops). Takoder je prikazano da se primjenom tehnologija umjetne inteligencije značajno može poboljšati upravljanje mrežom raskrižja sa semaforima.

Abstract (english)

With the development of the transport industry and the daily increase in the number of vehicles, there is an increasing problem of congestion in cities. The resulting congestion is characterized by low speeds and high traffic flow density, which significantly reduces the Level of Service. To reduce the effects of traffic congestion, various traffic control systems from the domain of Intelligent Transport Systems have been developed. The most commonly used control systems for intersections with traffic lights in cities are based on the implementation of fixed-time or traffic-actuated control systems. More advanced control systems are based on Adaptive Traffic Control Systems (ATCS). Thus, today’s ATCS apply advanced technologies of Artificial Intelligence to solve the problem of congestion at intersections with traffic lights. In this thesis, a control algorithm based on Artificial Intelligence, with the use of the PTV Vissim simulation tool and objective-oriented programming language C#, was successfully implemented. The traffic control algorithm uses the Genetic Algorithm and Artificial Neural Networks to achieve traffic control. The analysis of the obtained results showed a significant reduction in Total Travel Time, delay, and the number of vehicle stops. It was also shown that the traffic control of a network of signalized intersections can be significantly improved by applying Artificial Intelligence based technology.

• Keywords: Inteligentni transportni sustavi; mreža raskrižja sa semaforima; signalni plan; neuronske mreže; genetski algoritam
• Keywords (english): Intelligent Transport Systems; Signalized Intersection Network; Traffic Signal Program; Neural Networks; Genetic Algorithm
• Language: croatian
• URN:NBN: urn:nbn:hr:119:127983
• Study programme: Title: Intelligent Transport Systems and Logistics; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka prometa (magistar/magistra inženjer/inženjerka prometa)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Open access
• Created on: 2022-12-09 16:53:10