Predviđanje količine dolaznog i odlaznog prometa komunikacijskih mreža pomoću neuronske mreže

master's thesis

• Title (english): Prediction of Uplink and Downlink Traffic of Communication Networks using Neural Networks
• Author: Andrija Tomljenović
• Mentor: Edouard Ivanjko (mentor)
• Committee member: Marko Periša (predsjednik povjerenstva)
• Committee member: Ivan Cvitić (član povjerenstva)
• Committee member: Štefica Mrvelj (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: 2020-09-24, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Traffic and Transport Technology; Postal and Telecommunications Traffic

Abstract

U ovom diplomskom radu cilj je predvidjeti količina prometa na dolaznom i odlaznom linku koristeći neuronske mreže. Kreirano je nekoliko mreža koje su se na temelju prikupljenih podataka naučile karakteristici prometnog toka. Korišteni podatkovni skup prikupljan je unutar perioda od jedne godine u petominutnim koracima. Rezultati rada pokazuju da neuronska mreža ima vrlo dobru sposobnost naučiti proces prema predstavljenim podacima, ali i da rezultati koje mreža daje uvelike ovise o karakteristikama podatkovnog skupa na temelju kojega se uči.

Abstract (english)

Goal of this thesis is predicting amount of uplink and downlink traffic using neural networks. Several networks were created which, based on the collected data, learned the characteristics of the traffic flow. Used data set was collected over period of one year in five-minute steps. The results of this work show that neural network has a very good ability to learn the process according to the presented data, but also that the results that the network gives largely depend on the characteristics of the data set on which network has been learning.

• Keywords: neuronske mreže; umjetna inteligencija; predviđanje prometa; telekomunikacijske mreže
• Keywords (english): neural networks; artificial intelligence; traffic prediction; telecommunication networks
• Language: croatian
• URN:NBN: urn:nbn:hr:119:160199
• Study programme: Title: Traffic and Transport; specializations in: Road Traffic and Transport, Railway Traffic and Transport, Water Traffic and Transport, Air Traffic and Transport, Postal Traffic, Information and Communication Traffic, Urban Traffic and Transport; Course: Road Traffic and Transport; 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: 2020-11-06 12:37:47