Analiza metoda predviđanja prometa u optičkoj mreži

master's thesis

• Title (english): Analysis of Traffic Forecasting Methods in the Optical Network
• Author: Antonio Brdar
• Mentor: Ivan Grgurević (mentor)
• Committee member: Marko Periša (predsjednik povjerenstva)
• Committee member: Petra Teskera (član povjerenstva)
• Committee member: Ivan Cvitić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Transport and Traffic Sciences; (Division of Transport); (Department of Information and Communications Traffic); Zagreb
• Defense date and country: 2024-07-02, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Traffic and Transport Technology; Postal and Telecommunications Traffic

Abstract

Optička mreža je podatkovna komunikacijska mreža koja koristi tehnologiju svjetlovodnog vlakna za prijenos podataka, a karakterizira ju visoka propusnost i velika brzina prijenosa podataka. U ovom diplomskom radu opisane su neke od mogućih izvedbi, arhitekture tih izvedbi te neke od tehnologija koje se koriste u optičkim mrežama. Također su opisani i razni prometni parametri koji postoje u optičkim mrežama, neki od njih su specifični za većinu komunikacijskih mreža, dok su neki specifični isključivo za optičke mreže. Nadalje, prikazane su i objašnjene tehnike praćenja i prikupljanja prometnih podataka u optičkim mrežama. Uz navedene prikazane su i analizirane relevantne metode i tehnike strojnog učenja u optičkim mrežama, a koje mogu poslužiti za predviđanje varijabilnosti odabranih prometnih parametra. U diplomskom radu je također objedinjena i prikazana praktična primjena odabranih metoda strojnog učenja kroz relevantna dostupna istraživanja.

Abstract (english)

An optical network is a data communication network that uses fiber optic technology for data transmission, characterized by high bandwidth and high data transfer speeds. This thesis describes some of the possible implementations, architectures of these implementations, and some of the technologies used in optical networks. Various traffic parameters existing in optical networks are also described, some of which are common to most communication networks, while others are specific to optical networks. Furthermore, techniques for monitoring and collecting traffic data in optical networks are presented and explained. In addition, relevant machine learning methods and techniques in optical networks that can be used to predict the variability of selected traffic parameters are also analyzed. The thesis also consolidates and presents the practical application of selected machine learning methods through relevant available research.

• Keywords: optička mreža; prometni parametri; prikupljanje podataka; strojno učenje; predviđanje prometnih parametara
• Keywords (english): optical network; traffic parameters; data collection; machine learning; forecasting of traffic parameters
• Language: croatian
• URN:NBN: urn:nbn:hr:119:792460
• Study programme: Title: Transport; specializations in: Road Transport, Rail Transport, Water Transport, Air Transport, Postal Transport, Information and Communication Traffic, Urban Transport; Course: Road Transport; Study programme type: university; Study level: graduate; Academic / professional title: sveučilišni/a magistar/magistra inženjer/inženjerka prometa (sveučilišni/a magistar/magistra inženjer/inženjerka prometa)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Open access
• Created on: 2024-07-12 13:20:24