Komunikacijski modeli za Edge/5G

master's thesis

• Title (english): Communication models for Edge/5G
• Author: Josip Lasić
• Mentor: Ivona Brandic (mentor); ISVU oznaka: IB341
• Committee member: Ivona Brandic (predsjednik povjerenstva); ISVU oznaka: IB341
• Committee member: Vincenzo de Maio (član povjerenstva); ISVU oznaka: VM183
• Committee member: Ivan Lujic (član povjerenstva); ISVU oznaka: IL127
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2020-08-05, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Nove IoT aplikacije se pojavljuju koje zahtijevaju odgovore u približno stvarnom vremenu. Strogi zahtjevi za latencijom važni su za primjenu u zdravstvu i pametnom prometu. U ovoj tezi je uzet primjer upravljanja prometom kao studija koja zahtjeva odgovor u gotovo stvarnom vremenu. Cilj ove studije je povećati sigurnost na cestama i spasiti živote najugroženijih korisnika ceste - pješaka i biciklista. Trenutna rješenja temeljena na oblaku nisu dovoljna da udovolje ovako strogim vremenskim ograničenjima zbog suštinskog problema oblaka - dugotrajno usmjerivanje paketa kroz Internet mrežu. Da bi se to otklonilo, potrebno je upotrijebiti nove tehnologije. Cilj edge rečunanja je približiti obradu lokaciji korisnika i smanjiti kašnjenje.

U ovoj se tezi obrada na rubu mreže stapa s 5G mrežom kako bi se postiglo maksimalno poboljšanje performansi komunikacije. Uz ove tehnologije, razmatraju se različiti komunikacijski modeli za primjenjivost u spomenutom primjeru prometa. Budući da su edge računanje i 5G mreže nove tehnologije, vrše se procjene stvarne izvedivosti studije. Procjene su provedene na različitim konfiguracijama brokera i mreže koristeći koncept edge obrade zajedno s 5G mrežom. Rezultati pokazuju značajno poboljšanje do 76,7% u vidu smanjenja kašnjenja u usporedbi s tradicionalnim rješenjima temeljenim na oblaku.

Abstract (english)

New IoT applications are emerging which require near real-time responses. Low latency requirements are important for life-critical applications in healthcare and smart traffic applications. In this thesis, smart traffic management is considered as a use case with near real-time requirements. This case study aims to increase road safety and save the lives of the road’s most vulnerable users - pedestrians and bicyclists. Current cloud-based solutions are not sufficient to meet such hard time constraint, because of the cloud’s intrinsic problem – long multi-hop Internet packet transfers. In order to solve it, new technologies need to be employed. Edge computing aims to bring computation closer to the users’ location and reduce delay.

In this thesis, edge computing is fused with 5G network to achieve the maximum communication performance improvements. In addition to these technologies, different communication models are considered for applicability with the mentioned traffic use case. Since edge computing and 5G networks are emerging technologies, evaluations are made for the assessment of the use case’s real-world feasibility. Evaluations were carried across different broker and network configurations using the edge computing concept together with 5G network connection. The results show a significant improvement of up to 76.7% in decreased latency compared to traditional cloud-based solutions.

• Keywords: komunikacijski modeli; edge; 5g; IoT; mqtt
• Keywords (english): communication models; edge; 5g; IoT; mqtt
• Language: english
• URN:NBN: urn:nbn:hr:168:854590
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-13 09:14:43