Energetski učinkovite tehnologije računarstva na rubu za IoT-uređaje

master's thesis

• Title (english): Energy-efficient edge computing technologies for IoT devices
• Author: Dominik Rozić
• Mentor: Gordan Ježić (mentor)
• Committee member: Gordan Ježić (predsjednik povjerenstva)
• Committee member: Ivana Podnar Žarko (član povjerenstva)
• Committee member: Mario Kušek (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2023-07-10, Croatia

Abstract

Energetska učinkovitost računalnih sustava sve je bitnija uz veću potrebu za računalnom snagom. Računarstvo na rubu i TinyML neke su od tehnologija kojima je cilj povećanje energetske učinkovitosti u sustavima Interneta stvari. TinyML omogućava strojno učenje na krajnjim uređajima u mreži s ograničenim resursima. Pri primjeni takvih tehnologija potrebno je obratiti pozornost na parametre koji utječu na energetsku učinkovitost. Predloženi sustav uz korištenje ESP32 mikrokontrolera i Raspberry Pi uređaja u ulozi rubnog poslužitelja omogućava energetski učinkovit sustav koji koristi TinyML za zadatke klasifikacije na krajnjem uredaju uz pametno korištenje različitih načina rada ESP uređaja koji pridonose manjoj potrošnji energije.

Abstract (english)

Energy efficiency of computing systems is getting more important with bigger
computing power needs. Edge computing and TinyML are some of the technologies that whose goal is to increase energy efficiency in Internet of Things. TinyML
is enabling machine learning on end devices with limited resources. When using these
technologies it is important to know what parameters are affecting the energy efficiency. The sugested system is using ESP32 microcontroller and Raspberry Pi which
acts as edge server to present an energy efficient system that uses TinyML for classification tasks on end device with smart usage of different sleep modes on ESP device
which improve its energy consumption.

• Keywords: Energija; ucinkovitost; ESP32; TinyML; poslužitelj; mikrokontroler; rub; IoT; oblak
• Keywords (english): Edge; TinyML; ESP32; microcontroller; IoT; energy; efficiency; cloud
• Language: croatian
• URN:NBN: urn:nbn:hr:168:313243
• 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: 2023-10-11 10:22:26