Višeagentski sustav za nadzor i predviđanje potrošnje u sustavu plinoopskrbe

master's thesis

• Title (english): Multi-agent system for monitoring and prediction of consumption in the gas supply system
• Author: Lea Ming Li
• Mentor: Gordan Ježić (mentor)
• Committee member: Gordan Ježić (predsjednik povjerenstva)
• Committee member: Mario Kušek (član povjerenstva)
• Committee member: Krunoslav Tržec (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2022-07-07, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Electrical Engineering

Abstract

Višeagentski sustavi preraspodjeljuju velike zadatke na manje zadatke s ciljem ubrzanja, učinkovitosti, skalabilnosti i fleksibilnosti. Inteligentni agenti posjeduju svojstvo reaktivnosti, socijalne sposobnosti i učenja u svrhu autonomnog djelovanja i ispunjenja zadanih ciljeva. U ovom radu korišten je višeagentski sustav za simulaciju sustava za plinoopskrbu. U sklopu rada opisani su agenti za vršenje predviđanja potrošnje plina u kućanstvu i industrijskom postrojenju te agent zadužen za vršenje revizije predviđene potrošnje. Višeagentski sustav razvijen je koristeći programski jezik Python.

Abstract (english)

Multi-agent systems redistribute large tasks into smaller tasks with the goal of acceleration, efficiency, scalability, and flexibility. Intelligent agents possess the property of reactivity, social ability, and learning for the purpose of acting autonomously and meeting set goals. In this paper, a multi-agent system was used to simulate the gas supply system. The paper describes agents for forecasting gas consumption in households and industrial plants and the agent in charge of auditing projected consumption. The multi-agent system was developed using the Python programming language.

• Keywords: Umjetna neuronska mreža; višeagentski sustavi; programski agenti
• Keywords (english): Artificial neural network; multi-agent systems; software agents
• Language: croatian
• URN:NBN: urn:nbn:hr:168:455235
• Study programme: Title: Information and Communication Technology; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka informacijske i komunikacijske tehnologije (magistar/magistra inženjer/inženjerka informacijske i komunikacijske tehnologije)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-14 09:17:19