Određivanje topologije elektroenergetskog sustava primjenom neuronskih mreža

scientific master's theses

• Title (english): Power System Topology Identification Using Neural Networks
• Author: Marko Delimar
• Mentor: Zdravko Hebel (mentor)
• Committee member: Ivica Pavić (predsjednik povjerenstva)
• Committee member: Zdravko Hebel (član povjerenstva)
• Committee member: Srete Nikolovski (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; (Department of Energy and Power Systems); Zagreb
• Defense date and country: 2001-09-26, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Electrical Engineering; Power Engineering
• Universal decimal classification (UDC): 621.3 - Electrical engineering

Abstract

Procjena stanja elektroenergetskog sustava je osnovna funkcija za vođenje i analizu elektroenergetskog sustava. Kako se topološka struktura mreže tijekom pogona mijenja, prije procjene stanja potrebno je provjeriti ispravnost prijavljene topološke strukture sustava jer su u suprotnom moguće vrlo grube pogreške u procjeni stanja. U radu je prikazan model za provjeru topološke strukture elektroenergetskog sustava zasnovan za neuronskim mrežama. Postupak je podijeljen u dva dijela. Prvi dio predstavlja model za određivanje točnog broja mrežnih čvorišta, a drugi analizu njihove povezanosti. Uspoređeno je više arhitektura neuronskih mreža isprobanih na više elektroenergetskih mreža. Prikazani su i analizirani rezultati dobiveni primjenom višeslojnog perceptona učenog algoritmom povratnog prostiranja izlazne pogreške.

Abstract (english)

Power system state estimation is a basic function in power system control and analysis. The topological structure of the power system changes during power system operation and must be checked before state estimation to avoid gross error during state estimation. This paper present a model for identifying anomalies in power system topology based on neural networks. The procedure is divided into two parts: nodes and branch processing. Several types of neural networks are tried out on different power system network configurations. The results obtained using multilayer percepton with backpropagation learning algorithm are presented and analysed.

• Keywords: Topologija; pogreške; neuronske mreže; elektroenergetski sustav; procjena stanja
• Keywords (english): Topology; anomalies; neural networks; power system; state estimation
• Language: croatian
• URN:NBN: urn:nbn:hr:168:558817
• Study programme: Title: Postgraduate master programme in electrical engineering; Study programme type: university; Study level: postgraduate; Academic / professional title: Magistar znanosti elektrotehnike (Magistar znanosti elektrotehnike)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2019-04-19 08:47:40