Procjena statičke sigurnosti elektroenergetskih mreža

doctoral thesis

• Title (english): Static Security Assessment of Power Networks
• Author: Marko Delimar
• Mentor: Zdravko Hebel (mentor)
• Committee member: Ivica Pavić (član povjerenstva)
• Committee member: Zdravko Hebel (član povjerenstva)
• Committee member: Srete Nikolovski (član povjerenstva)
• Committee member: Sven Lončarić (član povjerenstva)
• Committee member: Vladimir Mikuličić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; (Department of Energy and Power Systems); Zagreb
• Defense date and country: 2005-10-27, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Electrical Engineering; Power Engineering
• Universal decimal classification (UDC): 621.3; APPLIED SCIENCES. MEDICINE. TECHNOLOGY; Electrical engineering

Abstract

Vođenje modernog elektroenergetskog sustava je balans između ekonomskih i sigurnosnih zahtjeva. Zadatak ovog rada bio je ispitati mogućnosti primjene neuronskih mreža pri procjeni statičke sigurnosti mreže elektroenergetskog sustava. U radu su prikazani osnovni modeli za procjenu stanja i statičku procjenu sigurnosti elektroenergetskih mreža, kao i pregled primjena neuronskih mreža u elektroenergetici. U radu je predložena metoda za procjenu statičke sigurnosti elektroenergetskih mreža temeljena na višeslojnom perceptronu, čiji su ulazni podaci tokovi snaga u stacionarnom stanju elektroenergetske mreže, a izlazni podaci indeksi djelovanja povezani s pogonskim prekoračenjima nakon ispada elemenata mreže. Neuronska mreža učena je povratnim prostiranjem izlazne pogreške. U radu je prikazana i metoda za procjenu topološke strukture elektroenergetske mreže temeljena na neuronskim mrežama koja je poslužila kao temelj za analizu ispada. Predložene metode testirane su na IEEE test mreži od 24 čvorišta pri čemu su simulirana različita pogonska stanja.

Abstract (english)

The modern operation of an electric power system is often a balance between economic and security issues. The main goal of this research was to determine the possibilities of applying an artificial neural network to the power system static security assessment. In this thesis, basic state estimation and security assessment models were presented, as well as a short overview of neural networks applications to electric power engineering. This thesis has explored a multilayer perceptron neural network for static security assessment with power flows as inputs and post contingency performance indices as outputs. A backpropagation learning algorithm was used. As a basis for outage analysis, a neural network for topology identification was also discussed. The performance of the proposed methods was evaluated for different operating conditions using the IEEE 24bus test system.

• Keywords: Elektroenergetske mreže; statička sigurnost; nadzor i upravljanje; neuronske mreže; analiza slučajnih događaja; topološke analize
• Keywords (english): Electric power networks; steady-state security assessment; supervision and control; neural networks; contingency analysis; topology identification
• Language: croatian
• URN:NBN: urn:nbn:hr:168:083611
• Study programme: Title: Doctoral study programme "Electrical Engineering and Computing"; Study programme type: university; Study level: postgraduate; Academic / professional title: doktor/doktorica znanosti, po-dručje tehničkih znanosti (doktor/doktorica znanosti, po-dručje tehničkih znanosti)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2019-07-10 09:13:38