Detekcija otočnog pogona foto naponskih sustava metodama umjetne inteligencije

Mlakić, Dragan

doctoral thesis

Detekcija otočnog pogona foto naponskih sustava metodama umjetne inteligencije

Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2019. urn:nbn:hr:200:505475

Mlakić, Dragan

Josip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Department of Power Engineering
Chair of Power Systems and Substations

Cite this document

APA 6th Edition

Mlakić, D. (2019). Detekcija otočnog pogona foto naponskih sustava metodama umjetne inteligencije (Doctoral thesis). Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek. Retrieved from https://urn.nsk.hr/urn:nbn:hr:200:505475

MLA 8th Edition

Mlakić, Dragan. "Detekcija otočnog pogona foto naponskih sustava metodama umjetne inteligencije." Doctoral thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2019. https://urn.nsk.hr/urn:nbn:hr:200:505475

Chicago 17th Edition

Harvard

Mlakić, D. (2019). 'Detekcija otočnog pogona foto naponskih sustava metodama umjetne inteligencije', Doctoral thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 29 September 2023, https://urn.nsk.hr/urn:nbn:hr:200:505475

Vancouver

Mlakić D. Detekcija otočnog pogona foto naponskih sustava metodama umjetne inteligencije [Doctoral thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2019 [cited 2023 September 29] Available at: https://urn.nsk.hr/urn:nbn:hr:200:505475

IEEE

D. Mlakić, "Detekcija otočnog pogona foto naponskih sustava metodama umjetne inteligencije", Doctoral thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Osijek, 2019. Available at: https://urn.nsk.hr/urn:nbn:hr:200:505475

Cite this item: https://urn.nsk.hr/urn:nbn:hr:200:505475

Please login to the repository to save this object to your list.

Metadata

Title	Detekcija otočnog pogona foto naponskih sustava metodama umjetne inteligencije
Title (english)	Detection of island powered photo voltage systems by artificial intelligence methods
Author	Dragan Mlakić
Mentor	Srete Nikolovski (mentor)
Committee member	Marinko Barukčić (predsjednik povjerenstva)
Granter	Josip Juraj Strossmayer University of Osijek Faculty of Electrical Engineering, Computer Science and Information Technology Osijek (Department of Power Engineering) (Chair of Power Systems and Substations) Osijek
Defense date and country	2019-05-09, Croatia
Scientific / art field, discipline and subdiscipline	TECHNICAL SCIENCES Electrical Engineering Power Engineering
Universal decimal classification (UDC)	621.3 - Electrical engineering
Abstract	U doktorskom radu je predstavljena metodologija detekcije otočnog rada distribuiranih izvora energije uz pomoć metoda umjetne inteligencije (umjetne inteligencije) sa ciljem zadržavanja pasivne prirode metode detekcije a povećanja preciznosti, smanjenja vremena detekcije i zone ne-detekcije (zone ne detekcije). Predložena metodologija se sastoji od tri cjeline realizirane kroz 9 poglavlja: snimanje parametara mreže sa pametnim brojilom, treniranje umjetne inteligencije metoda sa slogovima podataka, testiranje metoda kroz standarde IEEE 1547 i UL 1741. Detekcija otočnog rada je realizirano kroz tri predložene metode: Adaptivni sustav neuro-neizrazitog zaključivanja(eng. Adaptive Neuro-Fuzzy Inference System - ANFIS), Duboko učenje (eng. Deep Learning - DL) i Metoda potpornih vektora (eng. Support Vector Machine - MPV). Mjerenja su prikupljeni podaci sa realnog foto-naponskog (FN) sustava uz pomoć kojih je modeliran model u programskom alatu Matlabu/Simulink za testiranje navedenih umjetne inteligencije metoda. Također su izmjereni rezultati korišteni za treniranje kognitivnih metoda. Ocjenjivanje efikasnosti metoda se radi prema navedenim standardima, te još tri vrste kvara na niskonaponskoj distribucijskoj mreži, još jednim distribuiranim izvorom na istoj točki spajanja distribuiranog izvora sa distribucijskoj mreži-om, brzo punjenje električnih i hibridnih automobila (PHEV), te promjeni faktora kvalitete mreže (Qf). Na kraju su predstavljeni rezultati od sve tri predložene umjetne inteligencije metode, kao sumarni prikaz u izvješću u poglavlju 8, te diskutirana moguća daljnja istraživanja u cilju poboljšanja navedena tri faktora metoda za detekciju otočnog rada.
Abstract (english)	The methodology for detecting islanding of Distributed Generators (DGs) in Distribution Network (DN) using the method of artificial intelligence (AI) is presented in the dissertation with the aim of retaining the passive nature of the detection method and increasing the precision, reduction of detection time and non-detection zone (NDZ). The proposed methodology consists of three units realized through 9 chapters: smart metering network parameters, training of AI methods using recorded data, testing methods through standards IEEE 1547 and UL 1741. Detection of the islanding is done through three proposed methods: Adaptive Neuro-Fuzzy Inference System 239 (ANFIS), Deep Learning (DL), and Vector Support Machine (MPV). The measurements were collected from the real photographic (FN) system used in modeling of testing simulation environment in Matlab / Simulink software to test these Artificial Intelligence methods. Measurement results were also used to train cognitive methods. Efficiency evaluation of the method is done according to the mentioned standards and three other situations in microgrid: fault on the low voltage distribution network, another distribution sources at the same point of common coupling of distribution source with distribution network, rapid charging of electric and hybrid cars (PHEV) and change of network quality factors (Qf). Finally, the results of all three proposed Artificial Intelligence methods are presented as a summary report in the chapter 8 and discussed possible further research to improve mentioned three factors of inslanding detection methods.
Keywords
Keywords (english)
Language	croatian
URN:NBN	urn:nbn:hr:200:505475
Promotion	2019-06-14
Study programme	Title: Postgraduate doctoral study programme; specializations in: branch Power Engineering and Communications, branch Informatics Course: branch Power Engineering and Communications Study programme type: university Study level: postgraduate Academic / professional title: doktor/doktorica znanosti, područje tehničkih znanosti, polje elektrotehnika (doktor/doktorica znanosti, područje tehničkih znanosti, polje elektrotehnika)
Type of resource	Text
File origin	Born digital
Access conditions	Open access
Terms of use
Repository	Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Created on	2019-09-03 12:08:13