magistrsko delo
Matjaž Škrlec (Author), Urban Rudež (Mentor)

Abstract

Sprotna ocena elektroenergetskega sistema (EES) je za zagotovitev njegovega zanesljivega obratovanja ključnega pomena. Še posebej v razmerah z višjim deležem nekovencionalnih proizvodnih enot električne energije. Vsaka od vrst stabilnosti EES ima svoje zakonitosti in specifike, zato je za oceno vsake od njih zahtevan drugačen pristop. V magistrski nalogi je opisana metoda za sprotno oceno kotne stabilnosti za majhne motnje, ki ne uporablja sprotnega izračunavanja lastnih vrednosti in vektorjev. Glede na to, da so oboji močno odvisni od obratovalnega stanja EES (konvencionalni viri v obratovanju in njihova moč, razporeditev in višina odjema moči, topologija) katerih ponovljivost je precejšna, bo predstavljeni koncept temeljil na podatkovni bazi, ki vsebuje množico vnaprej analiziranih obratovalnih stanj. Iskanje dovoljšne podobnosti med dejanskim obratovalnih stanjem in tistim iz podatkovne baze pa se nato izvaja v realnem času. Jedro iskanja podobnosti je odločitveno drevo, ki najprej v dveh slojih opredeli obratovalno stanje glede na dva ključna kriterija (vključeni viri, topologija). Dalje sledi primerjava podobnosti desnih lastnih vektorjev še na osnovi analize glavnih komponent in s k-d drevesi. V nalogi sta učinkovitost in robustnost postopka ocenjena s pomočjo rezultatov simulacij na modelu 39-vozliščnega IEEE sistema. Predstavljeni sta hitrost in natančnost postopka za različno velik nabor vhodnih podatkov ter v primerjavi s sprotnim izračunavanjem lastnih vrednosti in vektorjev. Predstavljena je tudi možnost združitve obeh postopkov, saj je na ta način mogoče izkoristiti prednosti obeh ter se hkrati izogniti njunim pomanjkljivostim.

Keywords

sprotna ocena stabilnosti EES;kotna stabilnost EES za majhne motnje;rudarjenje podatkov;nihajni nacin;analiza glavnih komponent;k-d drevesa;magisteriji;

Data

Language: Slovenian
Year of publishing:
Typology: 2.09 - Master's Thesis
Organization: UL FE - Faculty of Electrical Engineering
Publisher: [M. Škrlec]
UDC: 621.31(043.3)
COBISS: 165734147 Link will open in a new window
Views: 51
Downloads: 5
Average score: 0 (0 votes)
Metadata: JSON JSON-RDF JSON-LD TURTLE N-TRIPLES XML RDFA MICRODATA DC-XML DC-RDF RDF

Other data

Secondary language: English
Secondary title: Electric power system small signal stability assessment applying machine learning
Secondary abstract: Online monitoring of power system stability is essential for its reliability, especially if it includes a large amount of alternative energy sources. Each type of power system stability is unique, requiring a specialized approach for its assessment. In this thesis a new approach to small-signal stability assessment is presented, which does not require real time calculation of eigenvalues or eigenvectors. Considering that both are strongly dependent on power system operating conditions (list of operational power plants, their power infeed, power flow, topology), which are reoccurring to a certain extent, the proposed concept relies on a data base consisting of numerous foreseen/past operating conditions that have been analysed in advance. Screening for similarities within the database is something that is performed in real time. The core od similarity screening is a decision tree technique, which splits the original data in two layers, according to the list of operating power plants and topology. Only then screening of the database for most similar operating conditions is done by help of principal component analysis and k-d trees. In the thesis the efficiency and reliability of the method are tested on the IEEE 39 bus system. The speed and accuracy using different input values is assessed and compared to the speed and accuracy of the existing method. The possibility of combining both methods is also presented, thus using advantages of both methods and avoiding their deficiencies.
Secondary keywords: real time stability assessment of power systems;small signal stability of power systems;data mining;oscillation mode;principal component analysis;k-d trees;
Type (COBISS): Master's thesis/paper
Study programme: 1000316
Embargo end date (OpenAIRE): 1970-01-01
Thesis comment: Univ. v Ljubljani, Fak. za elektrotehniko
Pages: XII, 48 str.
ID: 19872232