Nova metoda detekcije propada napona u mreži sa distribuiranim generatorima
Novel method for detection of voltage dips in the grid with distributed generation
Author
Stanisavljević, AleksandarMentor
Katić, Vladimir
Committee members
Strezoski, VladimirDumnić, Boris
Grabić, Stevan
Mujović, Saša
Katić, Vladimir

Metadata
Show full item recordAbstract
U ovoj doktorskoj disertaciji je predstavljena je nova metoda za detekciju propada napona, zasnovana na Rekurentnoj neuronskoj mreži i analizi u harmonijskom domenu. Metoda je namenjena za primenu u savremenim distributivnim mrežama koje sadrže obnovljive izvore, i u skladu sa tim je optimizovana i testirana. Pametna metoda postiže izuzetne rezultate u brzini detekcije, sa prosečnim vremenom detekcije manjim od 1 ms, uz izuzetnu pouzdanost (preko 97%). U doktorskoj disertaciji dokazana je i druga hipoteza, a to je da je moguće predvideti dubinu propada algoritmom zasnovanim na harmonijskoj analizi.
In this PhD thesis, a novel method for the detection of voltage dips (sags), based on the Recurrent Neural Network and analysis in the frequency domain, is presented. The method is intended for use in the modern distribution grids that contains renewable sources, and accordingly it is optimized and tested. The smart method achieves exceptional results in detection speed, with an average detection time of less than 1 ms and with high reliability (over 97%). In the PhD thesis, another hypothesis is proved, which claims that is possible to predict the depth of dip with algorithm based on the harmonic analysis.