Untitled

Abstract

Original scientific paper The paper analyzes the possibility of reducing active power losses in power system, constrained by regulated voltage levels, by implementing appropriate distributed generation capacity. The objectives of this paper were achieved by developing hybrid methods based on artificial neural network and genetic algorithm. Methods have been developed to determine the impact of different distributed generation power on all terminals in the observed system. The method that uses artificial neural network and genetic algorithm is applicable for radial distribution networks, and method using load flow and genetic algorithm is applicable to doubly-fed distribution network. For comparison purposes, additional method was developed that uses neural networks for the decision-making process. Data for training the neural network was obtained by power flow calculation in the DIgSILENT PowerFactory software on a part of Croatian distribution network. The same software was used as an analytical tool for checking the correctness of solutions obtained by optimization. Keywords: artificial neural networks; distributed generation; genetic algorithm Kontrola naponskih prilika i gubitaka snage korištenjem distribuirane proizvodnje i računalne inteligencijeIzvorni znanstveni članak U radu se analizira mogućnost smanjenja aktivnih gubitaka elektroenergetskog sustava, uz poštivanje propisanih naponskih razina, primjenom odgovarajućih kapaciteta distribuirane proizvodnje. Ciljevi ovog rada ostvareni su razvojem hibridnih metoda baziranih na umjetnim neuronskim mrežama i genetskom algoritmu. Razvijene su metode za određivanje utjecaja distribuirane proizvodnje različitih snaga na svim čvorovima u promatranom sustavu. Metoda koja koristi umjetnu neuronsku mrežu i genetski algoritam primjenjiva je za radijalne distributivne mreže, a metoda koja koristi proračun tokova snaga i genetski algoritam primjenjiva je za dvostruko napajane distributivne mreže. S ciljem usporedbe razvijena je i metoda koja koristi neuronske mreže za proces odlučivanja o najboljem rješenju. Podaci za učenje neuronske mreže dobiveni su proračunom tokova snaga u programskom alatu DIgSILENT PowerFactory i to na djelu hrvatske distributivne mreže. Isti programski alat se koristi analitički kao sredstvo provjere ispravnosti rješenja dobivenih optimizacijom.