Mitigation of Shunt Reactor Overvoltages Using Delta-Bar-Delta and Directed Random Search Algorithms

摘要

This paper introduces an intelligent-based method using artificial neural network (ANN) to reduce shunt reactor switching overvoltages. In power systems, an overvoltage could be caused by core saturation on the energization of a shunt reactor with residual flux. The most effective method for the limitation of the switching overvoltages is controlled switching since the magnitudes of the produced transients are strongly dependent on the closing instants of the switch. We introduce a harmonic index that it's minimum value is corresponding to the best case switching time. In addition, in this paper three learning algorithms, delta-bar-delta (DBD), extended delta-bar-delta (EDBD) and directed random search (DRS), were used to train the ANNs to estimate the optimum switching instants for real time applications. ANN is trained with equivalent circuit parameters of the network, so that developed ANN is applicable to every studied system. To verify the effectiveness of the proposed index and accuracy of the ANN-based approach, two case studies are presented and demonstrated.%W artykule przedstawiono metod? redukcji mo?liwych przepi?? ??czeniowych, wyst?puj?cych w reaktancji bocznikowej, przy wykorzystaniu algorytmu inteligentnego, opartego na sieciach neuronowych. Wyznaczono wska?nik okre?laj?cy najlepsze momenty prze??czeń, w zale?no?ci od pojawiaj?cych si? stanów nieustalonych. Do trenowania sieci neuronowej wykorzystano trzy algorytmy ucz?ce si?. Przedstawiono dwa przyk?ady potwierdzaj?ce skuteczno?? dzia?ania.