Study of Transformer Switching Overvoltages during Power System Restoration Using Delta-Bar-Delta and Directed Random Search Algorithms
Abstract In this paper an intelligent-based approach is introduced to evaluate harmonic overvoltages during three-phase transformer energization. In a power system that appears in an early stage of a black start of a power system, an overvoltage could be caused by core saturation on the energization of a three-phase transformer with residual flux. Such an overvoltage might damage some equipment and delay power system restoration. A new approach based on worst case determination is proposed to reduce time-domain simulations. Also, an artificial neural network (ANN) has been used to estimate the temporary overvoltages (TOVs) due to three-phase transformer energization. Three learning algorithms, delta-bar-delta (DBD), extended delta-bar-delta (EDBD), and directed random search (DRS), were used to train the ANNs. ANN Training is performed based on equivalent circuit parameters of the network; thus trained ANN is applicable to every studied system. The developed ANN is trained with the worst case of the switching condition and remanent flux, and tested for typical cases. The simulated results for a partial of 39-bus New England test system, show that the proposed technique can estimate the peak values and durations of switching overvoltages with good accuracy and EDBD algorithm presents best performance.