Neural network based power system stabilizers

摘要

Novel power system artificial neural network (ANN) based power system stabilizers (PSSs) are presented. The two ANN-PSS designs are driven by the speed error and its rate of change. Other supplementary stabilizing signals such as voltage deviation, excursion error, and PSS output rate of change are utilized to ensure the best matching between the ANN-PSS design and the optimized conventional analog PSS benchmark model. The use of ANN based PSSs is motivated by their noise rejection and robustness under varying network topologies, loading conditions, parametric variations, and model uncertainties.