Application of a novel fuzzy neural network to real-time transientstability swings prediction based on synchronized phasor measurements

摘要

The ability to rapidly acquire synchronized phasor measurementsnfrom around a power system opens up new possibilities for power systemnprotection and control. In this paper, the authors develop a novel classnof fuzzy hyperrectangular composite neural networks which utilizensynchronized phasor measurements to provide fast transient stabilitynswings prediction for use with high-speed control. Primary features ofnthe method include constructing a fuzzy neural network for all faultnlocations, using a short window of realistic-precision post-fault phasornmeasurements for the prediction, and testing robustness to variations innthe operating point. From simulation tests on a sample power system, itnreveals that the proposed tool can yield a highly successful predictionnrate in real-time