Bad data identification in voltage and reactive power control
Peipei Liu · Engineering Journal of Wuhan University · 2010
The voltage and reactive power control(VRPC)system may cause misoperation due to bad measurements without being identified effectively and accurately.In this paper,for the function and study of VRPC,according to the similarity and smoothness characteristics of the reactive load curve,reactive load curve is trained off-line,and predicted based on improved BP neural network.Through comparing the realtime reactive load data and forecasting load data to identify bad reactive data on-line.The results of the simulation show effectiveness and accuracy of the improved BP neural network.