Position Identification of Switched Capacitor Using Wavelet- and Kohonen- based Network

The transient caused by capacitor switching is an important power quality (PQ) problem. Switching the capacitor may cause a disturbance to a voltage-sensitive load or a resonance in the system. This paper presents a new method to identify the positions of the transients caused by capacitors through the PQ monitoring system. The discrete wavelet transform is used to extract the features of transients caused by capacitor switching. The signal energies attained by wavelet coefficients serve as inputs to the hybrid Kohonen-based Network (self-organizing feature mapping neural network, SOFMNN) for locating the transient sources. The output dimension of SOFMNN, which is cascaded to a multi-layer feedforward neural network, is discussed. The simulation results obtained from an 18-bus distribution system show the applicability of the proposed method.