An integrated data compression scheme for power quality events using spline wavelet and neural network

Spline wavelet (SW) is an optimum wavelet among the various existing wavelets which possesses some superior properties like regularity, best approximation and compactness at a given order over other conventional bases. In this paper a novel integrated approach for power quality data compression using the SW transform (SWT) and neural network is presented and its performance is assessed in terms of compression ratio (CR), mean square error and percentage of energy retained in the reconstructed signals. Varieties of power quality events including voltage sag, swell, momentary interruption, harmonics, transient oscillation and voltage fluctuation are used to test the performance of the proposed approach. Computer simulation results indicate that the proposed scheme offers superior compression performance compared to the conventional discrete cosine transform (DCT) and the discrete wavelet transform (DWT)-based approaches.