Fault detection in smart grids with time-varying distributed generation using wavelet energy and evolving neural networks

Online monitoring systems have been developed for real-time detection of high impedance faults in power distribution networks. Sources of distributed generation are usually ignored in the analyses. Distributed generation imposes great challenges to monitoring systems. This paper proposes a wavelet transform-based feature-extraction method combined with evolving neural networks to detect and locate high impedance faults in time-varying distributed generation systems. Empirically validated IEEE models, simulated in the ATPDraw and Matlab environments, were used to generate data streams containing faulty and normal occurrences. The energy of detail coefficients obtained from different wavelet families such as Symlet, Daubechies, and Biorthogonal are evaluated as feature extraction method. The proposed evolving neural network approach is particularly supplied with a recursive algorithm for learning from online data stream. Online learning allows the neural models to capture novelties and, therefore, deal with nonstationary behavior. This is a unique characteristic of this type of neural network, which differentiate it from other types of neural models. Comparative results considering feed-forward, radial-basis, and recurrent neural networks as well as the proposed hybrid wavelet-evolving neural network approach are shown. The proposed approach has provided encouraging results in terms of accuracy and robustness to changing environment using the energy of detail coefficients of a Symlet-2 wavelet. Robustness to the effect of distributed generation and to transient events is achieved through the ability of the neural model to update parameters, number of hidden neurons, and connection weights recursively. New conditions could be captured on the fly, during the online operation of the system.