A method to recognize transient voltage disturbance in power system based on non-extensive wavelet entropy and ant colony optimization

Based upon Tsallis wavelet entropy (WE) and ant colony optimization (ACO), a novel method for the recognition of transient voltage disturbance was presented. The features of voltage disturbance were extracted with Tsallis wavelet energy entropy (WEE) algorithm, and from which the criterions of transient voltage disturbance were summarized to constitute classification rules with clustering algorithm. By analyzing the criterions of transient voltage disturbance, it can be found that there existed the redundancy criterions in classification rules, which verifies the necessity of optimizing classification rules. Through removing the redundancy criterions from classification rules based on ACO, the optimized classification rules were obtained. By use of Matlab/Simulink, a simulation model of transient voltage disturbance was built to verify the proposed method. Simulation results showed that this method can simplify the recognition process of the transient voltage disturbance, reduce the computing complexity and improve the classification accuracy.