Voltage sag is one of the most serious problems in power quality. The occurrence of voltage sag will lead to a huge loss in the social economy and have a serious effect on people’s daily life. The identification of sag types is the basis for solving the problem and ensuring the safe grid operation. Therefore, with the measured data uploaded by the sag monitoring system, this paper proposes a sag type identification algorithm based on K-means-Singular Value Decomposition (K-SVD) and Least Squares Support Vector Machine (LS-SVM). Firstly; each phase of the sag sample RMS data is sparsely coded by the K-SVD algorithm and the sparse coding information of each phase data is used as the feature matrix of the sag sample. Then the LS-SVM classifier is used to identify the sag type. This method not only works without any dependence on the sag data feature extraction by artificial ways, but can also judge the short-circuit fault phase, providing more effective information for the repair of grid faults. Finally, based on a comparison with existing methods, the accuracy advantages of the proposed algorithm with be presented.
Accurately determining power consumer harmonic contribution determination is an effective method to solve power quality disputes and alleviate harmonic pollution of power grids. This paper proposes a multi-harmonic sources harmonic contribution determination algorithm based on data filtering and cluster analysis. Aiming at the problem of background harmonic fluctuation, this paper uses the cross-approximation entropy (CAE) algorithm to filter the effective data segments of the harmonic voltage and current at the point of common coupling (PCC) to avoid the interference caused by background harmonics. For the problem of harmonic impedance changes of system, using the density-based spatial clustering of applications with noise (DBSCAN) clustering algorithm to detect the harmonic impedance changes of the system. The harmonic contribution under different system harmonic impedance is calculated based on the data of each class cluster. The accuracy of the proposed method is improved compared with existing methods. The experimental analysis demonstrates the effectiveness and superiority of the algorithm.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.