Research on Power Grid Over-voltage Anomaly Data Management Based on the Improved Clustering Algorithm

Abstract

The relational database uses distributed storage for grid over-voltage anomaly data, which lacks the division of the anomaly data, resulting in a long query time for anomaly data management. For this reason, the research of grid over-voltage anomaly data management based on the clustering algorithm is proposed. The clustering algorithm is combined with the outlier detection to divide the anomaly data and improve the query efficiency. The data are classified according to their characteristics. Row storage is selected as the main storage method for grid over-voltage anomaly data, and a three-dimensional model library is used to build out the management framework of the anomaly data to realize the efficient management of the anomaly data. In the experiment, the query time consumption of the proposed method is tested, and the analysis of the experimental results shows that the proposed method has a high query efficiency in managing the grid over-voltage anomaly data.