Correlation knowledge extraction based on data mining for distribution network planning

Traditional distribution network planning relies on the professional knowledge of planners, especially when analyzing the correlations between the problems existing in the network and the crucial influencing factors. The inherent laws reflected by the historical data of the distribution network are ignored, which affects the objectivity of the planning scheme. In this study, to improve the efficiency and accuracy of distribution network planning, the characteristics of distribution network data were extracted using a data-mining technique, and correlation knowledge of existing problems in the network was obtained. A data-mining model based on correlation rules was established. The inputs of the model were the electrical characteristic indices screened using the gray correlation method. The Apriori algorithm was used to extract correlation knowledge from the operational data of the distribution network and obtain strong correlation rules. Degree of promotion and chi-square tests were used to verify the rationality of the strong correlation rules of the model output. In this study, the correlation relationship between heavy load or overload problems of distribution network feeders in different regions and related characteristic indices was determined, and the confidence of the correlation rules was obtained. These results can provide an effective basis for the formulation of a distribution network planning scheme.