Spatial Load Distribution Law Based on Geographic Feature Extraction and Non-parametric Kernel Density Estimation

The research on spatial load is of great significance to distribution network planning. The existing research focuses on the study of spatial load prediction, but the study of various spatial load distribution law is not sufficient. Hence, a research method of spatial load distribution based on geographic feature extraction and non-parametric kernel density estimation is proposed in the paper. Firstly, the functional communities are generated according to the actual land use of a certain place, the geographic feature information of the functional communities is extracted, and the land use types are given. Then, a clustering algorithm is applied to classify the functional communities according to the extracted information. After that, the non-parametric kernel density estimation method is used to extract the typical distribution characteristics of the load density of functional communities of different geographical categories and different land-use types. Finally, the distribution characteristics are analyzed to derive the distribution patterns of various spatial loads in the research area. The reasonableness and practicality of this method are verified by the simulation of various spatial load distribution law in a certain geographical area of a first-tier city.