Three-dimensional park portrait drawing method and system based on clustering algorithm

Abstract

The invention relates to a three-dimensional park portrait drawing method and system based on a clustering algorithm. The method comprises the following steps: carrying out clustering analysis on power consumption behaviors of users in a park by adopting a SpectralBiclustering biclustering algorithm to obtain power consumption behaviors of the users; analyzing the user energy configuration by adopting a Logistic curve model and an improved gray Verhulst model to obtain a user energy configuration maturity result; analyzing the user demand response by adopting a demand response evaluation algorithm based on the minimum load power consumption mode and the demand response load reduction rate to obtain a user demand response capability evaluation result; respectively clustering the user powerconsumption behaviors, the user energy configuration maturity results and the user demand response capability evaluation results to obtain user power consumption behavior features, user energy configuration features and user demand response features; and splicing the features to obtain a park portrait sequence. The method and the system can be applied to park portraits of a user group level, and park portrait analysis of quantitative description features is realized.

Description

technical field [0001] The invention relates to the field of park electricity management, in particular to a three-dimensional park portrait method and system based on a clustering algorithm. Background technique [0002] Since 2008, China's economic transformation has become an economic development mode that is too dependent on external demand growth, and promoting the optimization and upgrading of China's industrial structure has become an urgent and important strategic task related to the overall national economy. Developing the park economy and building leading industrial clusters can promote the adjustment of industrial structure and change the mode of economic growth in various places, so the construction of parks has been carried out in various places. The power consumption level of the park is relatively high, and there are large differences in the power consumption level of different parks, which increases the difficulty of power consumption management in the park. ...

AI Technical Summary

Problems solved by technology

However, the current clustering analysis is mostly based on the analysis of unlabeled data. In the analysis process, the data is regarded as a whole and the distance between different data is calculated. It is difficult to reflect the differences in the data and cannot extract local features.

For the park portrait model, 96 points of data need to be processed, that is, the local characteristics of the data and the differences in the data need to be considered. Therefore, it is difficult for traditional clustering algorithms to effectively perform cluster analysis in the park portrait model

In general, user profiling technology has been explored more in the fields of Internet recommendation systems such as books and travel, but it is only for profiling analysis at the user level and has not yet been applied to park profiling at the user group level.

Images