基于改进决策树的停电敏感度分析

当重要用户或敏感用户发生停电事件时,电网企业将面临较大压力,所以对用电敏感用户进行准确辨识,降低停电对其带来的损失具有重要意义。提出了采用蚁群算法优化决策树算法,主要从属性离散化,启发信息,信息素更新等方面进行优化。通过UCI数据库的分类数据建立仿真对比实验,与传统的SVM和决策树方法进行实验对比,验证了本文所提方法具有更高的分类准确性。将所提方法与传统的SVM和Logistic算法进行仿真对比,验证所提方法更适用于用户停电敏感度的分析。

Power Failure Sensitivity Analysis Based on Improved Decision Tree

If the power failure happens to important or sensitive users,the power grid enterprises will face on great pressure.Therefore,it is of great significance to accurately identify sensitive users and reduce the loss caused by power failure.An ant colony optimization decision tree algorithm is proposed,which is mainly optimized from the aspects of attribute discretization,heuristic information and pheromone updating.The simulation comparison experiment was established through the classification data of UCI database,and compared with the traditional SVM and decision tree methods,which verifies the higher classification accuracy of the proposed method in this paper.The proposed method in this paper is compared with the traditional SVM and Logistic algorithm to verify that it is more suitable for the analysis of user's power failure sensitivity.