基于随机森林的非侵入式家庭负荷辨识方法

智能量测技术是智能电网的重要组成部分,文章为增强非侵入式家庭负荷辨识算法的适用性,提出了一种负荷低频监测技术,结合居民用电行为与外部非电力负荷特征相关特性,建立一种基于随机森林的家庭负荷监测模型,在该模型中,选取常用的电气特征以及引入诸如居民负荷使用的时间特征等外部数据特征,通过互信息分析方法筛选与用电行为关联度高的多维特征量,进而采用随机森林算法对居民用电行为进行建模,从而实现对不同家庭各个类型的负荷进行有效监测。算法运行在AMPds公开数据集上,与贝叶斯分类算法进行比较,验证了所提算法的有效性。

Nonintrusive household load identification method based on random forest

Intelligent measurement technology is an important part of smart grid.In order to enhance the applicability of the non-intrusive household load identification algorithm,this paper proposes a low frequency monitoring technology,and combined with residential electricity behavior associated with external non-electric load characteristic,a household load monitoring model is built based on random forest.In this model,firstly,the commonly used electrical characteristics as well as the introduction of external data such as the time characteristics of resident load characteristics,through the analysis of the mutual information selection method and multi-dimensional characteristics of high electricity behavior correlation,and the random forest algorithm is adopted to model the residential electricity behavior,so as to realize the effective monitoring of different types of load in different families.Finally,the algorithm runs on the AMPds open data set and compares with the Bayesian classification algorithm,and the results verify the effectiveness of the proposed algorithm.