基于主成分分析与Wasserstein距离的低压用户相别识别

Phase Identification of Low Voltage Users Based on Principal Component Analysis and Wasserstein Distance

负载不平衡会导致电能质量差、功率损耗增加、变压器使用寿命缩短等问题,而准确识别用户相别可调整部分用户相别,尽可能达到三相负载平衡,因此提出一种基于主成分分析与Wasserstein距离的低压用户相别识别方法。首先利用主成分分析提取低压用户电压主成分进行聚类,然后计算聚类中值与关口各相电压Wasserstein距离进行相别归属。实测数据证明该方法对相别识别准确性较高,且相较于传统相似度算法在判别相别时具有明显区分度。

Load imbalance will cause problems such as poor power quality,increased power loss,and shortened transformer service life.Accurate identification of user phases can adjust some user phases to achieve three-phase load balance as much as possible.Therefore,a method based on principal component analysis and Low-voltage user phase identification method based on Wasserstein distance is proposed.First,the principal component analysis is used to extract the main components of the low-voltage user voltage for clustering,and then the Wasserstein distance is used to assign the clustering results to each other.The measured data proves that the method has higher accuracy for phase identification,and it has obvious distinguishing degree compared with the traditional similarity algorithm in distinguishing phases.