一种新K-means聚类算法的多元线性回归台区线损率预测模型  

Prediction model of line loss rate in the station area based on the multivariate linear regression integrated with a new K-means clustering algorithm

作　　者：张裕 徐依明 张彦 赵庆明 罗宁 杨兴武 ZHANG Yu;XU Yiming;ZHANG Yan;ZHAO Qingming;LUO Ning;YANG Xingwu(Research Center of Guizhou Power Grid Planning Limited Liability Company,Guiyang 550002,China;Electric Power Engineering,Shanghai University of Electric Power,Shanghai 200082,China)

机构地区：[1]贵州电网有限责任公司电网规划研究中心,贵州贵阳550002 [2]上海电力大学电气工程学院,上海200082

出　　处：《电力科学与技术学报》2021年第5期179-186,共8页Journal of Electric Power Science And Technology

基　　金：贵州电网有限责任公司科技项目(GZKJXM20172673);国家自然科学基金(51207086)。

摘　　要：线损率是反映线损管理的重要依据,由于其理论计算的复杂性,一直倍受电力工作者的广泛关注。基于国内外线损管理研究现状以及相关理论计算方法,提出一种基于K-means聚类算法的多元线性回归模型预测台区线损率方法。首先,利用K-means聚类算法对台区样本数据聚类分析,根据聚类结果建立线性回归预测模型计算台区线损率。然后,通过预测线损率与实际线损率比较分析,对线损估计误差较大的台区重点关注。最后,以贵州部分地区的台区样本数据为依据,验证所提方法的准确性与快速性,为贵州地区的线损管理提供理论依据。The line loss rate is an important basis to reflect line loss management.Due to the complexity of its theoretical calculation,it has been widely concerned by power workers.Based on the current research status of line loss management at home and abroad and related theoretical calculation methods,a multiple linear regression model based on the K-Means clustering algorithm is proposed to predict the line loss rate of the station area.Firstly,the proposed K-Means clustering algorithm is utilized to cluster and analyze the sample data of the station area.Linear regression prediction models are established to calculate the line loss rate of the station area according to the clustering results.Then,through the comparison and analysis of the predicted line loss rate and the actual line loss rate,much attention is paid on the stations with large errors in line loss estimation.Finally,Finally,based on the sample data of some regions in Guizhou,the accuracy and rapidity of the proposed method are verified,which provides a theoretical basis for line loss management in Guizhou.

关 键 词：线损率 K-MEANS聚类算法 聚类分析 预测计算 

分 类 号：TM74[电气工程—电力系统及自动化]