联合改进SVR和渐消记忆递推最小二乘算法的电能表误差评估模型研究  

Research on error evaluation model of electricity meter combining improved SVR and fading memory recursive least squares algorithm

作　　者：王浩 杨鹏 李翀 申洪涛 薛强 李倩 WANG Hao;YANG Peng;LI Chong;SHEN Hongtao;XUE Qiang;LI Qian(State Grid Hebei Electric Power Company Marketing Service Center,Shijiazhuang 050000,China;State Grid Hebei Electric Power Company,Shijiazhuang 050000,China;School of Electrical and Electronic Engineering,Shijiazhuang Tiedao University,Shijiazhuang 050000,China)

机构地区：[1]国网河北省电力有限公司营销服务中心,河北石家庄050000 [2]国网河北省电力有限公司,河北石家庄050000 [3]石家庄铁道大学电气与电子工程学院,河北石家庄050000

出　　处：《电力科学与技术学报》2023年第5期206-215,共10页Journal of Electric Power Science And Technology

基　　金：国家自然科学基金(11872253);国网河北省电力公司科技项目(kj2021-056)。

摘　　要：针对电能计量装置运行误差现场检定难度大、定期轮换成本高等问题,提出一种联合麻雀搜索算法(SSA)、支持向量回归机(SVR)和渐消记忆递推最小二乘算法(FMRLS)的电能表误差评估模型。该方法首先利用改进的K-Means算法对台区进行分类,将分类后的样本导入利用SSA优化后的SVR模型进行训练,建立台区线损率预测模型;而后将得到的线损率代入改进的线损模型,构建电能表误差求解方程,利用FMRLS算法对误差方程进行求解,对电能表误差进行估计。通过河北省某低压台区样本的数据验证,该方法可以实现对低压台区线损率的有效预测,并估计出在运电能表的误差,为加快推进智能电能表检修策略由定期更换转向状态轮换提供技术保障。Aiming at the problems of on-site verification difficulties and high periodic replacement costs of electricity metering devices,a combined electric meter error assessment model is proposed,which integrates the sparrow search algorithm(SSA),support vector regression(SVR),and fading memory recursive least squares algorithm(FMRLS).Firstly,this method utilizes an improved K-Means algorithm to classify platform areas,and imports the classified samples into an SVR model optimized by the SSA for training to build a platform area line loss rate prediction model.Then,the obtained line loss rate is taken into the improved line loss model to construct an equation for solving electricity meter errors.The FMRLS algorithm is subsequently used to solve the error equation and estimate electricity meter errors.By validating the data from a sample of low-voltage platform areas in Hebei Province,this method can effectively predict the line loss rate in low-voltage platform areas and estimate the errors in electricity meters during operation.This provides technical support for accelerating the transition of the smart electricity meter maintenance strategy from regular replacement to state rotation.

关 键 词：智能电能表 台区线损率 SVR FMRLS算法 误差估计 

分 类 号：TM933[电气工程—电力电子与电力传动]